阅读说明：本技术 用于预测对pd-1轴导向疗法的应答的方法和系统 (Methods and systems for predicting response to PD-1 axis guided therapy ) 是由 M·霍贾斯泰 J·马丁 L·佩斯蒂克-德拉戈维奇 L·唐 X·王 W·张 R·安德斯 于 2019-09-30 设计创作，主要内容包括：本发明提供一种评分函数,所述评分函数经过开发并用于鉴定可能对PD-1轴导向疗法有应答的患者。所述评分函数通过以下步骤获得：从多重染色切片提取特征,使用特征选择函数选择与对所述疗法的应答有关的特征,以及将所选特征中的一者或多者拟合至多个候选评分函数。然后,可以选择表明预测灵敏度和特异性之间所需平衡的候选评分函数,以纳入至少包括图像分析系统的评分系统中。(The present invention provides a scoring function that has been developed and used to identify patients who are likely to respond to PD-1 axis-directed therapy. The scoring function is obtained by: extracting features from the multiplicity of stained sections, selecting features relevant to a response to the therapy using a feature selection function, and fitting one or more of the selected features to a plurality of candidate scoring functions. Candidate scoring functions that indicate a desired balance between predictive sensitivity and specificity can then be selected for inclusion in a scoring system that includes at least an image analysis system.)

1. A method of scoring a tumor sample for a likelihood of response to PD-1 axis-directed therapy, the method comprising:

(a) obtaining a digital image of a tumor section from the tumor sample, wherein the tumor section is stained for each of PD-L1, CD8, CD3, CD68, and Epithelial Markers (EM) with multiple affinity histochemical stains;

(b) extracting a feature metric from a region of interest (ROI) in the image, the feature metric selected from the group consisting of:

(i) CD8 in the ROI⁺Cells were compared with the most recent PD-L1⁺/CD68⁺The average distance between the cells is determined,

(ii) CD8 in the ROI⁺Cells were compared with the most recent PD-L1⁺/CD3⁺The average distance between the cells is determined,

(iii) epithelial cells and the nearest CD8 in the ROI⁺The average distance between the cells is determined,

(iv) in the ROI at CD8⁺PD-L1 within 10 μm of cells⁺The number of epithelial cells in the cell line,

(v) in the ROI at CD8⁺PD-L1 within 30 μm of cells⁺Number of epithelial cells

(vi) CD8 within 10 μm of epithelial cells in the ROI⁺Number of cells

(vii) CD8 within 30 μm of epithelial cells in the ROI⁺Number of cells

(viii) PD-L1 in the ROI⁺/CD3⁺Density of cells

(ix) PD-L1 in the ROI⁺/CD3⁺/CD8^–Density of cells

(x) PD-L1 in the ROI⁺/CD8⁺Density of cells

(xi) PD-L1 in the ROI⁺/CD68⁺Density of cells

(xii) PD-L1 in the ROI⁺Density of epithelial cells

(xiii) CD3 in the ROI⁺Density of cells

(xiv) CD8 in the ROI⁺Density of cells

(xv) CD68 in the ROI⁺Density of cells

(xvi) Density of epithelial cells in the ROI

(xvii) The ROPD-L1 in I⁺Ratio between the area occupied by epithelial cells and the total area of the ROI

(xviii) Ratio between area occupied by epithelial cells in the ROI and total area of the ROI

(xix) PD-L1 in the ROI⁺Ratio between number of epithelial cells and total number of epithelial cells in the ROI

(xx) PD-L1 in the ROI⁺/CD3⁺Number of cells and CD3 in the ROI⁺Ratio between total number of cells

(xxi) PD-L1 in the ROI⁺/CD3⁺/CD8^–Number of cells and CD3 in the ROI⁺/CD8^–Ratio between total number of cells

(xxii) PD-L1 in the ROI⁺/CD8⁺Number of cells and CD8 in the ROI⁺Ratio between total number of cells

(xxiii) PD-L1 in the ROI⁺/CD68⁺Number of cells and CD68 in the ROI⁺Ratio between total number of cells

(xxiv) PD-L1 in the ROI⁺/CD3⁺/CD8^–Number of cells and CD3 in the ROI⁺/CD8^–The ratio between the total number of cells,

(xxv) CD3 in the ROI⁺/CD8^–Number of cells and CD3 in the ROI⁺The ratio between the total number of cells,

(xxvi)CD3⁺the total area occupied by the cells, and

(xxvii)CD3⁺the total area occupied by the cells; and

(c) applying a scoring function to a feature vector comprising the feature metrics to generate a score indicative of a likelihood that a tumor will respond to the PD-1 axis-directed therapy.

2. The method of claim 1, wherein the ROI is selected from the group consisting of: tumor ROI, stromal (ROI), epithelial marker Positive (EM)⁺) ROI, epithelial marker negative (EM)^–) ROI, peri-medial (PI) ROI, peri-cancerLateral (PO) ROI and peri-cancerous region (PR) ROI.

3. The method of claim 2, wherein the ROI is the interstitial ROI or the EM^–The ROI, and the feature vector comprises one or more feature metrics selected from the group consisting of:

(xx) PD-L1 in the ROI⁺/CD3⁺Number of cells and CD3 in the ROI⁺The ratio between the total number of cells,

(xxii) PD-L1 in the ROI⁺/CD8⁺Number of cells and CD8 in the ROI⁺The ratio between the total number of cells,

(xxiii) PD-L1 in the ROI⁺/CD68⁺Number of cells and CD68 in the ROI⁺The ratio between the total number of cells, and

(xxiv) PD-L1 in the ROI⁺/CD3⁺/CD8^–Number of cells and CD3 in the ROI⁺CD8^–The ratio between the total number of cells.

4. The method of claim 3, wherein the feature vector comprises each of: the interstitial ROI or the EM^–PD-L1 in ROI⁺/CD68⁺Number of cells and the interstitial ROI or the EM^–CD68 in ROI⁺Ratio between total number of cells, the interstitial ROI or the EM^–PD-L1 in ROI⁺/CD3⁺/CD8^–Number of cells and the interstitial ROI or the EM^–CD3 in ROI⁺/CD8^–The ratio between the total number of cells, and

the interstitial ROI or the EM^–PD-L1 in ROI⁺/CD3⁺Number of cells and the interstitial ROI or the EM^–CD3 in ROI⁺The ratio between the total number of cells.

5. The method of claim 2, wherein the ROI is the tumor ROI or the EM⁺ROI, and the feature vector includes a selectionOne or more feature metrics selected from the group consisting of:

(i) the EM⁺CD8 in ROI or tumor ROI⁺Cells were compared with the most recent PD-L1⁺/CD68⁺The average distance between the cells is determined,

(ix) PD-L1 in the ROI⁺/CD3⁺/CD8^–The density of the mixture is higher than the density of the mixture,

(xx) PD-L1 in the ROI⁺/CD3⁺Number of cells and CD3 in the ROI⁺The ratio between the total number of cells,

(xxii) The EM⁺PD-L1 in ROI or tumor ROI⁺/CD8⁺Number of cells and the EM⁺CD8 in ROI or tumor ROI⁺The ratio between the total number of cells,

(xxiii) PD-L1 in the ROI⁺/CD68⁺Number of cells and CD68 in the ROI⁺The ratio between the total number of cells,

(xxiv) PD-L1 in the ROI⁺/CD3⁺/CD8^–Number of cells and CD3 in the ROI⁺CD8^–The ratio between the total number of cells, and

(xxv) The EM⁺CD3 in ROI or tumor ROI⁺/CD8^–Number of cells and the EM⁺CD3 in ROI or tumor ROI⁺The ratio between the total number of cells.

6. The method of claim 1, wherein the ROI is derived from a digital image of a morphologically stained section of the tumor sample, wherein the morphologically stained section and a multiple affinity histochemical stained sample are serial sections.

7. The method of claim 1, wherein the ROI is identified by a user in the digital image of the morphologically stained section and automatically registered in the digital image of the multi-affinity histochemical stained section.

8. A method of scoring a tumor sample for a likelihood of response to PD-1 axis-directed therapy, the method comprising:

(a) obtaining a digital image of a tumor section from the tumor sample, wherein the tumor section is stained for each of PD-1, PD-L1, CD8, Lag3, and one or more epithelial markers with multiple affinity histochemical stains;

(b) extracting a feature metric from a region of interest (ROI) in the image, the feature metric selected from the group consisting of the feature metrics listed in Table 9; and

(c) applying a scoring function to a feature vector comprising the feature metrics to generate a score indicative of a likelihood that a tumor will respond to the PD-1 axis-directed therapy.

9. The method of claim 8, wherein the ROI is selected from the group consisting of: tumor ROI, interstitial ROI, epithelial marker Positive (EM)⁺) ROI, epithelial marker negative (EM)^–) ROI, medial carcinostatic (PI) ROI, lateral carcinostatic (PO) ROI, and peri-cancerous region (PR) ROI.

10. The method of claim 8, wherein the feature metric is selected from the group consisting of:

(i)PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The maximum number of the first and second groups,

(ii)CD8⁺the maximum value of the intensity of PD-L1 of the cells,

(iii) PD-1 in epithelial region⁺/PD-L1^–/Lag3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells to one another,

(iv)PD-L1⁺PD-1 within a 20 μm radius of a cell⁺The spatial variance number of the cells,

(v) the maximum value of the PD-L1 intensity for all cells,

(vi)EM⁺the number of bag 3 positive cells in the ROI,

(vii) PD-L1 in EM-ROI⁺/EM^–The density of the cells is such that,

(viii)EM⁺PD-L1 in ROI⁺The number of the cells is determined by the number of the cells,

(ix) PD-L1 in EM-ROI⁺The number of the cells is determined by the number of the cells,

(x) PD-1 in EM-ROI⁺The number of the cells is determined by the number of the cells,

(xi)PD-L1⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The maximum number of cells in the culture medium,

(xii)PD-L1⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The average number of cells is the number of cells,

(xiii) From CD8⁺Lag3⁺The maximum value of the cell, the bag 3 intensity,

(xiv)EM⁺CD8 in ROI⁺The number of the cells is determined by the number of the cells,

(xv)PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The variance of the number of cells is determined,

(xvi) From PD-L1⁺Cell to its nearest PD-1⁺The average distance of the cells is determined,

(xvii)PD-L1⁺/EM⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The maximum number of cells in the culture medium,

(xviii) From PD-L1 in the ROI⁺Cell to its nearest PD-1⁺The standard deviation of the distance of the cells,

(xix)EM⁺lan 3 in ROI⁺/CD8⁺Number of cells and CD8⁺The ratio of the number of cells to one another,

(xx)EM⁺PD-L1 in ROI⁺/CD8⁺Number of cells and CD8⁺The ratio of the number of cells to one another,

(xxi)PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}/CD8⁺The average number of cells is the number of cells,

(xxii)PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}/CD8⁺The variance of the number of cells is determined,

(xxiii) From all PD-1⁺The average value of the PD-1 intensity of the cells,

(xxiv) From all of the lads 3⁺Bag 3 strength of cellsThe minimum value of (a) is determined,

(xxv)EM⁺PD-L1 in ROI⁺/EM⁺The density of the cells is such that,

(xxvi)PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}/CD8⁺The maximum number of cells in the culture medium,

(xxvii)EM⁺PD-1 in ROI⁺The number of the cells is determined by the number of the cells,

(xxviii) PD-1 in EM-ROI⁺/PD-L1^–/Lag3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells, and

(xxix) From CD8⁺/Lag3⁺The maximum value of the lang 3 intensity of the cells,

(xxx)EM^-lan 3 in ROI⁺/CD8⁺Number of cells and CD8⁺The ratio of the number of cells, and

(xxxi)EM⁺number of bag 3 positive cells in ROI.

11. The method of claim 8, wherein the feature metric is selected from the group consisting of:

PD-L1 in the EM + ROI or the tumor ROI⁺CD8 within 20 μm of cells⁺/PD-1_{Is low in}The maximum number of cells in the culture medium,

PD-L1⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The average number of cells is the number of cells,

CD8⁺/Lag3⁺the maximum of the lang 3 intensity in the cells,

PD-L1⁺PD-1 within a 20 μm radius of a cell⁺Average number of cells, and

CD8⁺lan 3 on cells⁺The maximum value of the intensity.

12. The method of claim 8, wherein the feature vector comprises each of:

PD-L1 in EM + ROI⁺CD8 within 20 μm of cells⁺/PD-1_{Is low in}The maximum number of cells in the culture medium,

PD-L1⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The average number of cells is the number of cells,

CD8⁺/Lag3⁺the maximum of the lang 3 intensity in the cells,

PD-L1⁺PD-1 within a 20 μm radius of a cell⁺Average number of cells, and

CD8⁺lan 3 on cells⁺The maximum value of the intensity.

13. The method of claim 8, wherein the feature metric is selected from the group consisting of:

EM^–in region bag 3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells to one another,

Lag3⁺/EM^–number of cells divided by the EM^–The area of the ROI,

the EM^–Lan 3 in ROI⁺The number of the cells is determined by the number of the cells,

CD8⁺the maximum value of the intensity of bag 3 in the cells,

the EM⁺Lan 3 in ROI⁺The number of the cells is determined by the number of the cells,

PD-L1⁺/EM⁺PD-1 within a 10 μm radius of a cell_In/CD8⁺The average number of cells is the number of cells,

PD-L1⁺/EM⁺PD-1 within a 20 μm radius of a cell_In/CD8⁺The average number of cells is the number of cells,

PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_In/CD8⁺The variance of the cells is determined by the variance of the cells,

PD-L1⁺/EM⁺PD-1 within a 20 μm radius of a cell_In/CD8⁺The variance of the cells is determined by the variance of the cells,

PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}/CD8⁺The variance of the cells is determined by the variance of the cells,

PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_In/CD8⁺Maximum number of cells, and

PD-L1⁺PD-1 within a 20 μm radius of a cell_In/CD8⁺Maximum number of cells.

14. The method of claim 8, wherein the ROI is derived from a digital image of a morphologically stained section of the tumor sample, wherein the morphologically stained section and a multiple affinity histochemical stained sample are serial sections.

15. The method of claim 9, wherein the ROI is identified by a user in the digital image of the morphologically stained section and automatically registered in the digital image of the multi-affinity histochemical stained section.

16. The method of any one of claims 1 to 15, wherein the scoring function is derived from a modeling function selected from the group consisting of: quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN).

17. The method of claim 16, wherein the scoring function is a QDA model fitted to selected features to predict response to treatment, and wherein treatment outcomes for fitting the QDA model are combined together in a configuration selected from the group consisting of:

progressive Disease (PD) versus Stable Disease (SD) versus Partial Response (PR) + Complete Response (CR);

PD vs SD + PR + CR; and

PD + SD vs PR + CR.

18. A method of selecting a patient to receive PD-1 axis guidance therapy, the method comprising:

generating a score according to the method of any one of claims 1 to 17,

comparing the score with a predetermined cutoff value, an

Selecting a patient to receive the PD-1 axis therapy or replacement therapy based on whether the score is above or below the predetermined cutoff value.

19. A method of treating a patient with PD-1 axis guidance therapy, the method comprising:

the method of claim 19, selecting a patient to receive the PD-1 axis guidance therapy; and

administering the PD-1 axis-directed therapy to the patient.

20. The method of claim 19, wherein the PD-1 axis-directed therapy is a PD-1-specific monoclonal antibody or a PD-L1-specific monoclonal antibody.

21. The method of claim 19, wherein the PD-1 axis-directed therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

22. A method of developing a scoring function for predicting tumor response to PD-1 axis-directed therapy, the method comprising:

(a) obtaining:

(i) a set of digital images of tumor tissue samples obtained from a plurality of patients prior to treatment with the PD-1 axis guidance therapy, wherein at least one digital image of each patient is a digital image of a tissue section stained with multiple affinity histochemical stains for each of one or more epithelial markers, one or more immune cell markers, and one or more PD-1 axis pathway markers; and

(ii) post-treatment response data for each patient;

(b) extracting a plurality of feature metrics from the digital image of a multiply stained tissue section, the plurality of feature metrics selected from the group consisting of the features of table 4;

(c) applying a feature selection function to the extracted plurality of feature metrics and the post-treatment response data to obtain an ordering for each feature of the strength of correlation with response to the PD-1 axis guided therapy;

(d) applying a modeling function to one or more of the ranked features and the post-treatment response data to generate a plurality of candidate models that predict response to checkpoint inhibitor therapy, and testing each candidate model for consistency with response; and

(e) selecting the candidate model with the highest agreement with the response as the scoring function.

23. The method of claim 22, wherein the multiple affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68, and Epithelial Markers (EM) (group 1), and the features are selected from the group consisting of the features in the left column of table 4.

24. The method of claim 22, wherein the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, PD1, CD8, LAG3 and Epithelial Markers (EM) (group 2), and the features are selected from the group consisting of the features in the right column of table 4.

25. The method of claim 22, wherein the feature selection function is selected from the group consisting of: set feature selection methods (including, for example, random forest functions), filtering methods (including, for example, mutual information based functions (mRMR)/correlation coefficient based functions and Relief based functions), and/or embedded feature selection functions (e.g., elastic network/minimum absolute shrinkage function or selection operator (LASSO) functions).

26. The method of claim 22, wherein the candidate model is made using one or more of the top 25, top 20, top 15, top 10, top 9, top 8, top 7, top 6, top 5, top 4, or top 3 features identified by the feature selection function.

27. The method of claim 26, wherein the candidate model uses at least 1, at least 2, at least 3, at least 4, or at least 5 features identified in the top 10 features of the feature selection function.

28. The method of claim 26, wherein the candidate model comprises at least one feature that is present in the top 5 features of at least 2 feature selection functions.

29. The method of claim 22, wherein the modeling function is selected from the group consisting of: quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN).

30. The method of claim 29, wherein the scoring function is a QDA model fitted to selected features to predict response to treatment.

31. The method of claim 30, wherein the treatment outcomes for fitting the QDA model are combined together in a configuration selected from the group consisting of:

progressive Disease (PD) versus Stable Disease (SD) versus Partial Response (PR) + Complete Response (CR);

PD vs SD + PR + CR; and

PD + SD vs PR + CR.

32. A method, the method comprising:

(a) labeling a region of interest (ROI) on a digital image of a test sample of a tumor, wherein the digital image is a digital image of a sample that is subjected to multiple affinity staining for PD-L1, CD8, CD3, CD68, and Epithelial Markers (EM) (group 1);

(b) extracting one or more feature metrics from the ROI of the left column of table 4; and

(c) applying a scoring function obtained according to the method of any one of claims 29 to 31 to a feature vector comprising one or more features of (b).

33. The method of claim 32, wherein the ROI is labeled in a digital image of a first continuous section of the test sample, wherein the first continuous section is stained with hematoxylin and eosin, and wherein the ROI is automatically enrolled into a digital image of at least a second continuous section of the test sample, wherein the second continuous section is stained with set 1.

34. A method, the method comprising:

(a) labeling a region of interest (ROI) on a digital image of a test sample of a tumor, wherein the digital image is a digital image of a sample that is subjected to multiple affinity staining for PD-L1, PD-1, CD8, LAG3, and epithelial markers (panel 2);

(b) extracting one or more feature metrics from the ROI in the right column of Table 4; and

(c) applying a scoring function obtained according to the method of any one of claims 29 to 31 to a feature vector comprising one or more features of (b).

35. The method of claim 34, wherein the ROI is identified in digital images of a first continuous section of the test sample, wherein the first continuous section is stained with hematoxylin and eosin, and wherein the ROI is automatically enrolled into digital images of at least a second continuous section of the test sample, wherein the second continuous section is stained with set 2.

36. A system for predicting a patient's response to PD-1 axis therapy, the system comprising: a processor; and a memory coupled with the processor, the memory to store computer-executable instructions that, when executed by the processor, cause the processor to perform operations comprising one or more methods of any of claims 1-35.

37. The system of claim 36, further comprising a scanner or microscope adapted to capture a digital image of a section of the tissue sample and transmit the image to a computer device.

38. The system of claim 36, wherein the system further comprises an automated slide stainer programmed to histochemically stain sections of the tissue sample with group 1 or group 2.

39. The system of claim 38, wherein the system further comprises an automated hematoxylin and eosin stainer programmed to stain one or more consecutive sections of the section stained by the automated slide stainer.

40. The system of any one of claims 36 to 39, further comprising a Laboratory Information System (LIS) for tracking sample and image workflows and diagnostic information, the LIS comprising a central database configured to receive and store information related to the tissue sample, the information comprising at least one of: a processing step to be performed on the tumor tissue sample, a processing step to be performed on a digital image of a section of the tumor tissue sample, a processing history of the tumor tissue sample and the digital image; and one or more clinical variables (e.g., MMR or MSI status) that correlate with the likelihood that the patient will respond to the therapy.

41. A non-transitory computer-readable storage medium storing computer-executable instructions for execution by a processor to perform operations comprising the method of any of claims 1-35.

42. A method of treating a patient having a tumor, the method comprising identifying a level of a characteristic of the tumor that indicates the tumor is likely to respond to PD-1 axis directed therapy, and administering the PD-1 axis directed therapy to the patient, wherein the characteristic is selected from the group consisting of:

(a) interstitial PD-L1⁺/CD3⁺Number of cells and interstitial CD3⁺The ratio between the total number of cells,

(b) interstitial PD-L1⁺/CD8⁺Number of cells and interstitial CD8⁺The ratio between the total number of cells,

(c) interstitial PD-L1⁺/CD68⁺Number of cells and interstitial CD68⁺The ratio between the total number of cells, and

(d) interstitial PD-L1⁺/CD3⁺/CD8^–Number of cells and interstitial CD3⁺CD8^–Ratio between total number of cells

(e) Epithelial CD8⁺Cells were compared with the most recent PD-L1⁺/CD68⁺The average distance between the cells is determined,

(f) epithelial PD-L1⁺/CD3⁺/CD8^–The density of the cells is such that,

(g) epithelial PD-L1⁺/CD3⁺Number of cells and epithelial CD3⁺The ratio between the total number of cells,

(h) the ratio between the number of epithelial PD-L1+/CD8+ cells in the EM + ROI or tumor ROI and the total number of epithelial CD8+ cells in the EM + ROI or tumor ROI,

(i) the ratio between the number of epithelial PD-L1+/CD68+ cells in the ROI and the total number of epithelial CD68+ cells in the ROI,

(j) the ratio between the number of epithelial PD-L1+/CD3+/CD 8-cells in the ROI and the total number of epithelial CD3+/CD 8-cells in the ROI,

(k) the ratio between the number of epithelial CD3+/CD 8-cells in the EM + ROI or tumor ROI and the total number of epithelial CD3+ cells in the EM + ROI or tumor ROI,

(l)PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The maximum number of the first and second groups,

(m)CD8⁺the maximum value of the intensity of PD-L1 of the cells,

(n) PD-1 in epithelial region⁺/PD-L1^–/Lag3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells to one another,

(o)PD-L1⁺PD-1 within a 20 μm radius of a cell⁺The number of spatial variances of the cells,

(p) the maximum value of the intensity of PD-L1 for all cells,

(q)EM⁺the number of bag 3 positive cells in the ROI,

(r) PD-L1 in EM-ROI⁺/EM^–The density of the cells is such that,

(s)EM⁺PD-L1 in ROI⁺The number of the cells is determined by the number of the cells,

(t) PD-L1 in EM-ROI⁺The number of the cells is determined by the number of the cells,

(u) PD-1 in EM-ROI⁺The number of the cells is determined by the number of the cells,

(v)PD-L1⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The maximum number of cells in the culture medium,

(w)PD-L1⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The average number of cells is the number of cells,

(x) From CD8⁺Lag3⁺The maximum value of the cell, the bag 3 intensity,

(y)EM⁺CD8 in ROI⁺The number of the cells is determined by the number of the cells,

(z)PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The variance of the number of cells is determined,

(aa) from PD-L1⁺Cell to its nearest PD-1⁺The average distance of the cells is determined,

(bb)PD-L1⁺/EM⁺PD-1 within a 20 μm radius of a cell_{Is low in}/CD8⁺The maximum number of cells in the culture medium,

(cc) from PD-L1⁺Cell to its nearest PD-1⁺The standard deviation of the distance of the cells,

(dd)EM⁺lan 3 in ROI⁺/CD8⁺Number of cells and CD8⁺The ratio of the number of cells to one another,

(ee)EM⁺PD-L1 in ROI⁺/CD8⁺Number of cells and CD8⁺The ratio of the number of cells to one another,

(ff)PD-L1⁺PD-1 within a cell radius of 10 μm_{Is low in}/CD8⁺The average number of cells is the number of cells,

(gg)PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}/CD8⁺The variance of the number of cells is determined,

(hh) from all PD-1⁺The average value of the PD-1 intensity of the cells,

(ii) from all of the lads 3⁺The minimum value of the lang 3 intensity of the cells,

(jj)EM⁺PD-L1 in ROI⁺/EM⁺The density of the cells is such that,

(kk)PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}/CD8⁺The maximum number of cells in the culture medium,

(ll)EM⁺PD-1 in ROI⁺The number of the cells is determined by the number of the cells,

(mm) PD-1 in EM-ROI⁺/PD-L1^–/Lag3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells to one another,

(nn) from CD8⁺/Lag3⁺The maximum value of the lang 3 intensity of the cells,

(oo)EM^-lan 3 in ROI⁺/CD8⁺Number of cells and CD8⁺The ratio of the number of cells, and

(pp)EM⁺number of bag 3 positive cells in ROI.

43. A method of treating a patient having a tumor, the method comprising identifying a level of a characteristic of the tumor that indicates the tumor is likely to respond to PD-1 axis directed therapy, and administering the PD-1 axis directed therapy to the patient, wherein the characteristic is selected from the group consisting of:

(a) bag 3 in the panCK-negative region⁺/CD8⁺Cellular and Total CD8⁺The ratio of the number of cells;

(b) bag 3 in the panCK-negative region^–/CD8⁺Cells and CD8⁺The ratio of the number of cells to one another,

(c)Lag3⁺/panCK^–the number of cells divided by the panCK-negative area,

(d) the number of Lan 3 positive cells in the panCK negative region,

(e)CD8⁺the maximum value of the intensity of bag 3 in the cells,

(f) number of Lan 3+ cells in the panCK-positive region,

(g)PD-L1⁺/panCK⁺PD-1 within a 10 μm radius of a cell_InThe average number of/CD 8+ cells,

(h)PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_InThe average number of/CD 8+ cells,

(i)PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_InThe variance of the number of/CD 8+ cells,

(j)PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_InThe variance of the number of/CD 8+ cells,

(k)PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}The variance of the number of/CD 8+ cells,

(l)PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_InMaximum number of/CD 8+ cells, and

(m)PD-L1⁺PD-1 within a 20 μm radius of a cell_InMaximum number of/CD 8+ cells.

Technical Field

The present invention relates to the detection, characterization and enumeration of biomarkers in tumor samples for predicting response to checkpoint inhibitor therapy.

Background

Cancer can escape immune monitoring and eradication by up-regulating the programmed death 1(PD-1) pathway and its ligand programmed death ligand 1(PD-L1) on tumor cells and in the tumor microenvironment. Blocking this pathway with antibodies against PD-1 or PD-L1 has led to significant clinical responses in certain cancer patients. However, identifying predictive biomarkers for patient selection is a significant challenge.

PD-L1 is the most widely used predictive biomarker for selecting patients to receive PD-1 axis-directed therapy. However, the observed results are not consistent. See Yi.

Mismatch Repair (MMR) deficiency predicts the response of solid tumors to PD-1 blockade. See le (I) and le (II). However, not all patients with mismatch repair defects respond to PD-1 blocking therapy. Predictive value is limited for variable strength of association between study and tumor type.

Recent studies have shown that the spatial arrangement and interaction between cancer cells and immune cells can affect patient prognosis, survival, and response to treatment. Wang and Barrera.

There is an increasing need to understand the microenvironment of tumors and related biomarkers to guide cancer immunotherapy.

Disclosure of Invention

The present disclosure relates generally to systems and methods for identifying and using novel biomarkers to predict the response of solid tumors to PD-1 axis guided therapy.

In a certain embodiment, a method of developing a scoring function for predicting tumor response to PD-1 axis-directed therapy, the method comprising: (a) obtaining: (a1) a set of digital images of tumor tissue samples obtained from a plurality of patients prior to treatment with the PD-1 axis guidance therapy, wherein at least one digital image of each patient is a digital image of a tissue section stained with multiple affinity histochemical stains for each of one or more epithelial markers, one or more immune cell markers, and one or more PD-1 axis pathway markers; and (a2) post-treatment response data for each patient; (b) extracting a plurality of features from the digital image of the multiply stained tissue section; (c) applying a feature selection function to the extracted plurality of features and the post-treatment response data to obtain an ordering for each feature of the strength of correlation with response to the PD-1 axis guided therapy; (d) applying a modeling function to one or more of the ranked features and the post-treatment response data to generate a plurality of candidate models that predict response to checkpoint inhibitor therapy, and testing each candidate model for consistency with response; (e) the candidate model with the highest agreement with the response is selected as the scoring function. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), and the features are selected from the group consisting of the features in the left column of table 4. In a certain embodiment, the multiple affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PanCK, PD-L1, PD1, CD8, and LAG3 (group 2), and the feature is selected from the group consisting of the features in the right column of table 4. In a certain embodiment, the feature selection function is selected from the group consisting of: set feature selection methods (including, for example, random forest functions), filtering methods (including, for example, mutual information based functions (mRMR)/correlation coefficient based functions and Relief based functions), and/or embedded feature selection functions (e.g., elastic network/minimum absolute shrinkage function or selection operator (LASSO) functions). In a certain embodiment, the candidate model is made using one or more of the top 25, 20, 15, 10, 9,8, 7, 6,5, 4, or 3 features identified by the feature selection function. In another embodiment, the candidate model uses at least 1, at least 2, at least 3, at least 4, or at least 5 features identified in the top 10 features of the feature selection function. In another embodiment, the candidate model comprises at least one feature that is present in the first 5 features of the at least 2 feature selection functions. In a certain embodiment, the modeling function is selected from the group consisting of: quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN). In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In one embodiment, a method for scoring a tumor sample for likelihood of response to PD-1 axis-directed therapy is provided, the method comprising: (a) obtaining a digital image of a tumor section from the tumor sample, wherein the tumor section is stained for each of one or more epithelial markers, one or more immune cell markers, and one or more PD-1 axis pathway markers with multiple affinity histochemical stains; (b) identifying a region of interest (ROI) in the digital image; (c) extracting one or more features from the ROI that relate to cells stained for the respective biomarker; and (d) applying a scoring function to the feature vector comprising the one or more extracted features of (c) to generate a score, wherein the score indicates a likelihood that the tumor will respond to the PD-1 axis guidance therapy. In a certain embodiment, the ROI is derived from a digital image of a morphologically stained section of the tumor sample, wherein the morphologically stained section and the multiple affinity histochemical stained sample are serial sections. In a certain embodiment, the ROI is identified by the user in the digital image of said morphologically stained section and automatically registered into the digital image of the multi-affinity histochemical stained section. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of the features in the left column of table 4. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is an ROI according to table 3, and the features comprise at least one feature determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI being an ROI according to table 3, and said features comprise at least one feature determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is an ROI according to table 3, and the features comprise at least 1, 2, 3,4, 5,6, 7, 8, 9 or 10 of the top 10 most important features determined to predict patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3, and the features comprise each of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PanCK, PD-L1, PD1, CD8 and LAG3 (group 2), the ROI is an ROI according to table 3 and the features are selected from the group consisting of the features in the right column of table 4. In a certain embodiment, the multiple affinity histochemical staining comprises panel 2, the ROI is an ROI according to table 3, and the features comprise at least one feature in the right column of table 4 determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the multiple affinity histochemical staining comprises panel 2, the ROI is an ROI according to table 3, and said features comprise at least one feature in the right column of table 4 determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the multiple affinity histochemical staining comprises a group 2, the ROI is an ROI according to table 3, and said features comprise at least 1, 2, 3,4, 5,6, 7, 8, 9 or 10 of the features of the right column of table 4 determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiple affinity histochemical staining comprises set 2, the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of: the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells, the mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, the maximum of the lang 3 intensity in CD8+ lang 3+ cells, the mean # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and the maximum of the lang 3+ intensity on CD8+ cells in epithelial tumors. In a certain embodiment, the multiple affinity histochemical staining comprises set 2, the ROI is an ROI according to table 3, and said features comprise each of: the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors, the mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, the maximum of the lang 3 intensity in CD8+ lang 3+ cells, the mean # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and the maximum of the lang 3+ intensity on CD8+ cells. In a certain embodiment, the scoring function is derived from a modeling function selected from the group consisting of: quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN). In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In one embodiment, a method of selecting a patient to receive PD-1 axis guidance therapy is provided, the method comprising: (a) obtaining a digital image of a tumor section from the tumor sample, wherein the tumor section is stained for each of one or more epithelial markers, one or more immune cell markers, and one or more PD-1 axis pathway markers with multiple affinity histochemical stains; (b) identifying a region of interest (ROI) in the digital image; (c) extracting one or more features from the ROI that relate to cells stained for the respective biomarker; (d) applying a scoring function to a feature vector comprising one or more of the extracted features of (c) to generate a score, wherein the score indicates a likelihood that a tumor will respond to the PD-1 axis-directed therapy; (e) comparing the score to a predetermined cutoff value; and (f) selecting a patient to receive the PD-1 axis therapy or replacement therapy based on the comparison of (e). In a certain embodiment, the ROI is derived from a digital image of a morphologically stained section of the tumor sample, wherein the morphologically stained section and the multiple affinity histochemical stained sample are serial sections. In a certain embodiment, the ROI is identified by the user in the digital image of said morphologically stained section and automatically registered into the digital image of the multi-affinity histochemical stained section. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of the features in the left column of table 4. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is an ROI according to table 3, and the features comprise at least one feature determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI being an ROI according to table 3, and said features comprise at least one feature determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is an ROI according to table 3, and the features comprise at least 1, 2, 3,4, 5,6, 7, 8, 9 or 10 of the top 10 most important features determined to predict patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3, and the features comprise each of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PanCK, PD-L1, PD1, CD8 and LAG3 (group 2), the ROI is an ROI according to table 3 and the features are selected from the group consisting of the features in the right column of table 4. In a certain embodiment, the multiple affinity histochemical staining comprises panel 2, the ROI is an ROI according to table 3, and the features comprise at least one feature in the right column of table 4 determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the multiple affinity histochemical staining comprises panel 2, the ROI is an ROI according to table 3, and said features comprise at least one feature in the right column of table 4 determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the multiple affinity histochemical staining comprises group 2, the ROI is an ROI according to table 3, and said features comprise at least 1, 2, 3,4, 5,6, 7, 8, 9 or 10 in the right column of table 4 determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiple affinity histochemical staining comprises set 2, the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of: the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors, the mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, the maximum of the lang 3 intensity in CD8+ lang 3+ cells, the mean # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and the maximum of the lang 3+ intensity on CD8+ cells. In a certain embodiment, the multiple affinity histochemical staining comprises set 2, the ROI is an ROI according to table 3, and said features comprise each of: the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors, the mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, the maximum of the lang 3 intensity in CD8+ lang 3+ cells, the mean # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and the maximum of the lang 3+ intensity on CD8+ cells. In a certain embodiment, the scoring function is derived from a modeling function selected from the group consisting of: quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN). In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In one embodiment, a method of treating a patient having a tumor is provided, the method comprising: (a) obtaining a digital image of a tumor section from the tumor sample, wherein the tumor section is stained for each of one or more epithelial markers, one or more immune cell markers, and one or more PD-1 axis pathway markers with multiple affinity histochemical stains; (b) identifying a region of interest (ROI) in the digital image; (c) extracting one or more features from the ROI that relate to cells stained for the respective biomarker; (d) applying a scoring function to a feature vector comprising one or more of the extracted features of (c) to generate a score, wherein the score indicates a likelihood that a tumor will respond to the PD-1 axis-directed therapy; (e) comparing the score to a predetermined cutoff value; and (f) administering a PD-1 axis-directed therapy to the patient if the comparison of (e) indicates that the patient is likely to respond to the PD-1 axis-directed therapy, or administering a course of treatment that does not include the PD-1 axis-directed therapy to the patient if the comparison of (e) indicates that the patient is likely to not respond to the PD-1 axis-directed therapy. In a certain embodiment, the ROI is derived from a digital image of a morphologically stained section of the tumor sample, wherein the morphologically stained section and the multiple affinity histochemical stained sample are serial sections. In a certain embodiment, the ROI is identified by the user in the digital image of said morphologically stained section and automatically registered into the digital image of the multi-affinity histochemical stained section. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of the features in the left column of table 4. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is an ROI according to table 3, and the features comprise at least one feature determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI being an ROI according to table 3, and said features comprise at least one feature determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is an ROI according to table 3, and the features comprise at least 1, 2, 3,4, 5,6, 7, 8, 9 or 10 of the top 10 most important features determined to predict patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker specific reagents for each of PD-L1, CD8, CD3, CD68 and PanCK (group 1), the ROI is a ROI according to table 3, and the features comprise each of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the multiplex affinity histochemical staining comprises histochemical staining with biomarker-specific reagents for each of PanCK, PD-L1, PD1, CD8 and LAG3 (group 2), the ROI is an ROI according to table 3 and the features are selected from the group consisting of the features in the right column of table 4. In a certain embodiment, the multiple affinity histochemical staining comprises panel 2, the ROI is an ROI according to table 3, and the features comprise at least one feature in the right column of table 4 determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the multiple affinity histochemical staining comprises panel 2, the ROI is an ROI according to table 3, and said features comprise at least one feature in the right column of table 4 determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the multiple affinity histochemical staining comprises a group 2, the ROI is an ROI according to table 3, and said features comprise at least 1, 2, 3,4, 5,6, 7, 8, 9 or 10 features in the right column of table 4 determined as one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the multiple affinity histochemical staining comprises set 2, the ROI is a ROI according to table 3 and said features comprise at least one feature selected from the group consisting of: the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors, the mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, the maximum of the lang 3 intensity in CD8+ lang 3+ cells, the mean # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and the maximum of the lang 3+ intensity on CD8+ cells. In a certain embodiment, the multiple affinity histochemical staining comprises set 2, the ROI is an ROI according to table 3, and said features comprise each of: the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors, the mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, the maximum of the lang 3 intensity in CD8+ lang 3+ cells, the mean # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and the maximum of the lang 3+ intensity on CD8+ cells. In a certain embodiment, the scoring function is derived from a modeling function selected from the group consisting of: quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), and Artificial Neural Networks (ANN). In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In one embodiment, a method is provided comprising: (a) labeling a region of interest (ROI) on a digital image of a test sample of a tumor, wherein the digital image is a digital image of a sample that is subjected to multiple affinity staining for PD-L1, CD8, CD3, CD68, and PanCK (group 1); (b) extracting one or more features of table 9 from the ROI; (c) applying a scoring function to a feature vector comprising one or more features of (b), wherein an output value of the scoring function is a value that predicts a patient's response to PD-1 axis guided therapy. In a certain embodiment, the one or more characteristics are determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the feature is one of the top 10 most important features determined for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the at least one feature is selected from the group consisting of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In one embodiment, the feature vector includes each of: the fraction of PD-L1+ macrophages in the stroma, the fraction of PD-L1+ CD3+ CD 8-cells in the stroma, and the fraction of PD-L1+ CD3+ cells in the stroma. In a certain embodiment, the feature vector comprises at least 1, 2, 3,4, 5,6, 7, 8, 9, or 10 of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the scoring function is derived by fitting a quadrant discriminant classification model to the selected features to predict response to treatment. In a certain embodiment, the treatment outcomes for fitting the quadrant discriminant classification model are combined together in a configuration selected from the group consisting of: PD vs SD vs PR + CR; PD vs SD + PR + CR; and PD + SD versus PR + CR. In a certain embodiment, wherein the ROI is identified in a digital image of a first continuous section of the test sample, wherein the first continuous section is stained with hematoxylin and eosin, and wherein the ROI is automatically displayed in a digital image of at least a second continuous section of said test sample, wherein the second continuous section is stained with group 1. In a certain embodiment, the method is computer-implemented. In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In one embodiment, a method is provided comprising: (a) labeling a region of interest (ROI) on a digital image of a test sample of a tumor, wherein the digital image is a digital image of a sample that is subjected to multiple affinity staining for PanCK, PD-L1, PD1, CD8, and LAG3 (panel 2); (b) extracting one or more features of table 16 from the ROI; (c) applying a scoring function to a feature vector comprising one or more features of (b), wherein an output value of the scoring function is a value that predicts a patient's response to PD-1 axis guided therapy. In a certain embodiment, the one or more features are features determined to be important for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forests. In a certain embodiment, the one or more features are features determined to be one of the top 10 most important features for predicting a patient's response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the feature vector comprises at least one feature selected from the group consisting of: "maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors," mean # of PD-1 low-intensity CD8+ cells within 20 μm radius of PD-L1+ cells, "maximum of Lag3 intensity in CD8+ Lag3+ cells, # of PD-1+ cells within 20 μm radius of PD-L1+ cells, and maximum of Lag3+ intensity on CD8+ cells. In a certain embodiment, the feature vector comprises each of the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in the epithelial tumor, and optionally further comprises one or more additional features selected from the group consisting of: mean # of PD-1 low intensity CD8+ cells within a 20 μm radius of PD-L1+ cells, maximum of the lang 3 intensity in CD8+ lang 3+ cells, mean # of PD-1+ cells within a 20 μm radius of PD-L1+ cells, and maximum of the lang 3+ intensity on CD8+ cells. In a certain embodiment, the feature vector includes at least 1, 2, 3,4, 5,6, 7, 8, 9, or 10 features determined to be one of the top 10 most important features for predicting patient response to PD-1 axis guided therapy by ReliefF and/or random forest. In a certain embodiment, the scoring function is derived by fitting a quadrant discriminant classification model to the selected features to predict response to treatment. In a certain embodiment, the treatment outcomes for fitting the quadrant discriminant classification model are combined together in a configuration selected from the group consisting of: PD vs SD vs PR + CR; PD vs SD + PR + CR; and PD + SD versus PR + CR. In a certain embodiment, wherein the ROI is identified in a digital image of a first continuous section of the test sample, wherein the first continuous section is stained with hematoxylin and eosin, and wherein the ROI is automatically displayed in a digital image of at least a second continuous section of said test sample, wherein the second continuous section is stained with group 2. In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In one embodiment, a system for predicting a patient's response to PD-1 axis therapy is provided, the system comprising: a processor; and a memory coupled to the processor for storing computer-executable instructions that, when executed by the processor, cause the processor to perform operations comprising one or more methods of predicting patient response to PD-1-directed therapy as described herein. In a certain embodiment, the system further comprises a scanner or microscope adapted to capture a digital image of a section of the tissue sample and transmit the image to a computer device. In a certain embodiment, the system further comprises an automated slide stainer programmed to histochemically stain sections of the tissue sample with group 1 or group 2. In a certain embodiment, the system further comprises an automated hematoxylin and eosin stainer programmed to stain one or more consecutive sections of the section stained by the automated slide stainer. In a certain embodiment, the system further comprises a Laboratory Information System (LIS) for tracking sample and image workflows and diagnostic information, the LIS comprising a central database configured to receive and store information related to the tissue sample, the information comprising at least one of: a processing step to be performed on the tumor tissue sample, a processing step to be performed on a digital image of a section of the tumor tissue sample, a processing history of the tumor tissue sample and the digital image; and one or more clinical variables (e.g., MMR or MSI status) associated with the likelihood that the patient will respond to the therapy. In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

In a certain embodiment, a non-transitory computer-readable storage medium is provided for storing computer-executable instructions for execution by a processor to perform operations comprising one or more methods of prediction of patient response to PD-1-directed therapy described herein. In a certain embodiment, the PD-1 axis-directed therapy is a monoclonal antibody specific for PD-1 or a monoclonal antibody specific for PD-L1. In a certain embodiment, the PD-1 axis-guided therapy is selected from the group consisting of: pembrolizumab, nivolumab, alemtuzumab, avizumab, devaluzumab, cimiraprizumab, tirezlizumab, and LY 3300054.

Drawings

This patent or application document contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the office upon request and payment of the necessary fee.

Fig. 1 is a flow diagram illustrating an exemplary method of deriving a scoring function as disclosed herein.

Fig. 2 is a flow chart illustrating an exemplary method of scoring a test sample using a scoring function described herein.

Fig. 3 illustrates an exemplary scoring system that incorporates the scoring functions described herein.

Fig. 4A illustrates an exemplary workflow implemented on the image analysis system disclosed herein, wherein an object recognition function is performed on the entire image prior to performing the ROI generator function.

Fig. 4B illustrates an exemplary workflow implemented on the image analysis system disclosed herein in which an object recognition function is performed on the ROI only after the ROI generator function is performed.

Figure 5 shows a multiple staining procedure using group 1 as described in example I.

Fig. 6 shows an exemplary slide stained with group 1.

Figure 7 shows the importance ranking of all features stained with group 1 in all cases.

Figure 8 shows the importance ranking of features stained with group 1 in the MMR defect case.

Fig. 9 is an IHC image of a sample stained with group 1 from a patient showing complete response to PD-1 axis-directed therapy treatment.

Fig. 10 is an IHC image of a sample stained with group 1 from a patient with progressive disease after treatment with PD-1 axis guidance therapy.

FIG. 11 shows the staining and image analysis procedure used in example II for group 2.

Fig. 12 shows the ranking of the top 15 features for group 2 using the ReliefF feature selection function. The characteristics are as follows: (1) PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺The maximum number of cells; (2) from PD-L1⁺/CD8⁺The maximum value of PD-L1 intensity of the cells; (3) in panCK^–PD-1 in the region⁺/PD-L1-/Lag3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells; (4) PD-L1⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺Spatial variance of the number of cells; (5) from all PD-L1⁺The maximum value of PD-L1 intensity of the cells; (6) panCK^–In region bag 3⁺The number of cells; (7) panCK^–PD-L1 in region⁺/panCK^–The density of the cells; (8) panCK⁺PD-L1 in region⁺The number of cells; (9) panCK^–PD-L1 in region⁺The number of cells; (10) panCK^–PD-1 in the region⁺The number of cells; (11) PD-L1⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺The maximum number of cells; (12) PD-L1⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺The average number of cells; (13) from CD8⁺/Lag3⁺Maximum of the lang 3 intensity of the cells; (14) panCK^–CD8 in region⁺The number of cells; and (15) PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺Variance of the number of cells.

Fig. 13 shows the ranking of the top 15 features for group 2 using a random forest feature selection function. The characteristics are as follows: (1) from PD-L1⁺Cell to its nearest PD-1⁺The average distance of the cells; (2) PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺The maximum number of cells; (3) PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_{Low strength}/CD8⁺The maximum number of cells; (4) from PD-L1⁺Cell to nearest PD-1⁺Standard distance of cells; (5) panCK^–In region bag 3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells; (6) panCK^–PD-L1 in region⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells; (7) PD-L1⁺PD-1 within a 10 μm radius of a cell_{Low strength}/CD8⁺The average number of cells; (8) PD-L1⁺PD-1 within a 10 μm radius of a cell_{Low strength}/CD8⁺Variance of the number of cells; (9) from all PD-1⁺Mean value of PD-1 intensity of cells; (10) from all of the lads 3⁺The minimum of the lang 3 intensity of the cells; (11) panCK^–PD-L1 in region⁺The density of the cells; (12) PD-L1⁺/CD8⁺Cell PD-1 within a radius of 10 μm_{Low strength}/CD8⁺The maximum number of cells; (13) panCK⁺PD-1 in the region⁺The number of cells; (14) panCK^–PD-1 in the region⁺/PD-L1^–/Lag3⁺/CD8⁺Cells and CD8⁺The ratio of the number of cells; and (15) from Lang 3⁺/CD8⁺Maximum of the lang 3 intensity of the cells.

Fig. 14A contains a chart illustrating the following: predicted values of spatial variance # PD-1+ cells within a 10 μm radius of PD-L1+ cells (F1), PD-L1⁺Mean # PD-1 within a 20 μm radius of the cells_{Low strength}CD8⁺Cellular predictive value (F2), and CD8⁺Lag3⁺Predicted value of the maximum of the intensity of tag 3 in cells (F3).

Fig. 14B is a scatter plot showing the following predicted values: spatial variance # PD-1+ cells within a 10 μm radius of PD-L1+ cells (F1) and PD-L1⁺Mean # PD-1 within a 20 μm radius of the cells_{Low strength}CD8⁺Cells (F2).

Fig. 14C is a scatter plot showing the following predicted values: spatial variance # PD-1+ cells within a 10 μm radius of PD-L1+ cells (F1), PD-L1⁺Radius of 20 μm of the cellMean value within # PD-1_{Low strength}CD8⁺Cells (F2), and CD8⁺Lag3⁺Maximum value of cell bag 3 intensity (F3).

FIG. 15 shows an exemplary IHC image of a non-responder and a responder, and shows PD-L1⁺Location of cells (grey dots), PD-1 within 20 μm of PD-L1+ cells_{Is low in}Cells (white point), and PD-1 within 10 μm of PD-L1+ cells⁺Graphical reconstruction of cells (black dots). Box (a) is the original fluorescence image of the non-responder. Block (b) is a graphical reconstruction of the white boxes from Block (a) showing PD-L1+ cells and PD-1 within 20 μm of PD-L1+ cells in non-responders_{Is low in}Spatial relationships between cells. Block (c) is a graphical reconstruction of the gray box from block (a), showing PD-L1 in the non-responder⁺PD-L1+ cells and PD-1 within 10 μm of the cells⁺Spatial relationships between cells. Box (d) is the original fluorescence image of the responder. Block (e) is a graphical reconstruction of the white boxes from Block (d), showing PD-L1+ cells and PD-1 within 20 μm of the responder PD-L1+ cells_{Is low in}Spatial relationships between cells. Block (f) is a graphical reconstruction of the gray box from block (d), showing the responder PD-L1⁺PD-L1+ cells and PD-1 within 10 μm of the cells⁺Spatial relationships between cells.

FIG. 16A is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment based on Lag3 in the panCK-negative region⁺/CD8⁺Number of cells and CD8⁺The ratio of the total number of cells.

FIG. 16B is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment based on Lag3 in the panCK-negative region^-/CD8⁺Cells and CD8⁺Ratio of the number of cells.

FIG. 16C is a Kaplan-Meier survival curve based on Lag3 for predicting overall survival after pembrolizumab treatment⁺/panCK^–The number of cells divided by the panCK-negative area.

FIG. 16D is a Kaplan-Meier survival curve based on the number of Lag3 positive cells in the panCK negative region used to predict overall survival after pembrolizumab treatment.

FIG. 16E is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on CD8⁺Maximum of the intensity of bag 3 in cells.

FIG. 16F is a Kaplan-Meier survival curve based on the number of Lag3+ cells in the panCK-positive region used to predict overall survival after pembrolizumab treatment.

FIG. 16G is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺/panCK⁺PD-1 within a 10 μm radius of a cell_InAverage number of/CD 8+ cells.

FIG. 16H is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_InAverage number of/CD 8+ cells.

FIG. 16I is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_InVariance of the number of/CD 8+ cells.

FIG. 16J is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_InVariance of the number of/CD 8+ cells.

FIG. 16K is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}Variance of the number of/CD 8+ cells.

FIG. 16L is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_InMaximum number of/CD 8+ cells.

FIG. 16M is a Kaplan-Meier survival curve for predicting overall survival after pembrolizumab treatment, based on PD-L1⁺PD-1 within a 20 μm radius of a cell_InThe most abundant of the/CD 8+ cellsA large number. For each feature index, the queues are divided into two groups using the median of the feature metric distribution as a cutoff value.

Detailed Description

I. Definition of

Unless otherwise indicated, scientific and technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. See, e.g., Lackie, DICTIONARY OF CELL AND MOLECULAR BIOLOGY, Elsevier (4 th edition 2007); sambrook et al, Molecula clone, A Laboratory manage, Cold Springs Harbor Press (Cold Springs Harbor, N.Y. 1989). The terms "a" or "an" are intended to mean "one or more". When preceding the recitation of steps or elements, the term "comprising" is intended to mean that the addition of additional steps or elements is optional and not precluded.

Antibody: the term "antibody" is used herein in the broadest sense and includes a variety of antibody structures, including, but not limited to, monoclonal antibodies, polyclonal antibodies, multispecific antibodies (e.g., bispecific antibodies), and antibody fragments, so long as they exhibit the desired antigen-binding activity.

Antibody fragment: an "antibody fragment" refers to a molecule other than an intact antibody that comprises a portion of an intact antibody and binds to an antigen to which the intact antibody binds. Examples of antibody fragments include, but are not limited to, Fv, Fab '-SH, F (ab') 2; a diabody; a linear antibody; single chain antibody molecules (e.g., scFv); and multispecific antibodies formed from antibody fragments.

Biomarkers: the term "biomarker" as used herein shall refer to any molecule or group of molecules found in a biological sample that can be used to characterize the biological sample or the subject from which the biological sample is obtained. For example, a biomarker may be a molecule or group of molecules whose presence, absence or relative abundance is characteristic of a particular cell or tissue type or state; or characteristic of a particular pathological condition or state; or an indication indicative of the severity of the pathological condition, the likelihood of progression or regression of the pathological condition, and/or the likelihood of the pathological condition responding to a particular treatment. As another example, the biomarker may be a cell type or microorganism (e.g., bacteria, mycobacteria, fungi, viruses, etc.), or a substituent molecule or group of molecules thereof.

Biomarker specific reagents: a specific detection reagent, such as a primary antibody, capable of binding specifically to one or more biomarkers in a cell sample directly.

Cell sample: the term "cell sample" as used herein refers to any sample containing intact cells, such as a cell culture, a body fluid sample or a surgical specimen taken for pathological, histological or cytological interpretation.

Detection reagent: a "detection reagent" is any reagent used to deposit a staining agent in the vicinity of the biomarker specific reagent in the cell sample. Non-limiting examples include biomarker specific reagents (e.g., primary antibodies), secondary detection reagents (e.g., secondary antibodies capable of binding to primary antibodies), tertiary detection reagents (e.g., tertiary antibodies capable of binding to secondary antibodies), enzymes directly or indirectly associated with the biomarker specific reagents, chemicals deposited that are reactive with such enzymes to affect fluorescent or chromogenic staining, washing reagents used between staining steps, and the like.

A detectable moiety: a molecule or material that can produce a detectable signal (e.g., visual, electronic, or otherwise) that is indicative of the presence (i.e., qualitative analysis) and/or concentration (i.e., quantitative analysis) of a detectable moiety deposited on a sample. Detectable signals may be generated by any known or yet to be discovered mechanism, including absorption, emission, and/or scattering of photons, including radio frequency, microwave frequency, infrared frequency, visible frequency, and ultraviolet frequency photons. The term "detectable moiety" includes chromogenic, fluorescent, phosphorescent, and luminescent molecules and materials that convert one substance to another to provide a catalyst (e.g., an enzyme) that can detect a difference (e.g., by converting a colorless substance to a colored substance or vice versa, or by producing a precipitate or increasing the turbidity of a sample). In some examples, the detectable moiety is a fluorophore, which belongs to several common chemical classes, including coumarins, fluorescein (or fluorescein derivatives and analogs), rhodamines, resorufins, luminophores, and cyanines. Additional examples of Fluorescent molecules can be found in Molecular Probes Handbook-A Guide to Fluorescent Probes and laboratory Technologies, Molecular Probes, Eugene, OR, ThermoFisher Scientific, 11 th edition. In other embodiments, the detectable moiety is a molecule detectable via bright field microscopy, such as dyes including Diaminobenzidine (DAB), 4- (dimethylamino) azobenzene-4 ' -sulfonamide (DABSYL), tetramethylrhodamine (decovery violet), N ' -dicarboxypentyl-5, 5 ' -disulfonic acid-indole-dicarbocyanine (Cy5), and rhodamine 110 (rhodamine).

And (3) feature measurement: a value indicative of the level of a biomarker or the relationship between biomarkers in a sample. Examples include: expression intensity (e.g., on a 0+, 1+, 2+, 3+ scale), number of cells positive for a biomarker, cell density (e.g., number of biomarker-positive cells over a region of the ROI, number of biomarker-positive cells over a linear distance defining an edge of the ROI, etc.), pixel density (i.e., number of biomarker-positive pixels over a region of the ROI, number of biomarker-positive pixels over a linear distance defining an edge of the ROI, etc.), mean or median between cells expressing one or more biomarkers, etc. The feature metric may be an overall metric or an overall metric.

Histochemical detection: a process involves labeling biomarkers or other structures in a tissue sample with biomarker-specific and detection reagents in a manner that allows microscopic detection of the biomarkers or other structures in the context of cross-sectional relationships between the structures of the tissue sample. Examples include Immunohistochemistry (IHC), Chromogenic In Situ Hybridization (CISH), Fluorescent In Situ Hybridization (FISH), Silver In Situ Hybridization (SISH), and hematoxylin and eosin (H & E) stained formalin-fixed paraffin-embedded tissue sections.

Immune checkpoint molecules: a protein expressed by an immune cell, the activation of which down-regulates a cytotoxic T cell response. Examples include PD-1, TIM-3, LAG-4, and CTLA-4.

Immune escape biomarkers: biomarkers expressed by tumor cells can help tumors avoid T cell-mediated immune responses. Examples of immune escape biomarkers include PD-L1, PD-L2, and IDO.

Immunological biomarkers: biomarkers characterized by or affecting the immune response to abnormal cells include, but are not limited to, the following: indicative of a particular class of immune cells (e.g., CD3), characterizing an immune response (e.g., the presence, absence, or amount of a cytokine protein or one or more particular immune cell subtypes), or expressed by, presented by, or otherwise localized to non-immune cell structures that affect the type or extent of an immune cell response.

Monoclonal antibodies: antibodies obtained from a substantially homogeneous population of antibodies, i.e., individual antibodies comprising the population are identical and/or bind the same epitope, except for possible variant antibodies (e.g., comprising naturally occurring mutations or produced during the production of monoclonal antibody preparations, such variants typically being present in minute amounts). In contrast to polyclonal antibody preparations, which typically include different antibodies directed against different determinants (epitopes), each monoclonal antibody in a monoclonal antibody preparation is directed against a single determinant on the antigen. Thus, the modifier "monoclonal" indicates that the characteristics of the antibody are obtained from a substantially homogeneous population of antibodies, and is not to be construed as requiring production of the antibody by any particular method. For example, monoclonal antibodies for use according to the invention can be prepared by a variety of techniques, including but not limited to hybridoma methods, recombinant DNA methods, phage display methods, and methods utilizing transgenic animals comprising all or part of a human immunoglobulin locus, or combinations thereof.

Multiple histochemical staining: a method of tissue chemical staining wherein a plurality of biomarker specific reagents that bind to different biomarkers are applied to a single section and stained with stains of different colors.

PD-1 axial guidance therapy: a therapeutic agent that disrupts the ability of PD-1 to down-regulate T cell activity. Exemplary PD-1 axis-directed therapies include PD-1 specific monoclonal antibodies (e.g., pembrolizumab, nivolumab, cimiralizumab, and tiramizumab), PD-L1 specific monoclonal antibodies (e.g., astuzumab, avizumab, devolumab, and LY3300054), and PD-1 small molecule inhibitors (e.g., CA-170, others reviewed by Li and Tian in preclinical development).

Sample preparation: the term "sample" as used herein shall refer to any material obtained from a subject capable of testing for the presence or absence of a biomarker.

And (3) secondary detection reagent: the specific detection reagent is capable of specifically binding to the biomarker specific reagent.

Slicing: when used as a noun, thin sections of tissue samples suitable for microscopic analysis are typically cut using a microtome. When used as verbs, the process of slicing is generated.

And (3) continuous slicing: the term "serial section" as used herein shall mean any one of a series of sections that are cut from a tissue sample by a microtome. For two sections to be considered "serial sections" of each other, they need not necessarily be serial sections of tissue, but they should generally contain sufficiently similar tissue structures having the same spatial relationship so that the structures can be matched to each other after histological staining.

Single histochemical staining: a method of tissue chemical staining wherein a single biomarker specific reagent is applied to a single section and stained with a stain of a single colour.

Specific detection reagent: in the context of a cell sample, a composition of any substance capable of specifically binding to a chemical structure of interest. The phrases "specifically binds," "specifically binds to," or "specific for" or other similar repeats, as used herein, refer to a measurable and reproducible interaction between a target and a specific detection reagent that determines the presence of the target in the presence of a heterogeneous population of molecules, including biomolecules. For example, an antibody that specifically binds to a target is an antibody that binds to the target with greater affinity, avidity, more readily, and/or for a longer duration than it binds to other targets. In one embodiment, the degree of binding of the specific detection reagent to an unrelated target is less than about 10% of the binding of the antibody to the antigen, as measured, for example, by Radioimmunoassay (RIA). In certain embodiments, the dissociation constant (Kd) of the biomarker-specific agent that specifically binds to the target is less than or equal to 1 μ M, less than or equal to 100nM, less than or equal to 10nM, less than or equal to 1nM, or less than or equal to 0.1 nM. In another embodiment, specific binding may include, but is not required to be, exclusive binding. Exemplary specific detection reagents include nucleic acid probes specific for a particular nucleotide sequence; antibodies and antigen binding fragments thereof; and engineered specific binding compositions comprising ADNECTIN (a 10FN3 fibronectin based scaffold; Bristol-Myers-Squibb Co.), AFFIBODY (a scaffold based on the Z domain of protein A from Staphylococcus aureus; Affibody AB, Solna, Sweden), AVIMER (a scaffold based on the domain A/LDL receptor; Amgen, Thousand Oaks, CA), dAb (a scaffold based on the VH or VL antibody domain; GlaxoSmithKline PLC, Cambridge, UK), DARPin (a scaffold based on ankyrin repeat proteins; Molecular Partners AG, Z ü, CH), ANTICALIN (a lipocalin based scaffold; Pieris AG, Freesing, DE), NANODY (a VHH (camelid) based scaffold; Ablynx N/V, transferrin, Pf-BO, a scaffold based on the lipocalin, Pf-B, a lectin type scaffold (Inc.), a lectin type C, Inc, Inc. lectin TETRANECTIN), a scaffold of tetranectin; borean Pharma A/S, Aarrhus, DK). A description of such engineered specific binding structures is reviewed by Wurch et al in the following: development of Novel Protein scans as Alternatives to wheel additives for Imaging and Therapy, Status on Discovery Research and Clinical Validation, Current Pharmaceutical Biotechnology, Vol.9, p.502 and 509 (2008), the contents of which are incorporated by reference.

Dyeing: when used as a noun, the term "stain" shall mean any substance that may be used to visualize a particular molecule or structure in a cell sample for microscopic analysis, including bright field microscopy, fluorescence microscopy, electron microscopy, and the like. When used as a verb, the term "stain" shall refer to any process that results in the deposition of a stain on a cell sample.

Subject: the term "subject" or "individual" as used herein is a mammal. Mammals include, but are not limited to, domesticated animals (e.g., cows, sheep, cats, dogs, and horses), primates (e.g., human and non-human primates such as monkeys), rabbits, and rodents (e.g., mice and rats). In certain embodiments, the individual or subject is a human.

Test samples: a tumor sample is obtained from a subject having a result of the location at the time the sample was obtained.

Tissue sample: the term "tissue sample" as used herein shall refer to a cell sample that maintains the cross-sectional spatial relationship between cells, as the cells are present in the subject from which the sample was obtained.

Tumor samples: tissue samples were obtained from tumors.

Description of biomarkers

CD 3: CD3 is a cell surface receptor complex that is commonly used as a defined biomarker for cells with T cell lineage. The CD3 complex consists of 4 distinct polypeptide chains: CD 3-gamma chain, CD 3-delta chain, CD3 epsilon chain, and CD 3-zeta chain. CD3- γ and CD3- δ form heterodimers with CD3 e, respectively (ε γ -homodimer and ε δ -heterodimer), and homodimers with the CD 3-zeta chain (zeta-homodimer). Functionally, the ε γ -homodimer, ε δ -heterodimer, and ζ ζ -homodimer form signaling complexes with the T cell receptor complex. Exemplary sequences for the human CD 3-gamma chain, CD 3-delta chain, CD3 epsilon chain, and CD 3-zeta chain (and subtypes and variants thereof) can be found at Uniprot accession No. P09693 (classical amino acid sequence for the sequences disclosed herein in SEQ ID NO: 1), P04234 (classical amino acid sequence for the sequences disclosed herein in SEQ ID NO: 2), P07766 (classical amino acid sequence for the sequences disclosed herein in SEQ ID NO: 3), and P20963 (classical amino acid sequence for the sequences disclosed herein in SEQ ID NO: 4), respectively. The term "human CD3 protein biomarker" as used herein encompasses any CD 3-gamma chain, CD 3-delta chain, CD3 epsilon chain, and CD 3-zeta chain polypeptides having the classical human sequence and natural variants thereof that retain the function of the classical sequence; epsilon gamma-homodimers, epsilon delta-heterodimers, and zeta-homodimers of one or more of the polypeptides comprising the CD 3-gamma chain, CD 3-delta chain, CD3 epsilon chain, and CD 3-zeta chain of the classical human sequence and its natural variants that retain the function of the classical sequence; and any signaling complex comprising one or more of the foregoing CD3 homodimers or heterodimers. In some embodiments, human CD3 protein biomarker specific agents encompass any biomarker specific agent that specifically binds to a structure (e.g., an epitope) within a CD 3-gamma chain polypeptide (e.g., a polypeptide at SEQ ID NO: 1), a CD 3-delta chain polypeptide (e.g., a polypeptide at SEQ ID NO: 2), a CD 3-epsilon chain polypeptide (e.g., a polypeptide at SEQ ID NO: 3), or a CD 3-zeta chain polypeptide (e.g., a polypeptide at SEQ ID NO: 4), or binds to a structure (e.g., an epitope) located within an epsilon gamma homodimer, an epsilon delta heterodimer, or a zeta homodimer.

CD 8: CD8 is a heterodimeric, disulfide-linked transmembrane glycoprotein found in the cytotoxic suppressor T cell subset, thymocytes, certain natural killer cells, and bone marrow subsets. Exemplary sequences for the alpha-and beta-chains of the human CD8 receptor (and subtypes and variants thereof) can be found in Uniprot accession numbers P01732 (classical amino acid sequence for the sequences disclosed herein in SEQ ID NO: 5) and P10966 (classical amino acid sequence for the sequences disclosed herein in SEQ ID NO: 6), respectively. The term "human CD8 protein biomarker" as used herein encompasses any CD 8-a chain polypeptide having a classical human sequence and natural variants thereof that retain the function of the classical sequence; any CD 8-beta chain polypeptide having a classical human sequence and natural variants thereof that retain the function of the classical sequence; including dimers of any CD 8-alpha chain polypeptide having a classical human sequence and natural variants thereof that retain the function of the classical sequence and/or any CD 8-beta chain polypeptide having a classical human sequence and natural variants thereof that retain the function of the classical sequence. In some embodiments, a human CD8 protein biomarker specific agent encompasses any biomarker specific agent that specifically binds to a structure (e.g., an epitope) within a CD 8-alpha chain polypeptide (e.g., a polypeptide at SEQ ID NO: 5), a CD 8-beta chain polypeptide (e.g., a polypeptide at SEQ ID NO: 6), or binds to a structure (e.g., an epitope) located within a CD8 dimer.

CD 68: CD68 is a glycoprotein encoded by the CD68 gene located at 17p13.1 on chromosome 17. CD68 protein is present in the cytoplasmic granules of a variety of different blood and muscle cells and is often used as a biomarker for cells of the macrophage lineage, including monocytes, histiocytes, giant cells, kupffer cells, and osteoclasts. An exemplary sequence for human CD68 (and isoforms and variants thereof) can be found at Uniprot accession number P34810 (the classical amino acid sequence for the sequence disclosed herein in SEQ ID NO: 7). The term "human CD68 protein biomarker" as used herein encompasses any CD68 polypeptide having a classical human sequence and natural variants thereof that retain the function of the classical sequence. In some embodiments, a human CD20 protein biomarker specific agent encompasses any biomarker specific agent that specifically binds to a structure (e.g., an epitope) within a human CD68 polypeptide (e.g., a polypeptide at SEQ ID NO: 7).

Whole cell keratin: as used herein, "whole cytokeratin" and "PanCK" refer to any biomarker-specific agent or set of biomarker-specific agents that specifically bind sufficient cytokeratin to specifically stain epithelial tissue in a tissue sample. Exemplary whole cell keratin biomarker specific reagents generally include: (a) a single cytokeratin-specific agent that recognizes an epitope common to multiple cytokeratins, wherein a majority of epithelial cells of the tissue express at least one of the multiple cytokeratins; or (b) a mixture of biomarker specific reagents such that the mixture is specifically reactive with a plurality of cytokeratins, wherein a majority of epithelial cells of the tissue express at least one of the plurality of cytokeratins. Reference to "a mixture" in this definition includes both a single composition comprising each member of the plurality of components and also includes providing each member of the plurality of components as a separate composition but dyeing them with a single dye or a combination thereof. PanCK mixtures were examined by NordiQC. In some embodiments, the PanCK biomarker-specific reagent comprises an antibody mixture containing two or more antibody clones selected from the group consisting of: 5D3, LP34, AE1, AE2, AE3, MNF116, and PCK-26. In a certain embodiment, the PanCK mixture is selected from the group consisting of: mixtures of AE1 and AE3, mixtures of AE1, AE3, and 5D3, and mixtures of AE1, AE3, and PCK 26. Mixtures of AE1 and AE3 are commercially available from Agilent Technologies (catalog numbers GA05361-2, IS05330-2, IR05361-2, M351501-2, and M351529-2). Mixtures of AE1, AE3, and 5D3 are commercially available from BioCare (catalog nos. CM162, IP162, OAI162, and PM162) and Abcam (catalog No. ab 86734). A mixture of AE1, AE3, and PCK26 is available from Roche (catalog number 760-.

PD-1: programmed death-1 (PD-1) is a member of the CD28 receptor family encoded by the PDCD1 gene on chromosome 2. An exemplary sequence for the human PD-1 protein (and isoforms and variants thereof) can be found at Uniprot accession No. Q15116 (classical amino acid sequence for the sequence disclosed herein in SEQ ID NO: 8). In some embodiments, a human PD-1 protein biomarker specific agent encompasses any biomarker specific agent that specifically binds to a structure (e.g., an epitope) within a human PD-1 polypeptide (e.g., a polypeptide in SEQ ID NO: 8).

PD-L1: programmed death ligand 1(PD-L1) is a type 1 transmembrane protein encoded by the CD274 gene on chromosome 9. PD-L1 acts as a ligand for PD-1 and CD 80. An exemplary sequence for the human PD-L1 protein (and isoforms and variants thereof) can be found in Uniprot accession No. Q9NZQ7 (classical amino acid sequence for the sequence disclosed herein in SEQ ID NO: 9). In some embodiments, a human PD-L1 protein biomarker specific agent encompasses any biomarker specific agent that specifically binds to a structure (e.g., an epitope) within a human PD-L1 polypeptide (e.g., a polypeptide at SEQ ID NO: 9).

LAG 3: lymphocyte activation gene 3 protein (LAG3) is a member of the immunoglobulin (Ig) superfamily encoded by the LAG3 gene on human chromosome 12. An exemplary sequence for the human LAG3 protein (and isoforms and variants thereof) can be found in Uniprot accession number P18627 (classical amino acid sequence for the sequence disclosed herein in SEQ ID NO: 10). In some embodiments, a human LAG3 protein biomarker-specific agent encompasses any biomarker-specific agent that specifically binds to a structure (e.g., an epitope) within a human LAG3 polypeptide (e.g., a polypeptide in SEQ ID NO: 10).

Generation of scoring function

Fig. 1 is a flow diagram illustrating an exemplary method of deriving a scoring function as disclosed herein. The scoring function of the present methods and systems is typically derived from tumor samples obtained from a patient cohort prior to treatment with PD-1 axis-directed therapy, and its outcome data (e.g., 3-or 5-year overall survival, progression-free survival, recurrent free survival, progressive disease, stable disease, partial response, complete response, etc.) can be obtained 101. A set of biomarkers to be tested is selected, and the cohort samples are stained 102 for the biomarkers and imaged (typically with morphologically stained serial sections) 103. Regions of interest (ROIs) are identified in the one or more digital images 104 and multi-biomarker features are extracted from the one or more ROIs 105. The extracted features are evaluated by a feature selection function to identify those features that are relevant to the response to the PD-1 axis by using the feature selection function 106. One or more selected features are modeled for the results using one or more modeling functions, candidate scoring functions are identified, and one or more cutoff values are optionally selected to group the queues according to their scores (e.g., "likely to answer" and "unlikely to answer" groups or "highly likely to answer" and "less likely to answer") (e.g., using a ROC curve), and the cutoff values are tested against the groups using a Kaplan-Meier curve 107. A scoring function and cutoff value combination that exhibits the desired spacing between groups is then selected for inclusion in the scoring systems and methods described herein.

Sample and sample preparation for generating a scoring function

The scoring function is typically modeled on tissue sections obtained from cohorts of subjects with tumors and known to be responsive to PD-1 axis guided therapy 101. In some embodiments, the tumor is a solid tumor, such as a carcinoma, lymphoma, or sarcoma. In one embodiment, the tumor is of skin, breast, head and/or neck, lung, upper gastrointestinal tract (including esophagus and stomach), female reproductive system (including uterus, fallopian tube and ovary tumors), lower gastrointestinal tract (including colon, rectum and anus tumors), urogenital tract, exocrine, endocrine, renal, neural or lymphocyte origin. In a certain embodiment, the subject has melanoma, breast cancer, ovarian cancer, pancreatic cancer, head and neck cancer, lung cancer, esophageal cancer, gastric cancer, colorectal cancer (including colon cancer, rectal cancer, and anal cancer), prostate cancer, urothelial cancer, or lymphoma. In particular embodiments, the tumor is non-small cell lung cancer, head and neck squamous cell carcinoma, hodgkin's lymphoma, urothelial cancer, gastric cancer, renal cell carcinoma, hepatocellular carcinoma, or colorectal cancer.

The obtained sample 101 is typically a tissue sample processed in a manner compatible with histochemical staining including, for example, fixation, embedding in a wax matrix (e.g., paraffin), and sectioning (e.g., with a microtome). The present disclosure does not require specific processing steps as long as the obtained sample is compatible with histochemical staining of the sample for the biomarker of interest and generates a digital image of the stained sample. In a particular embodiment, the scoring function is modeled using microtome sections of Formalin Fixed Paraffin Embedded (FFPE) samples. Furthermore, to generate a scoring function, the cohort of samples 101 should be samples with known outcomes, such as recurrence of disease, progression of disease, death due to disease, overall death, progressive disease, stable disease, partial response, and/or complete response.

Group of biomarkers

When generating the scoring function, at least one section of the sample is stained 102 with a set of biomarker specific reagents. These groups typically include at least one epithelial marker-specific agent (e.g., a Pan-CK-specific agent), at least one immune cell-specific agent (e.g., a CD3-, CD8-, and/or CD 68-specific agent), and at least one PD-1 axis biomarker-specific agent (e.g., a PD-1-, PD-L1-, and/or PD-L2-specific agent). In some embodiments, the panel may further comprise one or more additional immune checkpoint biomarker specific agents, such as LAG3 specific agents. In a certain embodiment, the biomarker specific reagent set is selected from the group consisting of: group 1, including CD8, Epithelial Markers (EM), CD68, CD3, and PD-L1; and group 2, including CD8, Epithelial Marker (EM), PD-L1, PD-1, and LAG 3. Examples of epithelial markers useful in groups 1 and 2 include cytokeratins. In one embodiment, the epithelial marker is a panel of cytokeratins stained with a panel of PanCK biomarker-specific reagents.

The panel of biomarker specific reagents is used in combination with a set of appropriate detection reagents to generate biomarker stained sections. Biomarker staining is typically accomplished by contacting a section of the sample with a biomarker specific reagent under conditions that allow specific binding between the biomarker and the biomarker specific reagent. The sample is then contacted with a set of detection reagents that interact with the biomarker specific reagents to facilitate deposition of the detectable moiety in close proximity to the biomarker, thereby generating a detectable signal that localizes the biomarker. Usually, a washing step is performed between the application of different reagents to prevent unwanted non-specific staining of the tissue. The biomarker stained sections may optionally be additionally stained with a contrast agent (e.g., hematoxylin stain) to visualize macromolecular structures. In addition, successive sections of biomarker-stained sections may be stained with morphological stains to facilitate identification of ROIs.

III.C.1. labelling protocols and related reagents

The biomarker specific reagent facilitates detection of the biomarker by mediating deposition of a detectable moiety in close proximity to the biomarker specific reagent.

In some embodiments, the detectable moiety is directly conjugated to the biomarker specific agent and is thus deposited on the sample when the biomarker specific agent binds to its target (commonly referred to as a direct labeling method). Direct labeling methods can often quantify more directly, but often lack sensitivity. In other embodiments, deposition of the detectable moiety is achieved by using a detection reagent that is associated with a biomarker-specific reagent (often referred to as an indirect labeling method). Indirect labeling methods increase the number of detectable moieties that can be deposited in the vicinity of the biomarker specific reagent, and thus indirect labeling methods are generally more sensitive than direct labeling methods, especially when used in combination with dyes.

In some embodiments, an indirect method is used, wherein the detectable moiety is deposited via an enzymatic reaction that localizes the biomarker-specific reagent. Suitable enzymes for such reactions are well known and include, but are not limited to, oxidoreductases, hydrolases, and peroxidases. Specific enzymes specifically included are horseradish peroxidase (HRP), Alkaline Phosphatase (AP), acid phosphatase, glucose oxidase, beta-galactosidase, beta-glucuronidase, and beta-lactamase. The enzyme may be directly conjugated to the biomarker specific agent, or may be indirectly associated with the biomarker specific agent via a label conjugate. As used herein, "labeled conjugate" includes:

(a) a specific detection reagent; and

(b) an enzyme conjugated to a specific detection reagent, wherein the enzyme reacts with a chromogenic substrate, a signaling conjugate, or an enzyme-reactive dye under suitable reaction conditions to effect in situ generation of the dye and/or deposition of the dye on the tissue sample.

In non-limiting examples, the detection reagent specific for the labeled conjugate can be a secondary detection reagent (e.g., a species-specific secondary antibody that binds to a primary antibody, an anti-hapten antibody that binds to a hapten-conjugated primary antibody, or a biotin-binding protein that binds to a biotinylated primary antibody), a tertiary detection reagent (e.g., a species-specific tertiary antibody that binds to a secondary antibody, an anti-hapten antibody that binds to a hapten-conjugated secondary antibody, or a biotin-binding protein that binds to a biotinylated secondary antibody), or other such arrangement. The enzyme localized to the sample-bound biomarker-specific reagent may then be used in a variety of protocols to deposit the detectable moiety.

In some cases, the enzyme reacts with a chromogenic compound/substrate. Specific non-limiting examples of chromogenic compounds/substrates include 4-nitrophenyl phosphate (pNPP), fast red, bromochloroindolyl phosphate (BCIP), nitroblue tetrazole (NBT), BCIP/NBT, fast red, AP orange, AP blue, Tetramethylbenzidine (TMB), 2' -azino-bis- [ 3-benzothiazolinesulfonate ] (ABTS), o-dianisidine, 4-chloronaphthol (4-CN), nitrophenyl-beta-D-galactoside (ONPG), o-phenylenediamine (OPD), 5-bromo-4-chloro-3-indolyl-beta-galactoside (X-Gal), methylumbelliferyl-beta-D-galactoside (MU-Gal), p-nitrophenyl-alpha-D-galactoside (PNP), 5-bromo-4-chloro-3-indolyl-beta-D-glucuronide (X-Gluc), 3-amino-9-ethylcarbazole (AEC), basic fuchsin, Iodonitrotetrazole (INT), tetrazolium blue, or tetrazolium violet.

In some embodiments, the enzyme may be used in a metallographic detection scheme. Metallographical assays involve the use of enzymes such as alkaline phosphatase in combination with water-soluble metal ions and a redox inactive substrate for the enzyme. In some embodiments, the substrate is converted to a redox active agent by the enzyme, and the redox active agent reduces the metal ion, causing it to form a detectable precipitate. (see, e.g., U.S. patent application No. 11/015,646, PCT publication No. 2005/003777, and U.S. patent application publication No. 2004/0265922, filed on 12/20/2004, each of which is incorporated herein by reference in its entirety.) the metallographic detection method involves the use of an oxidoreductase enzyme, such as horseradish peroxidase, and water-soluble metal ions, an oxidizing agent, and a reducing agent, to again form a detectable precipitate. (see, e.g., U.S. Pat. No. 6,670,113, incorporated herein by reference in its entirety.)

In some embodiments, enzymatic action occurs between the enzyme and the dye itself, wherein the reaction converts the dye from an unbound substance to a substance deposited on the sample. For example, the reaction of DAB with a peroxidase (e.g., horseradish peroxidase) oxidizes DAB and precipitates it.

In other embodiments, the detectable moiety is deposited via a signaling conjugate comprising a potentially reactive moiety configured to react with an enzyme to form a reactive species that can bind to the sample or other detection component. These reactive species are capable of reacting with the sample proximal to their generation, i.e., in the vicinity of the enzyme, but are rapidly converted to non-reactive species such that the signaling conjugate is not deposited distal to the site of enzyme deposition. Examples of potentially reactive moieties include: quinone Methide (QM) analogs (such as those described in WO2015124703a 1), and tyramine conjugates (such as those described in WO2012003476a 2), each of which is incorporated herein by reference in its entirety. In some examples, the potentially reactive moiety is directly conjugated to a dye, such as N, N ' -dicarboxypentyl-5, 5 ' -disulfonic acid-indole-dicarbocyanine (Cy5), 4- (dimethylamino) azobenzene-4 ' -sulfonamide (DABSYL), tetramethylrhodamine (DISCO violet), and rhodamine 110 (rhodamine). In other examples, the potentially reactive moiety is conjugated to one member of a specific binding pair and the dye is attached to the other member of the specific binding pair. In other examples, the potentially reactive moiety is linked to one member of a specific binding pair and the enzyme is linked to the other member of the specific binding pair, wherein the enzyme is (a) reactive with the chromogenic substrate to effect dye generation, or (b) reactive with the dye to effect dye (e.g., DAB) deposition. Examples of specific binding pairs include:

(1) biotin or a biotin derivative linked to a potentially reactive moiety (e.g., desthiobiotin), and a biotin-binding entity (e.g., avidin, streptavidin, deglycosylated avidin (e.g., NEUTRAVIDIN), or a biotin-binding protein having nitrotyrosine at the biotin-binding site (e.g., CAPTAVIDIN)) linked to or reactive with a chromogenic substrate (e.g., peroxidase linked to the biotin-binding protein when the dye is DAB); and

(2) a hapten linked to a potentially reactive moiety, and an anti-hapten antibody linked to a dye or an enzyme reactive with a chromogenic substrate or reactive with a dye (e.g., a peroxidase linked to a biotin-binding protein when the dye is DAB).

Specifically included are non-limiting examples of biomarker specific reagent and detection reagent combinations listed in table 1.

TABLE 1

In particular embodiments, the biomarker specific reagents and specific detection reagents listed in table 1 are antibodies. As will be appreciated by one of ordinary skill in the art, the detection scheme for each biomarker specific reagent may be the same, or may be different.

Non-limiting examples of commercially available detection reagents or kits comprising detection reagents suitable for use in the methods of the invention include: the VENTANA ultraView detection system (secondary antibody conjugated to enzymes including HRP and AP); the VENTANA iVIEW detection system (biotinylated anti-species secondary antibody and streptavidin conjugated enzyme); the VENTANA OptiView detection system (OptiView) (anti-species secondary antibody conjugated to hapten and anti-hapten tertiary antibody conjugated to enzyme multimer); VENTANA amplification kit (unconjugated secondary antibody, which is detectable with VENTANA as described previously)Any of the assay systems used together to amplify the amount of enzyme deposited at the primary antibody binding site); the VENTANA OptiView amplification System (anti-species secondary antibody conjugated to a hapten, anti-hapten tertiary antibody conjugated to an enzyme multimer, and tyramine conjugated to the same hapten in use, the secondary antibody is contacted with the sample to effect binding to the primary antibody. VENTANNAA DISCOVERY, DISCOVERY OmNIMap, DISCOVERY UltraMap anti-hapten antibodies, secondary antibodies, chromogens, fluorophores, and dye kits, each of which is available from Ventana Medical Systems, Inc. (Tucson, Arizona); PowerVision and PowerVision + IHC detection systems (secondary antibodies that polymerize directly with HRP or AP into compact polymers carrying a high proportion of enzyme-specific antibodies); and DAKO EnVision^TM+ system (enzyme-labeled polymer conjugated with secondary antibody).

III.C.2. multiple labeling protocol

In one embodiment, the biomarker specific reagent and the detection reagent are applied in a multiplex staining method. In a multiplex method, biomarker specific reagents and detection reagents are applied in a manner that allows for differential labeling of different biomarkers.

One way to accomplish differential labeling of different biomarkers is to select combinations of biomarker specific reagents, detection reagents, and enzyme combinations that do not result in off-target cross-reactivity between different antibodies or detection reagents (referred to as "combinatorial staining"). For example, in the case of using secondary detection reagents, each secondary detection reagent is capable of binding to only one of the primary antibodies used on the section. For example, primary antibodies derived from different animal species (e.g., mouse, rabbit, rat, and goat antibodies) can be selected, in which case species-specific secondary antibodies can be used. As another example, each primary antibody may include a different hapten or epitope tag, and the secondary antibody is selected to specifically bind to the hapten or epitope tag. Furthermore, each set of detection reagents should be suitable for depositing a different detectable entity on the slice, for example by depositing a different enzyme in the vicinity of each biomarker specific reagent. An example of such an arrangement is shown in US 8,603,765. Such an arrangement has the potential advantage of enabling each set of biomarker specific reagents and associated specific binding reagents to be present on the sample simultaneously and/or to be stained with a mixture of biomarker specific reagents and detection reagents, thereby reducing the number of staining steps. However, such an arrangement may not always be feasible, as the reagents may cross-react with different enzymes, and the various antibodies may cross-react with each other, resulting in abnormal staining.

Another way to accomplish differential labeling of different biomarkers is to perform sample staining for each biomarker in turn. In such embodiments, a first biomarker-specific reagent is reacted with the slice, followed by a second detection reagent to the first biomarker-specific reagent and the other detection reagents are reacted with the slice, resulting in deposition of a first detectable entity. The slice is then processed to remove the biomarker specific reagent and associated detection reagent from the slice, while retaining the deposited stain appropriately. This process is repeated for subsequent biomarker specific reagents. Examples of Methods of removing biomarker specific reagents and related detection reagents include heating a sample in the presence of a buffer, the eluent eluting antibodies from the sample (referred to as a "heat-kill method"), such as those disclosed by Stack et al, Multiplexed immunological chemistry, imaging, and quantification: A review, with an assessment of type signal amplification, Multiplexed imaging and multiplexing, Methods, Vol.70, No. 1, pp.46-58 (11 months 2014), and PCT/EP2016/057955, the contents of which are incorporated herein by reference.

As will be appreciated by those skilled in the art, the combination staining and sequential staining methods may be combined. For example, where only a subset of the primary antibodies are compatible with combinatorial staining, the sequential staining method can be modified, wherein antibodies compatible with combinatorial staining are applied to the sample using the combinatorial staining method and residual antibodies are applied using the sequential staining method.

III.C.3. counterdyeing

If desired, biomarker-stained slides may be counterstained to aid in identifying morphologically relevant regions for manual or automatic identification of ROIs. Examples of counterstains include chromogenic nuclear counterstains such as hematoxylin (blue to violet stain), methylene blue (blue stain), toluidine blue (deep blue stain nuclei and pink to red polysaccharide), nuclear fast red (also known as kerneechrot dye, red stain), and methyl green (green stain); non-nuclear chromogenic stains, such as eosin (pink); silver light and dyes including 4', 6-diamino-2-phenylindole (DAPI, blue-dyed), propidium iodide (red-dyed), Hoechst dye (blue-dyed), nuclear green DCS1 (green-dyed), and nuclear yellow (Hoechst S769121, yellow-dyed at neutral pH, blue-dyed at acidic pH), DRAQ5 (red-dyed), DRAQ7 (red-dyed); fluorescent non-nuclear staining, e.g. fluorophore-labeled phalloidin, (staining for fibrillar actin, color depending on the conjugated fluorophore).

Morphological staining of samples iii.c.4

In certain embodiments, it is also desirable to morphologically stain a series of sections of the biomarker stained section 102. The slice may be used to identify the ROI 103 from which to score. Basic morphological staining techniques typically rely on staining the nuclear structure with a first dye and staining the cytoplasmic structure with a second stain. Many morphological stains are known, including but not limited to hematoxylin and eosin (H & E) stains and li stains (methylene blue and basic fuchsin). In particular embodiments, at least one consecutive section of each biomarker-stained slide is H & E stained. Any method of applying H & E staining may be used, including manual and automated methods. In a certain embodiment, the at least one section of the sample is an H & E stained sample stained on an automated staining system. Automated systems for performing H & E staining typically operate based on one of two staining principles: batch staining (also known as "immersion basket") or single slide staining. Batch stainers typically use a bucket or vat of reagents into which many slides are immersed simultaneously. On the other hand, a single slide stainer applies the reagent directly to each slide, and no two slides share the same aliquot of reagent. Examples of commercially available H & E stainers include the VENTANA SYMPHONY (single slide stainer) and VENTANA HE 600 (single slide stainer) series H & E stainers from Roche; coverStainer (batch stainer) from Agilent Technologies; leica ST4020 Small Linear Stainer (batch Stainer), Leica ST5020 Multistainer (batch Stainer), and Leica ST5010 Autostainer XL series (batch Stainer) H & E Stainer from Leica Biosystems Nussloc GmbH.

ROI, object, and feature

In a certain embodiment, one or more objects associated with a set of biomarkers are identified in a digital image of the biomarker stained sample 104. The number of objects and/or the relationship between different objects and another object is used to define features to be evaluated for the development of a scoring function. Non-limiting exemplary groups of potential objects that may be detected from each group are listed in table 2 below:

TABLE 2

In some embodiments, one or more regions of interest (ROIs) are also identified in the digital image of the biomarker stained sample 104. The ROI encompasses the biologically relevant locations of the tissue slices from which relevant objects are identified for feature computation. In one embodiment, the ROI contains morphological regions of a tissue section of the tumor, such as Tumor Regions (TR), infiltration fronts, and peri-cancerous (PT) regions.

The ROI may be limited to the morphological region only, may extend to include regions outside the morphological region (i.e., by extending the edge of the ROI a specified distance outside the morphological region), or may be limited to sub-regions of the morphological region (e.g., by shrinking the ROI to a defined distance within the circumference of the morphological region, or by identifying regions in the ROI that have certain characteristics (e.g., baseline density of certain cell types). At the edge-defined morphological region (e.g., the wetting front), the ROI can be defined, for example, as all points within a defined distance of any point of the edge, all points to one side within a defined distance of any point of the edge, a minimum geometric region (e.g., circular, elliptical, square, rectangular, etc.), encompassing the entire edge region, all points within a circle having a defined radius centered at the center point of the edge region, etc.

In some embodiments, the same ROI may be used for all slices and biomarkers. For example, morphologically defined ROIs can be identified in H & E stained sections of the sample and used for all biomarker stained sections. In other embodiments, different ROIs may be used for different biomarkers. For example, an H & E stained slide can be used to identify a specific morphological region, e.g., a tumor region, that serves as a first ROI. A second ROI or multiple ROIs can then be identified in one of the biomarker stained sections, e.g., to identify regions having a class of cells at a threshold density (e.g., epithelial versus mesenchymal regions). The second ROI or ROIs can then be used for feature computation.

Table 3 shows non-limiting examples of different ROIs:

TABLE 3

In some embodiments, the ROI is identified manually in the digital image. For example, a trained expert may manually delineate one or more morphological regions (e.g., tumor regions and/or infiltration fronts) on a digital image of a sample. One or more regions depicted in the image may then be used as an ROI for feature calculation or as a reference point for calculating the ROI.

In other embodiments, a computer-implemented system may assist a user in annotating ROIs (referred to as "semi-automatic ROI annotation"). For example, a user may delineate one or more regions on a digital image, which the system then automatically converts to a complete ROI. For example, if the desired ROI is a PI, PO and/or PR region, the user can delineate the tumor region and the infiltration front, and the system automatically draws the PI, PO and PR regions according to the user's definition. In another embodiment, where the ROI is EA or SA, the user can draw a tumor region and optionally an infiltration front in the image, which is then registered into the biomarker stained image, and the system creates the relevant EA and SA ROIs by: all cells within a predetermined distance of the EM + cells are labeled as within EA and all cells beyond the predetermined distance are labeled as within SA. In another embodiment, the system may also apply pattern recognition functionality that uses computer vision and machine learning to identify regions with similar morphological features to the delineated and/or automatically generated regions. Thus, for example, a tumor region can be labeled in a semi-automated manner by:

(a) the user annotates the tumor region by delineating the tumor region in an H & E image of the sample; and

(b) the computer system applies pattern recognition functionality to identify additional regions of the sample having morphological features of the outline region, wherein the entire tumor region includes the region labeled by the user and the region automatically identified by the system.

In another example, PR, PI, and/or PO ROIs can be labeled in a semi-automated manner by a method that includes:

(a) marking the tumor area by the user by tracing the tumor area and the outline of the infiltration front in the H & E image of the sample; and

(b) the computer system automatically defining PR, PI, and/or PO areas encompassing all pixels within a defined distance of the marked wetting front; and

(c) the computer system applies pattern recognition functionality to identify additional regions of the sample having morphological characteristics of the PI, PO and/or PR regions identified by step (b).

Many other arrangements may also be used. In the case of a semi-automatic generation of the ROI, the user may be given the option of modifying the computer system labeled ROI, such as by enlarging the ROI, labeling the region of the ROI, or an object within the ROI to exclude it from analysis, or the like.

In other embodiments, the computer system may automatically suggest the ROI without any direct input from the user (referred to as "automatic ROI labeling"). For example, a previously stained tissue segmentation function or other pattern recognition function may be applied to the unlabeled image to identify a desired morphological region for use as a ROI. The user may be given the option of modifying the computer system labeled ROI, such as by enlarging the ROI, labeling the region of the ROI, or objects within the ROI to exclude them from analysis, and the like.

One or more features are extracted from the one or more ROIs and quantified to obtain a feature measure for each sample 105. Exemplary features include, for example, the total number of objects in the ROI, the density of particular objects in the ROI, the spatial relationship between different objects in the ROI, the spatial distribution of particular objects within the ROI, the ratio of the number and/or density of different objects within the ROI, the ratio of the same objects in different ROIs (e.g., the ratio of EA ROI to particular cells in SA ROI or the ratio of PI ROI to particular cells in PO ROI), the fraction of larger total objects of the ROI that fall into a smaller ROI (e.g., the fraction of particular cell types of TA ROI that fall into EA, SA, PI, PO, or PT ROI). Table 4 lists specific exemplary characteristics of each group:

TABLE 4

The ROI characterized in table 4 is the tumor area, unless otherwise stated. Any of the densities listed in table 4 are area densities (i.e., the number of positive cells over the entire ROI area) unless otherwise indicated. As used in table 4, "PD 1 low," "PD 1 medium," and "PD 1 high" refer to single cells with low, medium, and high PD-1 staining intensity. In a certain embodiment, a "PD 1 low" cell is a PD-1+ cell that is the lowest third of the staining intensity of all measured PD-1+ cells in all test samples, a "PD 1" cell is a PD-1+ cell that is the middle third of the staining intensity of all measured PD-1+ cells in all test samples, and a "PD 1 high" cell is a PD-1+ cell that is the highest third of the staining intensity of all measured PD-1+ cells in all test samples.

III.F. modeling scoring function

To identify the scoring function, the features are modeled to predict their ability to respond to the PD-1 axis-directed therapeutic process with relative likelihood.

In a certain embodiment, the features may be selected by executing a feature selection function 106. The feature metrics and result data for each member of the queue are input to a feature selection function, which is then used to rank the features according to their relative relevance to the desired result. Exemplary feature selection functions include aggregate feature selection functions (including, for example, random forest functions), filtering method functions (including, for example, mutual information based functions (mRMR)/correlation coefficient based functions and Relief based functions), and/or embedded feature selection functions (e.g., elastic network/minimum absolute shrinkage function or selection operator (LASSO) functions). In a certain embodiment, the candidate model is made using the top 25, 20, 15, 10, 9,8, 7, 6,5, 4, or 3 features identified by the feature selection function. In another embodiment, the candidate model uses at least 1, at least 2, at least 3, at least 4, or at least 5 features identified in the top 10 features of the at least two feature selection functions. In another embodiment, the candidate model comprises at least one feature that is present in the first 5 features of the at least 2 feature selection functions. In a certain embodiment, a "responder" is considered a patient with a partial response or a complete response. In a certain embodiment, a "responder" is considered a patient with a stable disease, a partial response, or a complete response.

The candidate model is generated by inputting the selected feature metrics and the resulting data for each member in the queue into a modeling function. The model with the highest agreement with the response was selected as the scoring function. Exemplary modeling functions include Quadrant Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), Support Vector Machines (SVMs), and Artificial Neural Networks (ANN). In a certain embodiment, the candidate functions are modeled only on features extracted from the digital image. In other embodiments, the candidate functions include other clinical variables such as age, gender, mismatch repair status, and/or microsatellite instability status. In a certain embodiment, the model is used to predict the likelihood of a post-treatment progressive disease versus a post-treatment stable disease versus a partial or complete response to therapy. In a certain embodiment, the model is used to predict the likelihood that a patient will have progressive disease after treatment relative to the likelihood that the patient will have stable disease, partial response to therapy, or complete response. In a certain embodiment, the model is used to predict the likelihood that a patient will have a progressive disease or a stable disease after treatment relative to the likelihood that the patient will have a partial or complete response to therapy.

Further, one or more stratification cutoff values may be selected to differentiate patients into "risk intervals" (e.g., "high risk" and "low risk" quartiles, deciles, etc.) 107 according to relative risk. In one example, a Receiver Operating Characteristic (ROC) curve is used to select the hierarchical cutoff value. The ROC curve allows a user to balance the sensitivity of the model (i.e., preferentially capturing as many "positive" or "likely to respond" candidates) with the specificity of the model (i.e., minimizing false positives for "likely to respond" candidates). In a certain embodiment, a cutoff value is selected between the risk intervals of likely and unlikely response, the cutoff value being selected to have a balanced sensitivity and specificity. In a certain embodiment, the stratification cut-off distinguishes between (a) patients who may have a progressive disease after treatment and (b) patients who may have a stable disease, partial response, or complete response to therapy. In a certain embodiment, the stratification cut-off distinguishes between (a) patients who may have a progressive disease after treatment, (b) patients who may have a stable disease after treatment, and (c) patients who may have a partial or complete response to therapy. In a certain embodiment, the stratification cut-off distinguishes between (a) patients who may have a progressive or stable disease after treatment and (b) patients who may have a partial or complete response to therapy.

If desired, the model can be performed using a computer statistical analysis software suite (e.g., R project for statistical calculations (available from https:// www.r-project. org.), SAS, MATLAB, etc.).

Scoring with scoring function

After modeling the scoring function and selecting an optional hierarchical cutoff value, the scoring function can be applied to the image of the test sample to calculate a score for the test sample. Fig. 2 is a flow chart illustrating an exemplary method of scoring a test sample using the scoring function described above. Tumor tissue sections 201 are first obtained from a patient in consideration of PD-1 axis guided therapy. Tissue sections are generally similar to the type of sample used to model the scoring function, except that the results are not yet clear. If ROI selection is required, at least one tissue section is stained for biomarkers associated with the scoring function, and with a morphological stain (e.g., H)&E) Serial sections 202 thereof are stained. The stained sections are imaged 203 and the one or more ROIs associated with the scoring function and any objects used in the calculation of the relevant feature measures are annotated in the biomarker stained images 204. Relevant features are extracted from the ROI, and a feature metric is computed for each feature 205. The feature vectors, including all variables used by scoring function 206, are then assembled and the scoring function is applied to feature vectors 207. In some casesThe variables are simply feature measures extracted from the ROI. In other cases, additional clinical variables may include, for example, age, gender, mismatch repair status (e.g., patient with defective mmr (dmmr) or non-defective mmr (pmmr)), microsatellite instability status (e.g., patient is MSI)^{Height of}Or MSI^{Is low in}. If a hierarchical cutoff value is used, the output score may also evaluate the relevant risk interval. The score may then be integrated by the clinician into a diagnostic and/or therapeutic decision, including, for example, by integrating the score with other clinical variables that may weigh the decision whether to administer PD-1 axis-directed therapy.

In one embodiment, the scoring function is integrated into a scoring system. An exemplary scoring system is shown in fig. 3.

The scoring system includes an image analysis system 300. Image analysis system 300 may include one or more computing devices, such as a desktop computer, a laptop computer, a tablet computer, a smartphone, a server, a special-purpose computing device, or any other electronic device or devices of one or more types capable of performing the techniques and/or operations described herein. In some embodiments, image analysis system 300 may be implemented as a single device. In other embodiments, the image analysis system 300 may be implemented as a combination of two or more devices, together implementing the various functions discussed herein. For example, the image analysis system 300 may include one or more server computers and one or more client computers communicatively coupled to each other via one or more local area networks and/or wide area networks such as the internet.

As shown in fig. 3, image analysis system 300 may include a memory 314, a processor 315, and a display 316. The memory 314 may include any combination of any type of volatile or non-volatile memory, such as Random Access Memory (RAM), read-only memory such as electrically erasable programmable read-only memory (EEPROM), flash memory, a hard drive, a solid state drive, an optical disk, and so forth. For simplicity, memory 314 is depicted in FIG. 3 as a single device, but it is understood that memory 314 may be distributed across two or more devices.

Processor 315 may include one or more processors of any type, such as a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a dedicated signal or image processor, a Field Programmable Gate Array (FPGA), a Tensor Processing Unit (TPU), or the like. For simplicity, processor 315 is depicted in fig. 3 as a single device, but it should be understood that processor 315 may be distributed across any number of devices.

The display 316 may be implemented using any suitable technology, such as LCD, LED, OLED, TFT, plasma, and the like. In some implementations, the display 316 may be a touch-sensitive display (touch screen).

As shown in fig. 3, the image analysis system 300 may further include an object identifier 310, a region of interest (ROI) generator 311, a user interface module 312, and a scoring engine 313. Although these modules are shown in fig. 3 as separate modules, it will be apparent to those of ordinary skill in the art that each module may alternatively be implemented as a sub-module, and in some embodiments any two or more modules may be combined into a single module. Further, in some embodiments, system 100 may include additional engines and modules (e.g., input devices, network and communication modules, etc.) not shown in fig. 3 for simplicity. Furthermore, in some embodiments, some of the blocks depicted in fig. 3 may be disabled or omitted. As will be discussed in more detail below, the functionality of some or all of the modules of system 100 may be implemented in hardware, software, firmware, or any combination thereof. Exemplary commercially available software packages that can be used to implement the modules as disclosed herein include VENTANA VIRTUOS; definiens TISSUE STUDIO, developper XD, and IMAGE MINER; and Visophorm BIOTOPIX, ONCOTOPIX, and STEREOTOPIX software packages.

After the image is acquired, the image analysis system 300 may pass the image to an object identifier 310, which functions to identify and tag relevant objects and other features in the image, which are then used for scoring. The object identifier 310 may extract from (or generate for) each image a plurality of image features characterizing the respective object in the image and pixels representing one or more biomarker expressions. The extracted image features may include, for example, texture features such as Haralick features, bag of words features, and the like. The values of the plurality of image features may be combined into a high-dimensional vector, hereinafter referred to as a "feature vector," which characterizes the expression of biomarkers related to the features of the scoring function. For example, if M features are extracted for each object and/or pixel, each object and/or pixel may be characterized by an M-dimensional feature vector. The output of the object identifier 310 is effectively a map of the image that annotates the locations of objects and pixels of interest and associates those objects and pixels with a feature vector that describes the objects or pixels.

For biomarkers scored based on their association with a particular type of object (e.g., membrane, nucleus, cells, etc.), the features extracted by the object identifier 310 may include features or feature vectors sufficient to classify the object in the sample as a biomarker-positive object of interest or a biomarker-negative marker of interest and/or features or feature vectors classified by the level of intensity of biomarker staining of the object. Where the biomarkers may be weighted differently according to the type of object expressing the biomarker, the features extracted by the object identifier 310 may include features related to determining the type of object associated with the biomarker positive pixels. Thus, the subject can then be classified based at least on the expression of the biomarker (e.g., biomarker positive or biomarker negative cells) and the subtype of the subject (e.g., tumor cells, immune cells, etc.). The features extracted by the object identifier 310 may include, for example, the location and/or intensity of biomarker-positive pixels, without scoring the degree of biomarker expression regardless of association with the object. The exact features extracted from the image will depend on the type of classification function applied and will be well known to those of ordinary skill in the art.

Examples of objects identified for certain biomarker panels are listed in table 5 below:

TABLE 5

The image analysis system 300 may also pass the image to the ROI generator 311. The ROI generator 311 is used to identify one or more ROIs of the image from the image for which the immune content score is calculated. In the event that the object identifier 310 is not applied to the entire image, the one or more ROIs generated by the ROI generator 311 may also be used to define a subset of the image on which the object identifier 310 is performed.

In one embodiment, the ROI generator 311 may be accessed through a user interface module 312. The image of the biomarker stained sample (or a morphologically stained serial section of the biomarker stained sample) is displayed on the graphical user interface of the user interface module 112, and the user marks one or more regions in the map that is considered to be the ROI. In this example, the ROI labeling can take a variety of forms. For example, the user may manually define the ROI (hereinafter referred to as "manual ROI annotation"). In other instances, the ROI generator 311 may assist the user in annotating the ROI (referred to as "semi-automatic ROI annotation"). For example, a user may delineate one or more regions on a digital image, which the system then automatically converts to a complete ROI. For example, if the desired ROI is a tumor region, the user delineates the tumor region, and the system identifies similar morphological regions, e.g., using computer vision and machine learning. As another example, the user may label edges in the image (e.g., by tracing lines defining the infiltration front of the tumor), and the ROI generator 311 may automatically define the ROI based on the user-defined edges. For example, the user may mark the edge of the infiltration front or tumor region in the user interface module 312, and the ROI generator 311 uses the edge as a guide to create the ROI, e.g., by drawing a ROI that encompasses all objects within a predetermined distance of the edge (e.g., a PT ROI), or within a predefined distance of one side of the edge (e.g., a PO or PI ROI), or within a first predefined distance of a first side of the edge and within a second predefined distance of a second side of the edge (e.g., a PT ROI with its inside and outside having different standard distances from the infiltration front).

In other embodiments, the ROI generator 311 may automatically suggest the ROI without any direct input from the user (e.g., by applying a tissue segmentation function to the unlabeled image), and the user may then choose to accept, reject, or edit as appropriate.

In some embodiments, the ROI generator 311 may also include a registration function whereby an ROI that is labeled in one slice of a set of consecutive slices is automatically registered in other slices of the set of consecutive slices. This function is particularly useful when the H & E stained serial sections are provided simultaneously with the biomarker-labeled sections. In such embodiments, the user may render the tumor region, for example, in a digital image of the H & E stained section. The ROI generator 311 then displays the ROI from the H & E image into the image of the biomarker stained serial section, thereby matching the tissue structure from the H & E image with the corresponding tissue structure in the serial section. Exemplary display methods can be found, for example, in WO2013/140070 and US 2016 0321809.

The object identifier 310 and the ROI generator 311 may be implemented in any order. For example, the object identifier 310 may first be applied to the entire image. Then, when the ROI generator 311 is implemented, the identified location and features of the object may be subsequently stored and awakened. In such an arrangement, the scoring engine 313 may generate the score immediately upon generating the ROI. This workflow is shown in fig. 3A. As can be seen at fig. 4A, the obtained image has a mixture of different objects (shown by the deep ellipses and the deep diamonds). After the object recognition task is performed, all diamonds (represented by open diamonds) in the image will be recognized. When the ROI is appended to the image (indicated by the dashed line), only the diamonds located in the ROI region are included in the metric calculation of the ROI. A feature vector is then computed, including the feature metrics and any additional metrics used by the scoring function performed by scoring engine 313. Alternatively, the ROI generator 311 may be implemented first. In this workflow, the object identifier 310 may be implemented only on the ROI (which may minimize computation time), or it may still be implemented on the entire image (which may allow for immediate adjustment without re-running the object identifier 310). This workflow is shown in fig. 4B. As can be seen at fig. 4B, the obtained image has a mixture of different objects (shown by the deep ellipses and the deep diamonds). The ROI is appended to the image (indicated by the dashed line), but the object has not yet been marked. After the object recognition task is performed on the ROI, all diamonds in the ROI (represented by open diamonds) will be identified and included in the feature metric calculation of the ROI. A feature vector is then computed, including one or more feature metrics and any additional metrics used by the scoring function performed by scoring engine 313. It is also possible to implement the object identifier 310 and the ROI generator 311 simultaneously.

After the object identifier 310 and the ROI generator 311 have been implemented, a scoring engine 313 is implemented. The scoring engine 313 calculates one or more feature metrics of the ROI and, if used, predetermined maximum and/or minimum cut-off values. The feature vectors, including the computed feature metrics and any other variables used by the scoring function, are assembled by the scoring engine and the scoring function is applied to the feature vectors.

Table 6 lists specific exemplary characteristics for each group:

TABLE 6

As shown in fig. 3, in some embodiments, the image analysis system 300 may be communicatively coupled to an image acquisition system 320. Image acquisition system 320 may acquire images of the sample and provide those images to image analysis system 300 for analysis and presentation to a user.

The image acquisition system 320 can include a scanning platform 325, such as a slide scanner, that can scan a stained slide at 20 x, 40 x, or other magnification to produce a high resolution full slide digital image, including, for example, a slide scanner. At a basic level, a typical slide scanner includes at least: (1) a microscope with an objective lens, (2) a light source (e.g., a halogen, light emitting diode, white light, and/or multispectral light source, depending on the dye, for example), (3) a robot that moves the slide around (or optics around the slide, (4) one or more digital cameras for image capture, (5) a computer and associated software to control the robot and to manipulate, manage, and view the digital slide.

(1) Tile-based scanning, in which the stage or optics are moved in very small increments to capture square image frames that slightly overlap adjacent squares. The captured squares are then automatically matched to each other to construct a composite image; and

(2) line-based scanning, in which the stage is moved in a single axis during acquisition, to capture a number of composite image "strips". The image strips may then be matched to one another to form a larger composite image.

A detailed overview of the various scanners (fluorescent and bright field) can be found in Farahani et al, where slide imaging in Pathology: advatages, limitations, and engineering perspectives, Pathology and Laboratory Medicine Int' l, Vol.7, pp.23-33 (2015, 6 months), the contents of which are incorporated herein by reference in their entirety. Examples of commercially available slide scanners include: 3DHistech PANNORAMIC SCAN II; DigiPath PATHSCOPE; hamamatsu Nanozoomer RS, HT, and XR; huron TISSUESCOPE 4000, 4000XT, and HS; leica SCANSCOPE AT, AT2, CS, FL, and SCN 400; mikroscan D2; olympus VS 120-SL; omnyx VL4, and VL 120; PerkinElmer LAMINA; philips ULTRA-FAST SCANNER; sakura Finetek VISIONTEK; unic PRECICE 500, and PRECICE 600 x; VENTANA ISCAN COREO and ISCAN Ht; and Zeiss AXIO scan.z 1. Other exemplary systems and features can be found, for example, in WO2011-049608) or in U.S. patent application No. 61/533,114 entitled "IMAGING SYSTEMS, CASSETTES, AND METHODS OF USING THE SAME" filed 9/2011, THE contents OF which are incorporated herein by reference in their entirety.

The images generated by scanning platform 325 may be transmitted to image analysis system 300 or a server or database accessible to image analysis system 300. In some embodiments, the images may be automatically transmitted via one or more local and/or wide area networks. In some embodiments, image analysis system 300 may be integrated with or included in other modules of scanning platform 325 and/or image acquisition system 320, in which case the images may be transferred to the image analysis system, for example, through a memory accessible to platform 325 and system 320. In some embodiments, image acquisition system 320 may not be communicatively coupled with image analysis system 300, in which case the images may be stored on any type of non-volatile storage medium (e.g., a flash drive) and may be downloaded from that medium to image analysis system 300 or a server or database communicatively coupled thereto. In any of the above examples, the image analysis system 300 may obtain an image of a biological sample, where the sample may have been mounted on a slide and stained by the histochemical staining platform 323, and the slide may have been scanned by a slide scanner or other type of scanning platform 325. However, it should be understood that in other embodiments, the techniques described below may also be applied to images of biological samples acquired and/or stained by other means.

The image acquisition system 320 may also include an automated histochemical staining platform 323, such as an automated IHC/ISH slide stainer. Automated IHC/ISH slide stainers typically include at least: the system includes a reservoir of various reagents used in the staining protocol, a reagent dispensing unit in fluid communication with the reservoir for dispensing the reagents onto the slides, a waste disposal system for removing used reagents or other waste from the slides, and a control system for coordinating the actions of the reagent dispensing unit and the waste disposal system. In addition to performing staining steps, many automated slide stainers can also perform staining assist steps (or be compatible with a separate system that performs such assist steps), including: slide baking (to adhere the sample to the slide), dewaxing (also known as deparaffinization), antigen retrieval, counterstaining, dehydration and removal, and coverslipping. Prichard, Overview of Automated immunology chemistry, Arch Pathol Lab Med., Vol.138, pp.1578-1582 (2014), the entire contents of which are incorporated herein by reference, describes several specific examples of Automated IHC/ISH slide stainers and various features thereof, including intelliPATH (biocare Medical), WAVE (Celerus diagnostics), DAKO OMNIS and DAKO AUTO TAINER LINK 48(Agilent Technologies), BENCHMARK (Ventana Medical Systems, Inc.), Leica BOND and Lab Vision AUTOSTAINER (Thermo Scientific) Automated slide stainers. Additionally, Ventana Medical Systems, inc. is the assignee of a number of U.S. patents disclosing Systems and methods for performing automated analysis, including U.S. patent nos.: 5,650,327, 5,654,200, 6,296,809, 6,352,861, 6,827,901 and 6,943,029, and U.S. published patent application nos.: 20030211630 and 20040052685, each of which is incorporated by reference herein in its entirety. Commercially available dyeing apparatuses generally operate according to one of the following principles: (1) open individual slide staining, in which the slide is placed horizontally and reagents are dispensed as puddles on the slide surface carrying the tissue sample (e.g., as achieved on DAKO AUTOSTAINER Link 48(Agilent Technologies) and intellipath (biocare medical) stainers); (2) liquid cover techniques, in which reagents are covered or dispensed by a layer of inert fluid deposited on the sample (e.g., as implemented on the VENTANA BenchMark and DISCOVERY stainers); (3) capillary gap staining, in which the slide surface is placed adjacent to another surface (possibly another slide or cover plate) to form a narrow gap, and liquid reagents are drawn and held in contact with the sample by capillary force (e.g., the staining principle used by DAKO TECHMATE, Leica BOND, and DAKO OMNIS stainers). Some iterations of capillary gap staining do not mix the fluids in the gap (such as on DAKO tech mate and Leica BOND). In a variation of capillary gap staining, known as dynamic gap staining, a sample is applied to a slide using capillary force, and then parallel surfaces are translated relative to each other to agitate the reagents during incubation to achieve reagent mixing (such as the staining principle implemented on a DAKO OMNIS stainer). In translational gap staining, a translatable head is positioned on a slide. The lower surface of the head is spaced from the slide by a first gap that is small enough to allow a meniscus of liquid to be formed by the liquid on the slide during translation of the slide. A mixing extension having a lateral dimension less than a width of the slide extends from a lower surface of the translatable head to define a second gap less than the first gap between the mixing extension and the slide. During head translation, the lateral dimension of the mixing extension is sufficient to generate lateral motion in the liquid on the slide in a direction generally extending from the second gap to the first gap. See WO 2011-. Recently it has been suggested to use ink jet technology to deposit reagents on glass slides. See WO 2016-. The staining technique list is not intended to be comprehensive and any fully or semi-automated system for performing biomarker staining may be integrated into the histochemical staining platform 323.

The image acquisition system 320 may include an automated H & E staining platform 324. Automated systems for performing H & E staining typically operate based on one of two staining principles: batch staining (also known as "immersion basket") or single slide staining. Batch stainers typically use a bucket or vat of reagents into which many slides are immersed simultaneously. On the other hand, a single slide stainer applies the reagent directly to each slide, and no two slides share the same aliquot of reagent. Examples of commercially available H & E stainers include the VENTANA SYMPHONY (single slide stainer) and VENTANA HE 600 (single slide stainer) series H & E stainers from Roche; coverStainer (batch stainer) from Agilent Technologies; leica ST4020 Small Linear Stainer (batch Stainer), Leica ST5020 Multistainer (batch Stainer), and Leica ST5010 Autostainer XL series (batch Stainer) H & E Stainer from Leica Biosystems Nussloc GmbH. The H & E staining platform 324 is typically used in the workflow of serial sections requiring morphological staining of the biomarker stained sections.

The scoring system may further include a Laboratory Information System (LIS) 330. LIS 330 will typically perform one or more functions selected from the group consisting of: the recording and tracking processes performed on the sample and slides and images derived from the sample, instructing the different components of the scoring system to perform specific processes on the sample, slides, and/or images, and tracking information about the specific reagents (e.g., lot number, expiration date, dispensed volume, etc.) applied to the sample and/or slide. LIS 330 typically includes at least one database containing information about the sample; labels associated with the sample, slide, and/or image file (e.g., bar codes (including one-dimensional and two-dimensional bar codes), Radio Frequency Identification (RFID) labels, alphanumeric codes affixed to the sample, etc.); and a communication device that reads the tags on the samples or slides and/or communicates information about the slides between LIS 330 and other components of the immune environment scoring system. Thus, for example, a communication device may be placed on each of the sample processing station, the automated histochemical stainer 323, the H & E staining platform 324, and the scanning platform 325. When a sample is initially processed into slices, information about the sample (e.g., patient ID, sample type, procedure to be performed on one or more slices) may be entered into the communication device and a tag created for each slice generated from the sample. At each subsequent station, the tag is entered into the communication device (e.g., by scanning a bar code or RFID tag or by manually entering an alphanumeric code), and the station is in electronic communication with a database, e.g., instructing the station or the station operator to perform a particular procedure on the slice and/or recording the procedure being performed on the slice. At scanning platform 325, scanning platform 325 may also encode each image with a computer readable tag or code that is correlated back to the slice or sample from which the image originated so that when the image is sent to image analysis system 300, image processing steps to be performed may be sent from the database of LIS 330 to the image analysis system and/or recorded in the database of LIS 330 by image analysis system 300. Commercially available LIS systems useful in the present methods and systems include, for example, the VENTANA Vantage Workflow System (Roche).

Examples of the invention

I. Characterization of PD-L1, CD8, CD3, CD68 and PanCK in the tumor microenvironment of gastrointestinal tumors with respect to patient mismatch repair status and anti-PD-1 treatment outcome using 5Plex IHC and whole slide image analysis

I.A. background art

There is an increasing need to understand the micro-environmental markers of tumors to guide cancer immunotherapy. Multiple Immunohistochemistry (IHC) enables characterization of tumor microenvironments while preserving tissue morphology by detecting multiple biomarkers and their co-expression on a single slide. Extracting information about the co-expression of multiple biomarkers and their spatial relationships requires a complete slide image analysis algorithm tailored to the individual assay and its intended use. Cancer can escape immune monitoring and eradication by up-regulating the programmed death 1(PD-1) pathway and its ligand programmed death ligand 1(PD-L1) on tumor cells and in the tumor microenvironment. Blocking this pathway with antibodies against PD-1 or PD-L1 has led to significant clinical responses in certain cancer patients.

Mismatch Repair (MMR) deficiency predicts the response of solid tumors to PD-1 blockade. However, not all patients with mismatch repair defects respond to PD-1 blocking therapy. To understand the different responses, we assessed the tumor microenvironment by detecting PD-L1 expression associated with tumor cells and tumor infiltrating immune cells.

I.b. samples, staining, and image acquisition

This study yielded a cohort of 60 pre-treatment (anti-PD-1 pembrolizumab) patient gastrointestinal tumor samples with acceptable image and tissue quality for automated analysis. After eliminating the response that could not be evaluated, 54 cases remained. Table 7 shows the attenuation of the response with respect to mismatch repair defects.

	Mismatch repair defect free	Mismatch repair defects
			Progressive disease	13	5
Stable disease	3	10
			Partial response + full response	1	22

TABLE 7

Samples were formalin fixed, paraffin embedded, sectioned, and mounted on microscope slides.

As shown in table 8, in the tyramine signal amplification procedure, slides were stained with fluorescent tyramine dye conjugate in multiplex format on a BenchMark ULTRA IHC/ISH automated slide stainer:

TABLE 8

The general concept of tyramine signal amplification is described by US 6,593,100. The staining procedure was essentially the same as the procedure described by Zhang I. The stains are applied sequentially as described in fig. 5. After each stain was deposited, a heat kill step was applied, which included the process described by Zhang I. An exemplary stained slide is shown in fig. 6. Sequential sections of each sample were also H & E stained using an VENTANA HE 600 automated slide stainer.

The IHC-stained slides were scanned on a Zeiss AxioScan Z1 slide scanner and the H & E stained slides were scanned on a VENTANA ISCAN COREO slide scanner. All images have been exported into the proprietary digital pathology image analysis suite software suite, DPath, from Roche.

I.C. image annotation and ROI generation

The tumor region ROI and the tumor's infiltration front (if available) are marked in the image by the pathologist. In addition, the pathologist notes necrotic and other areas excluded from the analysis.

The DPath system automatically labeled epithelial tumor ROIs from aggregates of panCK + cells, and interstitial regions. First, the tumor region is subdivided into patches. For each tile, the panCK mask was first generated by labeling each panCK + cell and finding the union between the labeled cells. Post-processing is then performed on the mask to compensate for lymphocytes infiltrating by:

(a) a disc-like structuring element with a radius of 10 pixels (resolution per pixel of 0.325 μms) performs a morphological closing operation;

(b) more than 80 pixels (8.5 μm) in the closed mask²) To create a "PanCK mask that fills the hole.

(c) The PanCK mask with holes was converted to polygons.

The polygons of all tiles are then assembled together to create polygons at the entire slide level. The entire slide-level polygons are then converted to a mask (lower resolution (size reduction 3^3)) and scaled up by 8.8 μm to generate the final mask for "PanCK + cell aggregates" at the entire slide level.

Furthermore, the peri-medial ROI was automatically generated in the region with a distance of 0.5mm from the infiltration front into the tumor, and the peri-lateral ROI was automatically generated in the region with a distance of 0.5mm from the infiltration front away from the tumor.

I.C. feature calculation and data analysis

The following features were calculated for each ROI: area density of all phenotypes; is PD-L1⁺panCK of⁺The fraction of cells; is PD-L1⁺CD3 (1)⁺The fraction of cells; is PD-L1⁺CD8 (1)⁺The fraction of cells; is also PD-L1⁺CD3 (1)⁺CD8^-The fraction of cells; PD-L1 with CD8+ cells adjacent to its nearest neighbor⁺/CD68⁺Descriptive statistics of the distance of (c); PD-L1 with CD8+ cells adjacent to its nearest neighbor⁺/panCK⁺Descriptive statistics of the distance of (c); PD-L1 with CD8+ cells adjacent to its nearest neighbor⁺/CD3⁺Descriptive statistics of the distance of (c); panCK⁺CD8 adjacent to the cell⁺Descriptive statistics of the distance of (c); and CD8⁺Mean # PD-L1 within 10, 30 μm of cells⁺/panCK⁺A cell. Table 9 lists a complete list of the calculated features:

TABLE 9

The features were subjected to ReliefF feature selection to determine the importance of each feature in classifying cases according to anti-PD-1 treatment outcome, then the 10 most important features were selected and fitted to a quadrant discriminant classification model to predict response to treatment. The treatment outcome was divided into 3 phenotypes (PD ═ progressive disease; SD ═ stable disease; PR ═ partial response; CR ═ complete response); PD vs SD vs PR + CR; PD vs SD + PR + CR; PD + SD vs PR + CR. Most of the 54 samples had no clear tumor infiltration front, so this feature was excluded from the analysis of the medial and lateral peri-cancerous regions. Each configuration was analyzed using 1) all features, 2) only tumor features, and 3) only epithelial and mesenchymal features. The purpose of this is to remove highly associated functions to explore the impact on the final classification. Because of the small sample size, no cross-validation was performed and the reported classification results represent the classification accuracy on the staining set.

Table 10 summarizes the classification accuracy from different configurations and different feature sets.

Watch 10

The shaded cells show that for the third configuration (binary answer), the multiple (Mpx) IHC data can reach 89% accuracy, while the mismatch repair (MMR) state can only reach 70%. FIG. 7 shows the importance ranking of all features in all cases. The following features were identified as being of primary importance:

(1) the fraction of PD-L1+ macrophages in the stroma,

(2) fraction of PD-L1+ T helper cells in the stroma, and

(3) fraction of PD-L1+ T cells in the stroma.

Mismatch Repair (MMR) deficiency has been shown in the past to predict response to anti-PD-1 therapy. An analysis was performed for mismatch repair-deficient cases only, in order to identify whether multiplex (Mpx) IHC data could identify which MMR-deficient cases responded to anti-PD-1 treatment. FIG. 8 shows the importance ranking of features in the analysis configuration in the case of MMR defects. Fig. 9 is an image showing a stained sample of a patient who completely responded to treatment, and fig. 10 is a patient with progressive disease after treatment. Table 11 shows that classification accuracy of 92% distinguishing PD + SD results from PR + CR can be achieved using epithelial and mesenchymal Mpx IHC data.

TABLE 11

Table 12 shows the confusion matrix for the classification. Of the 37 defect cases, 34 were correctly identified as responders and non-responders by Mpx IHC data, and only 3 were misclassified. In contrast, 53.7% of MMR deficient cases responded to anti-PD-1 treatment.

Answering	Predicted SD + PD by Mpx	PR + CR predicted by Mpx
			Actual SD + PD (15)	13	2
Actual PR + CR (22)	1	21

TABLE 12

Exploring the spatial interaction of PD-1/PD-L1 to predict the response of gastrointestinal tumors to immunotherapy by automated multiplex IHC quantitative image analysis

II.A. background art

In some cancer patients, blocking of the PD-1/L1 axis is an effective immunotherapy. However, identifying predictive biomarkers for patient selection is a significant challenge. Current clinical practice based on PD-L1 expression levels measured by IHC and the emerging biomarkers tumor mutation burden and mismatch repair (MMR) status is inadequate. Predictive value is limited for variable strength of association between study and tumor type. Recent studies have shown that the spatial arrangement and interaction between cancer cells and immune cells can affect patient prognosis, survival, and response to treatment. Multiple Immunohistochemistry (IHC) tissue staining may provide a detailed tumor microenvironment profile based on specific tumor and immune molecular characteristics.

II.B. sample, staining, and image acquisition

This study yielded a cohort of 50 pre-treatment (anti-PD-1 pembrolizumab) patient gastrointestinal tumor samples with acceptable image and tissue quality for automated analysis. Table 13 shows the decline in response.

anti-PD-1 response	Patient #in all pre-treatment samples
		PD (progressive disease)	15
SD (stability disease)	17
		NE (non-evaluable)	3
PR (partial response)	11
		CR (complete response)	4
Total of	50

Watch 13

Samples were formalin fixed, paraffin embedded, sectioned, and mounted on microscope slides.

An overview of staining and image analysis is shown in figure 11. As shown in table 14, in the tyramine signal amplification procedure, slides were stained with fluorescent tyramine dye conjugate in multiplex IHC on a BenchMark ULTRA IHC/ISH automated slide stainer against PanCK, PD-L1, PD1, CD8, LAG 3:

TABLE 14

The stains were applied sequentially as in example I. After the deposition of each stain, a heat kill step was applied, which included the process described by zhang (i). Sequential sections of each sample were also H & E stained using an VENTANA HE 600 automated slide stainer.

The entire slide was scanned with a Zeiss AXIO Z1 scanner, and the pathologist noted the tumor area on it. Halo Hi-Plex software was used for image analysis. MatLab Computer Vision, Image Processing, and Machine Learning Toolbox were used to (a) reconstruct a map of each cell type for spatial locations in the csv file output from Halo; (b) formulating a quantitative measure to characterize the interaction between different cell signals; (c) ranking and mining the most predictive combinations of features related to anti-PD-1 responses; and (d) building and optimizing a predictive model based on the selected features.

II.C. image annotation and ROI generation

The tumor region ROI and the tumor's infiltration front (if available) are marked in the image by the pathologist. As described in example I, the DPath system automatically labeled epithelial tumor ROIs from aggregates of panCK + cells, and interstitial regions.

II.C. feature calculation and data analysis

Each feature in table 16 was analyzed for each image and ranked by ReliefF and random forest:

TABLE 16

The ranking of the top 15 features from each ranking of ReliefF and random forest is illustrated in fig. 12 and 13, respectively. Of the 190 features analyzed, Relieff and random forests ranked the following features in the first two features in predicting response to treatment: "maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors". Quadrant Discriminant Analysis (QDA) with 5-fold cross validation can yield a prediction accuracy of 85%. When used in combination with "mean # PD-1+ cells within a 20 μm radius of PD-L1+ cells" and "maximum of Lag3+ intensity on CD8+ cells", the accuracy reached 90.2% regardless of MMR status (see fig. 14 and tables 17 and 18).

anti-PD-1 response	MMR defect free	MMR defect
			PD+SD+NE	17	18
PR+CR	1	14

TABLE 17

Prediction factor	MPX	MMR	MPX+MMR
				Rate of accuracy	90.2％	62％	80％

Watch 18

Other features have a lower accuracy (e.g., 60% -70%).

FIGS. 14A-14C show: (a) predictive value of spatial variance # PD-1+ cells within a 10 μm radius of PD-L1+ cells; (b) PD-L1⁺Mean # PD-1 within a 20 μm radius of the cells_{Low strength}CD8⁺A predicted value of the cell; (c) CD8⁺Lag3⁺Predicted value of the maximum of the lang 3 intensity in cells; and (d) displaying a scatter plot of (a) versus (b).

FIG. 15 shows an exemplary IHC image of a non-responder and shows PD-L1⁺Location of cells (grey dots), PD-1 within 20 μm of PD-L1+ cells_{Is low in}Cells (white point), and PD-1 within 10 μm of PD-L1+ cells⁺Graphical reconstruction of cells (black dots). It can be seen that there is also a similar presence of PD-L1+ cells in non-responders and responders. However, PD-L1 in responders and non-responders⁺Within 20 μm of the cells, responders showed CD8+ PD-1_{Is low in}Higher presence of cells. Furthermore, PD-1 within 10 μm of PD-L1+ cells in responders compared to non-responders⁺The cells are distributed more evenly.

II.D. survival assay

Total survival (OS) data for a subset of 46 patients was available. Survival analysis was performed for each variable in table 14. The following variables may significantly predict survival benefit: (a) bag 3 in the panCK-negative region⁺/CD8⁺Number of cells and CD8⁺The ratio of the total number of cells; (b) bag 3 in the panCK-negative region^–/CD8⁺Cells and CD8⁺Ratio of cell numbers, (c) Lan 3⁺/panCK^–The number of cells divided by the panCK-negative area, (d) the number of bag 3 positive cells in the panCK-negative region, (e) CD8⁺Maximum value of the intensity of Lang 3 in the cells, (f) number of Lang 3+ cells in the positive region of panCK, (g) PD-L1⁺/panCK⁺PD-1 within a 10 μm radius of a cell_InAverage number of/CD 8+ cells, (h) PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_InAverage number of/CD 8+ cells, (i) PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_InVariance of the number of/CD 8+ cells, (j) PD-L1⁺/panCK⁺PD-1 within a 20 μm radius of a cell_InVariance of the number of/CD 8+ cells, (k) PD-L1⁺PD-1 within a 10 μm radius of a cell_{Is low in}Variance of the number of/CD 8+ cells, (L) PD-L1⁺/CD8⁺PD-1 within a 20 μm radius of a cell_InMaximum number of/CD 8+ cells, and (m) PD-L1⁺PD-1 within a 20 μm radius of a cell_InMaximum number of/CD 8+ cells. For each feature index, the queues are divided into two groups using the median of the feature metric distribution as a cutoff value. Kaplan-Meier survival curves are shown in FIGS. 16A-16M.

Exemplary image analysis System and clinical workflow

In clinical practice, scoring functions can be integrated into prognostic analysis and treatment decision making. After biopsy or surgical resection of the tumor, representative tissue blocks showing tumor cross sections from patient tumor samples were selected for analysis. At least three 4 μm thick sections were cut from the tissue block and transferred to glass slides. The sections were stained as:

IHC negative control (i.e. a protocol in which staining was performed with primary antibody diluent instead of primary antibody);

2. multiple IHC (including at least PD-L1, PD1, CD8, and LAG3 primary antibody); and

3.H&E。

all sections were scanned on a slide scanner. The images are transmitted to the digital pathology system along with slide metadata. Slide metadata, including identification of tumor samples and staining of slides (H & E, IHC or negative controls), may be entered by the user while scanning the slides, or may be automatically obtained from a laboratory information system. The digital pathology system uses slide metadata triggers to perform automatic calculations of one or more features of table 9 or table 16. For example, the characteristics include at least the maximum number of CD8+/PD-1 low-intensity cells within 20 μm of PD-L1+ cells in epithelial tumors, and optionally further include "mean # PD-1+ cells within a 20 μm radius of PD-L1+ cells" and "maximum value of Lag3+ intensity on CD8+ cells".

In a digital pathology system, a pathologist or professional observer would open up a digital image of the H & E slide in viewing software to see the relevant morphological regions to score. The user then annotates the tumor using an annotation tool provided by the viewing software. Typically, a tumor is defined by creating one or more contours and identifying them as tumor contours. To do this, the user creates other contours that intersect the tumor contour. The intersection points define the beginning and end of the slice on the contour of the tumor involved in the infiltration process. The new contour is determined as the wetted edge.

The user then triggers the automatic transfer of the annotation onto the adjacent IHC slide. The digital pathology system provides a display function that allows for the transfer of annotations to adjacent slides while taking into account the location, orientation, and local deformation of the tissue slices. The user opens the IHC slide image in the viewer software and controls the position of the automatically displayed callout. Viewer software provides tools for modifying and editing annotations as necessary. Editing functions include moving the callout, rotating the callout, and locally modifying its outline. The user further examines the IHC slide image for tissue, staining, or imaging artifacts in the viewer software. The user delineates such artifact areas with annotations and identifies them to exclude from analysis.

In a digital pathology system, a user may select one or more IHC slides and trigger report generation. The user may obtain a quality control report, which may include the following components:

1. slide shows low to medium resolution images of all tissues on the slide

2. The same low to medium resolution image is overlaid with outlined and/or transparent colored regions that indicate morphological regions of interest, such as tumor margins. Furthermore, the image is covered with regions that are marked to be excluded from the analysis.

3. Identical low to medium resolution images with automatically generated small rectangular markers indicating the position of the high resolution FOV for quality control

4. Each high resolution FOV

5. Each high resolution FOV is covered with markers indicating the presence of each cellular phenotype as determined by automatic cell counting.

Alternatively, the morphological regions of interest and the markers indicative of cells from the automated cell count may also be displayed in the viewer software.

The user reviews the QC data and decides to accept or reject the case. For accepted cases, the digital pathology system reports quantitative readings and passes them to the scoring module. These quantitative readings may include:

1. area of each morphological region of interest (in mm)²Representation).

2. The number of cells in the morphological region of interest.

3. Descriptive statistics describe the spatial distribution of cells of different phenotypes and/or spatial relationships between cells in each morphological region of interest.

Additional information about the sample may be further input into the digital pathology system, such as MMR status (prior to exposure of the subject to therapy (e.g., chemotherapy, radiation therapy, and/or targeted therapy)), tumor score with TNM staging system and/or overall tumor staging, and clinical variables (e.g., age, directionality of the tumor, number of lymph nodes harvested, and sex of the patient), which the system may use to, for example, select an appropriate scoring function to apply to the image. Additionally or alternatively, the user may select an appropriate scoring function based on such criteria or other criteria. The scoring module calculates a score based on the extracted features, which may be reported as raw numbers. Further, the interval function can be applied to the score to assess the risk interval to which the patient belongs (e.g., by applying a cutoff value between populations based on "likely to respond" or "unlikely to respond" to the checkpoint inhibitor) and/or population stratification interval (e.g., based on the scored quartile or decile interval); and/or a feature selection function to rank the scores. The clinician reviews the report and discusses the results based on the results of the clinical pathologist's decision with the patient, which can then be used to make treatment decisions for the patient.

Reference to the literature

Barrera et al, Computer-induced features relating to spatial arrangement of motion-induced catalysis to prediction response to n-small cell-containing cancer (NSCLC). ASCO Annual Meeting 2018: Abstract #:12115.

Le et al, PD-1Block in Tumors with Mismatch-Repair Deficiency, N Engl J Med.2015 Jun 25; 372(26) 2509-20 ("le (I)").

Le et al, Mismatch-repeat deficience predictions of PD-1blockade, Science,10.1126/Science, aan6733(2017) ("Le (II)").

Li & Tian, Development of small-molecule immune therapy inhibitors of PD-1/PD-L1 as a new therapeutic protocol for tumor therapy, J.of Drug Targeting, DOI:10.1080/1061186X.2018.1440400 (date of Web publication 2018, 2/20).

Nordic Immunochistochemical Quality Control, CK-Pan run 47(2016), reference http:// www.nordiqc.org/downloads/assessages/82 _85.pdf (last access 2018, 10/4) ("NordiQC").

Topalian, Suzanne l. "Safety, activity, and immune complexes of anti-PD-1 antibody in cancer," New England Journal of Medicine 366.26(2012):2443 2454.

Wang et al, preliminary of recording in early stage non-small cell containing computer extracted nuclear sources from digital H & E images, Scientific Reports 7.1(2017):13543.

Woodcock-Mitchell et al. Immunological catalysis of ketamine polypeptides in human epitopic antigens.J Cell biol.1982; 95(2):580-588.

Yi et al, Biomarkers for predicting efficacy of PD-1/PD-L1 inhibitors, Mol cancer.2018; 17:129 (web publishing date 2018, 8, 23 and month)

Zhang et al. "automatic 5-plex fluoro immunological chemistry with a type signal amplification using antibodies from the same categories experiments," J Immunother cancer. 2015; 3(Suppl 2): P111 ("Zhang (I)").

Zhang et al. "Cancer Research 2016,76(14 Supplement):5117 (" Zhang (II) ") is described in the specification of" An automated 5-plex fluorescence enabled characterization of PD-L1 expression and tumor profiling immune cells in recess and binder cameras spec.

Sequence listing

<110> Wentana Medical Systems Inc. (Ventana Medical Systems, Inc.)

John Hopkins University (Johns Hopkins University)

Commemorative Sloan coding Cancer Center (Memorial Sloan coding Cancer Center)

<120> methods and systems for predicting response to PD-1 axis guided therapy

<130> 3000022-004977

<150> US 62/739,828

<151> 2018-10-01

<150> US 62/742,934

<151> 2018-10-09

<160> 10

<170> PatentIn version 3.5

<210> 1

<211> 182

<212> PRT

<213> Intelligent people

<400> 1

Met Glu Gln Gly Lys Gly Leu Ala Val Leu Ile Leu Ala Ile Ile Leu

1 5 10 15

Leu Gln Gly Thr Leu Ala Gln Ser Ile Lys Gly Asn His Leu Val Lys

20 25 30

Val Tyr Asp Tyr Gln Glu Asp Gly Ser Val Leu Leu Thr Cys Asp Ala

35 40 45

Glu Ala Lys Asn Ile Thr Trp Phe Lys Asp Gly Lys Met Ile Gly Phe

50 55 60

Leu Thr Glu Asp Lys Lys Lys Trp Asn Leu Gly Ser Asn Ala Lys Asp

65 70 75 80

Pro Arg Gly Met Tyr Gln Cys Lys Gly Ser Gln Asn Lys Ser Lys Pro

85 90 95

Leu Gln Val Tyr Tyr Arg Met Cys Gln Asn Cys Ile Glu Leu Asn Ala

100 105 110

Ala Thr Ile Ser Gly Phe Leu Phe Ala Glu Ile Val Ser Ile Phe Val

115 120 125

Leu Ala Val Gly Val Tyr Phe Ile Ala Gly Gln Asp Gly Val Arg Gln

130 135 140

Ser Arg Ala Ser Asp Lys Gln Thr Leu Leu Pro Asn Asp Gln Leu Tyr

145 150 155 160

Gln Pro Leu Lys Asp Arg Glu Asp Asp Gln Tyr Ser His Leu Gln Gly

165 170 175

Asn Gln Leu Arg Arg Asn

180

<210> 2

<211> 171

<212> PRT

<213> Intelligent people

<400> 2

Met Glu His Ser Thr Phe Leu Ser Gly Leu Val Leu Ala Thr Leu Leu

1 5 10 15

Ser Gln Val Ser Pro Phe Lys Ile Pro Ile Glu Glu Leu Glu Asp Arg

20 25 30

Val Phe Val Asn Cys Asn Thr Ser Ile Thr Trp Val Glu Gly Thr Val

35 40 45

Gly Thr Leu Leu Ser Asp Ile Thr Arg Leu Asp Leu Gly Lys Arg Ile

50 55 60

Leu Asp Pro Arg Gly Ile Tyr Arg Cys Asn Gly Thr Asp Ile Tyr Lys

65 70 75 80

Asp Lys Glu Ser Thr Val Gln Val His Tyr Arg Met Cys Gln Ser Cys

85 90 95

Val Glu Leu Asp Pro Ala Thr Val Ala Gly Ile Ile Val Thr Asp Val

100 105 110

Ile Ala Thr Leu Leu Leu Ala Leu Gly Val Phe Cys Phe Ala Gly His

115 120 125

Glu Thr Gly Arg Leu Ser Gly Ala Ala Asp Thr Gln Ala Leu Leu Arg

130 135 140

Asn Asp Gln Val Tyr Gln Pro Leu Arg Asp Arg Asp Asp Ala Gln Tyr

145 150 155 160

Ser His Leu Gly Gly Asn Trp Ala Arg Asn Lys

165 170

<210> 3

<211> 207

<212> PRT

<213> Intelligent people

<400> 3

Met Gln Ser Gly Thr His Trp Arg Val Leu Gly Leu Cys Leu Leu Ser

1 5 10 15

Val Gly Val Trp Gly Gln Asp Gly Asn Glu Glu Met Gly Gly Ile Thr

20 25 30

Gln Thr Pro Tyr Lys Val Ser Ile Ser Gly Thr Thr Val Ile Leu Thr

35 40 45

Cys Pro Gln Tyr Pro Gly Ser Glu Ile Leu Trp Gln His Asn Asp Lys

50 55 60

Asn Ile Gly Gly Asp Glu Asp Asp Lys Asn Ile Gly Ser Asp Glu Asp

65 70 75 80

His Leu Ser Leu Lys Glu Phe Ser Glu Leu Glu Gln Ser Gly Tyr Tyr

85 90 95

Val Cys Tyr Pro Arg Gly Ser Lys Pro Glu Asp Ala Asn Phe Tyr Leu

100 105 110

Tyr Leu Arg Ala Arg Val Cys Glu Asn Cys Met Glu Met Asp Val Met

115 120 125

Ser Val Ala Thr Ile Val Ile Val Asp Ile Cys Ile Thr Gly Gly Leu

130 135 140

Leu Leu Leu Val Tyr Tyr Trp Ser Lys Asn Arg Lys Ala Lys Ala Lys

145 150 155 160

Pro Val Thr Arg Gly Ala Gly Ala Gly Gly Arg Gln Arg Gly Gln Asn

165 170 175

Lys Glu Arg Pro Pro Pro Val Pro Asn Pro Asp Tyr Glu Pro Ile Arg

180 185 190

Lys Gly Gln Arg Asp Leu Tyr Ser Gly Leu Asn Gln Arg Arg Ile

195 200 205

<210> 4

<211> 164

<212> PRT

<213> Intelligent people

<400> 4

Met Lys Trp Lys Ala Leu Phe Thr Ala Ala Ile Leu Gln Ala Gln Leu

1 5 10 15

Pro Ile Thr Glu Ala Gln Ser Phe Gly Leu Leu Asp Pro Lys Leu Cys

20 25 30

Tyr Leu Leu Asp Gly Ile Leu Phe Ile Tyr Gly Val Ile Leu Thr Ala

35 40 45

Leu Phe Leu Arg Val Lys Phe Ser Arg Ser Ala Asp Ala Pro Ala Tyr

50 55 60

Gln Gln Gly Gln Asn Gln Leu Tyr Asn Glu Leu Asn Leu Gly Arg Arg

65 70 75 80

Glu Glu Tyr Asp Val Leu Asp Lys Arg Arg Gly Arg Asp Pro Glu Met

85 90 95

Gly Gly Lys Pro Gln Arg Arg Lys Asn Pro Gln Glu Gly Leu Tyr Asn

100 105 110

Glu Leu Gln Lys Asp Lys Met Ala Glu Ala Tyr Ser Glu Ile Gly Met

115 120 125

Lys Gly Glu Arg Arg Arg Gly Lys Gly His Asp Gly Leu Tyr Gln Gly

130 135 140

Leu Ser Thr Ala Thr Lys Asp Thr Tyr Asp Ala Leu His Met Gln Ala

145 150 155 160

Leu Pro Pro Arg

<210> 5

<211> 235

<212> PRT

<213> Intelligent people

<400> 5

Met Ala Leu Pro Val Thr Ala Leu Leu Leu Pro Leu Ala Leu Leu Leu

1 5 10 15

His Ala Ala Arg Pro Ser Gln Phe Arg Val Ser Pro Leu Asp Arg Thr

20 25 30

Trp Asn Leu Gly Glu Thr Val Glu Leu Lys Cys Gln Val Leu Leu Ser

35 40 45

Asn Pro Thr Ser Gly Cys Ser Trp Leu Phe Gln Pro Arg Gly Ala Ala

50 55 60

Ala Ser Pro Thr Phe Leu Leu Tyr Leu Ser Gln Asn Lys Pro Lys Ala

65 70 75 80

Ala Glu Gly Leu Asp Thr Gln Arg Phe Ser Gly Lys Arg Leu Gly Asp

85 90 95

Thr Phe Val Leu Thr Leu Ser Asp Phe Arg Arg Glu Asn Glu Gly Tyr

100 105 110

Tyr Phe Cys Ser Ala Leu Ser Asn Ser Ile Met Tyr Phe Ser His Phe

115 120 125

Val Pro Val Phe Leu Pro Ala Lys Pro Thr Thr Thr Pro Ala Pro Arg

130 135 140

Pro Pro Thr Pro Ala Pro Thr Ile Ala Ser Gln Pro Leu Ser Leu Arg

145 150 155 160

Pro Glu Ala Cys Arg Pro Ala Ala Gly Gly Ala Val His Thr Arg Gly

165 170 175

Leu Asp Phe Ala Cys Asp Ile Tyr Ile Trp Ala Pro Leu Ala Gly Thr

180 185 190

Cys Gly Val Leu Leu Leu Ser Leu Val Ile Thr Leu Tyr Cys Asn His

195 200 205

Arg Asn Arg Arg Arg Val Cys Lys Cys Pro Arg Pro Val Val Lys Ser

210 215 220

Gly Asp Lys Pro Ser Leu Ser Ala Arg Tyr Val

225 230 235

<210> 6

<211> 210

<212> PRT

<213> Intelligent people

<400> 6

Met Arg Pro Arg Leu Trp Leu Leu Leu Ala Ala Gln Leu Thr Val Leu

1 5 10 15

His Gly Asn Ser Val Leu Gln Gln Thr Pro Ala Tyr Ile Lys Val Gln

20 25 30

Thr Asn Lys Met Val Met Leu Ser Cys Glu Ala Lys Ile Ser Leu Ser

35 40 45

Asn Met Arg Ile Tyr Trp Leu Arg Gln Arg Gln Ala Pro Ser Ser Asp

50 55 60

Ser His His Glu Phe Leu Ala Leu Trp Asp Ser Ala Lys Gly Thr Ile

65 70 75 80

His Gly Glu Glu Val Glu Gln Glu Lys Ile Ala Val Phe Arg Asp Ala

85 90 95

Ser Arg Phe Ile Leu Asn Leu Thr Ser Val Lys Pro Glu Asp Ser Gly

100 105 110

Ile Tyr Phe Cys Met Ile Val Gly Ser Pro Glu Leu Thr Phe Gly Lys

115 120 125

Gly Thr Gln Leu Ser Val Val Asp Phe Leu Pro Thr Thr Ala Gln Pro

130 135 140

Thr Lys Lys Ser Thr Leu Lys Lys Arg Val Cys Arg Leu Pro Arg Pro

145 150 155 160

Glu Thr Gln Lys Gly Pro Leu Cys Ser Pro Ile Thr Leu Gly Leu Leu

165 170 175

Val Ala Gly Val Leu Val Leu Leu Val Ser Leu Gly Val Ala Ile His

180 185 190

Leu Cys Cys Arg Arg Arg Arg Ala Arg Leu Arg Phe Met Lys Gln Phe

195 200 205

Tyr Lys

210

<210> 7

<211> 354

<212> PRT

<213> Intelligent people

<400> 7

Met Arg Leu Ala Val Leu Phe Ser Gly Ala Leu Leu Gly Leu Leu Ala

1 5 10 15

Ala Gln Gly Thr Gly Asn Asp Cys Pro His Lys Lys Ser Ala Thr Leu

20 25 30

Leu Pro Ser Phe Thr Val Thr Pro Thr Val Thr Glu Ser Thr Gly Thr

35 40 45

Thr Ser His Arg Thr Thr Lys Ser His Lys Thr Thr Thr His Arg Thr

50 55 60

Thr Thr Thr Gly Thr Thr Ser His Gly Pro Thr Thr Ala Thr His Asn

65 70 75 80

Pro Thr Thr Thr Ser His Gly Asn Val Thr Val His Pro Thr Ser Asn

85 90 95

Ser Thr Ala Thr Ser Gln Gly Pro Ser Thr Ala Thr His Ser Pro Ala

100 105 110

Thr Thr Ser His Gly Asn Ala Thr Val His Pro Thr Ser Asn Ser Thr

115 120 125

Ala Thr Ser Pro Gly Phe Thr Ser Ser Ala His Pro Glu Pro Pro Pro

130 135 140

Pro Ser Pro Ser Pro Ser Pro Thr Ser Lys Glu Thr Ile Gly Asp Tyr

145 150 155 160

Thr Trp Thr Asn Gly Ser Gln Pro Cys Val His Leu Gln Ala Gln Ile

165 170 175

Gln Ile Arg Val Met Tyr Thr Thr Gln Gly Gly Gly Glu Ala Trp Gly

180 185 190

Ile Ser Val Leu Asn Pro Asn Lys Thr Lys Val Gln Gly Ser Cys Glu

195 200 205

Gly Ala His Pro His Leu Leu Leu Ser Phe Pro Tyr Gly His Leu Ser

210 215 220

Phe Gly Phe Met Gln Asp Leu Gln Gln Lys Val Val Tyr Leu Ser Tyr

225 230 235 240

Met Ala Val Glu Tyr Asn Val Ser Phe Pro His Ala Ala Gln Trp Thr

245 250 255

Phe Ser Ala Gln Asn Ala Ser Leu Arg Asp Leu Gln Ala Pro Leu Gly

260 265 270

Gln Ser Phe Ser Cys Ser Asn Ser Ser Ile Ile Leu Ser Pro Ala Val

275 280 285

His Leu Asp Leu Leu Ser Leu Arg Leu Gln Ala Ala Gln Leu Pro His

290 295 300

Thr Gly Val Phe Gly Gln Ser Phe Ser Cys Pro Ser Asp Arg Ser Ile

305 310 315 320

Leu Leu Pro Leu Ile Ile Gly Leu Ile Leu Leu Gly Leu Leu Ala Leu

325 330 335

Val Leu Ile Ala Phe Cys Ile Ile Arg Arg Arg Pro Ser Ala Tyr Gln

340 345 350

Ala Leu

<210> 8

<211> 288

<212> PRT

<213> Intelligent people

<400> 8

Met Gln Ile Pro Gln Ala Pro Trp Pro Val Val Trp Ala Val Leu Gln

1 5 10 15

Leu Gly Trp Arg Pro Gly Trp Phe Leu Asp Ser Pro Asp Arg Pro Trp

20 25 30

Asn Pro Pro Thr Phe Ser Pro Ala Leu Leu Val Val Thr Glu Gly Asp

35 40 45

Asn Ala Thr Phe Thr Cys Ser Phe Ser Asn Thr Ser Glu Ser Phe Val

50 55 60

Leu Asn Trp Tyr Arg Met Ser Pro Ser Asn Gln Thr Asp Lys Leu Ala

65 70 75 80

Ala Phe Pro Glu Asp Arg Ser Gln Pro Gly Gln Asp Cys Arg Phe Arg

85 90 95

Val Thr Gln Leu Pro Asn Gly Arg Asp Phe His Met Ser Val Val Arg

100 105 110

Ala Arg Arg Asn Asp Ser Gly Thr Tyr Leu Cys Gly Ala Ile Ser Leu

115 120 125

Ala Pro Lys Ala Gln Ile Lys Glu Ser Leu Arg Ala Glu Leu Arg Val

130 135 140

Thr Glu Arg Arg Ala Glu Val Pro Thr Ala His Pro Ser Pro Ser Pro

145 150 155 160

Arg Pro Ala Gly Gln Phe Gln Thr Leu Val Val Gly Val Val Gly Gly

165 170 175

Leu Leu Gly Ser Leu Val Leu Leu Val Trp Val Leu Ala Val Ile Cys

180 185 190

Ser Arg Ala Ala Arg Gly Thr Ile Gly Ala Arg Arg Thr Gly Gln Pro

195 200 205

Leu Lys Glu Asp Pro Ser Ala Val Pro Val Phe Ser Val Asp Tyr Gly

210 215 220

Glu Leu Asp Phe Gln Trp Arg Glu Lys Thr Pro Glu Pro Pro Val Pro

225 230 235 240

Cys Val Pro Glu Gln Thr Glu Tyr Ala Thr Ile Val Phe Pro Ser Gly

245 250 255

Met Gly Thr Ser Ser Pro Ala Arg Arg Gly Ser Ala Asp Gly Pro Arg

260 265 270

Ser Ala Gln Pro Leu Arg Pro Glu Asp Gly His Cys Ser Trp Pro Leu

275 280 285

<210> 9

<211> 290

<212> PRT

<213> Intelligent people

<400> 9

Met Arg Ile Phe Ala Val Phe Ile Phe Met Thr Tyr Trp His Leu Leu

1 5 10 15

Asn Ala Phe Thr Val Thr Val Pro Lys Asp Leu Tyr Val Val Glu Tyr

20 25 30

Gly Ser Asn Met Thr Ile Glu Cys Lys Phe Pro Val Glu Lys Gln Leu

35 40 45

Asp Leu Ala Ala Leu Ile Val Tyr Trp Glu Met Glu Asp Lys Asn Ile

50 55 60

Ile Gln Phe Val His Gly Glu Glu Asp Leu Lys Val Gln His Ser Ser

65 70 75 80

Tyr Arg Gln Arg Ala Arg Leu Leu Lys Asp Gln Leu Ser Leu Gly Asn

85 90 95

Ala Ala Leu Gln Ile Thr Asp Val Lys Leu Gln Asp Ala Gly Val Tyr

100 105 110

Arg Cys Met Ile Ser Tyr Gly Gly Ala Asp Tyr Lys Arg Ile Thr Val

115 120 125

Lys Val Asn Ala Pro Tyr Asn Lys Ile Asn Gln Arg Ile Leu Val Val

130 135 140

Asp Pro Val Thr Ser Glu His Glu Leu Thr Cys Gln Ala Glu Gly Tyr

145 150 155 160

Pro Lys Ala Glu Val Ile Trp Thr Ser Ser Asp His Gln Val Leu Ser

165 170 175

Gly Lys Thr Thr Thr Thr Asn Ser Lys Arg Glu Glu Lys Leu Phe Asn

180 185 190

Val Thr Ser Thr Leu Arg Ile Asn Thr Thr Thr Asn Glu Ile Phe Tyr

195 200 205

Cys Thr Phe Arg Arg Leu Asp Pro Glu Glu Asn His Thr Ala Glu Leu

210 215 220

Val Ile Pro Glu Leu Pro Leu Ala His Pro Pro Asn Glu Arg Thr His

225 230 235 240

Leu Val Ile Leu Gly Ala Ile Leu Leu Cys Leu Gly Val Ala Leu Thr

245 250 255

Phe Ile Phe Arg Leu Arg Lys Gly Arg Met Met Asp Val Lys Lys Cys

260 265 270

Gly Ile Gln Asp Thr Asn Ser Lys Lys Gln Ser Asp Thr His Leu Glu

275 280 285

Glu Thr

290

<210> 10

<211> 525

<212> PRT

<213> Intelligent people

<400> 10

Met Trp Glu Ala Gln Phe Leu Gly Leu Leu Phe Leu Gln Pro Leu Trp

1 5 10 15

Val Ala Pro Val Lys Pro Leu Gln Pro Gly Ala Glu Val Pro Val Val

20 25 30

Trp Ala Gln Glu Gly Ala Pro Ala Gln Leu Pro Cys Ser Pro Thr Ile

35 40 45

Pro Leu Gln Asp Leu Ser Leu Leu Arg Arg Ala Gly Val Thr Trp Gln

50 55 60

His Gln Pro Asp Ser Gly Pro Pro Ala Ala Ala Pro Gly His Pro Leu

65 70 75 80

Ala Pro Gly Pro His Pro Ala Ala Pro Ser Ser Trp Gly Pro Arg Pro

85 90 95

Arg Arg Tyr Thr Val Leu Ser Val Gly Pro Gly Gly Leu Arg Ser Gly

100 105 110

Arg Leu Pro Leu Gln Pro Arg Val Gln Leu Asp Glu Arg Gly Arg Gln

115 120 125

Arg Gly Asp Phe Ser Leu Trp Leu Arg Pro Ala Arg Arg Ala Asp Ala

130 135 140

Gly Glu Tyr Arg Ala Ala Val His Leu Arg Asp Arg Ala Leu Ser Cys

145 150 155 160

Arg Leu Arg Leu Arg Leu Gly Gln Ala Ser Met Thr Ala Ser Pro Pro

165 170 175

Gly Ser Leu Arg Ala Ser Asp Trp Val Ile Leu Asn Cys Ser Phe Ser

180 185 190

Arg Pro Asp Arg Pro Ala Ser Val His Trp Phe Arg Asn Arg Gly Gln

195 200 205

Gly Arg Val Pro Val Arg Glu Ser Pro His His His Leu Ala Glu Ser

210 215 220

Phe Leu Phe Leu Pro Gln Val Ser Pro Met Asp Ser Gly Pro Trp Gly

225 230 235 240

Cys Ile Leu Thr Tyr Arg Asp Gly Phe Asn Val Ser Ile Met Tyr Asn

245 250 255

Leu Thr Val Leu Gly Leu Glu Pro Pro Thr Pro Leu Thr Val Tyr Ala

260 265 270

Gly Ala Gly Ser Arg Val Gly Leu Pro Cys Arg Leu Pro Ala Gly Val

275 280 285

Gly Thr Arg Ser Phe Leu Thr Ala Lys Trp Thr Pro Pro Gly Gly Gly

290 295 300

Pro Asp Leu Leu Val Thr Gly Asp Asn Gly Asp Phe Thr Leu Arg Leu

305 310 315 320

Glu Asp Val Ser Gln Ala Gln Ala Gly Thr Tyr Thr Cys His Ile His

325 330 335

Leu Gln Glu Gln Gln Leu Asn Ala Thr Val Thr Leu Ala Ile Ile Thr

340 345 350

Val Thr Pro Lys Ser Phe Gly Ser Pro Gly Ser Leu Gly Lys Leu Leu

355 360 365

Cys Glu Val Thr Pro Val Ser Gly Gln Glu Arg Phe Val Trp Ser Ser

370 375 380

Leu Asp Thr Pro Ser Gln Arg Ser Phe Ser Gly Pro Trp Leu Glu Ala

385 390 395 400

Gln Glu Ala Gln Leu Leu Ser Gln Pro Trp Gln Cys Gln Leu Tyr Gln

405 410 415

Gly Glu Arg Leu Leu Gly Ala Ala Val Tyr Phe Thr Glu Leu Ser Ser

420 425 430

Pro Gly Ala Gln Arg Ser Gly Arg Ala Pro Gly Ala Leu Pro Ala Gly

435 440 445

His Leu Leu Leu Phe Leu Ile Leu Gly Val Leu Ser Leu Leu Leu Leu

450 455 460

Val Thr Gly Ala Phe Gly Phe His Leu Trp Arg Arg Gln Trp Arg Pro

465 470 475 480

Arg Arg Phe Ser Ala Leu Glu Gln Gly Ile His Pro Pro Gln Ala Gln

485 490 495

Ser Lys Ile Glu Glu Leu Glu Gln Glu Pro Glu Pro Glu Pro Glu Pro

500 505 510

Glu Pro Glu Pro Glu Pro Glu Pro Glu Pro Glu Gln Leu

515 520 525