Scoring Function for dMMR Colorectal Tumor Response Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biomarkers are ineffective in predicting the response of deficient mismatch repair (dMMR) colorectal tumors to PD-1 axis-directed therapies, leading to uncertainty in patient selection for immune checkpoint inhibitor therapy.
Innovation Solution
Development of scoring functions that integrate spatial relationships between immune cell types, such as the number of PD-1+ cells near PD-L1+ cells, to predict the likelihood of response to PD-1 axis-directed therapy, using Cox proportional hazard models and affinity histochemical assays for tissue analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If PD-L1 expression is used as a predictive biomarker for patient selection, then patient selection can be simplified, but prediction accuracy is insufficient for colorectal cancer patients
Solution Approach 1:
The patent segments the predictive biomarker assessment into multiple independent components: PD-L1 expression level, tumor mutational burden (TMB), and spatial immune cell architecture metrics. Each component is measured and evaluated separately, then integrated to form a comprehensive prediction model, thereby improving accuracy while maintaining operational feasibility through standardized assessment protocols for each parameter
Solution Approach 2:
The patent creates a composite biomarker signature by combining multiple distinct biomarker types (protein expression PD-L1, genomic feature TMB, and spatial cellular arrangement metrics) into an integrated predictive model. This composite approach leverages the complementary information from each biomarker type to achieve superior prediction accuracy compared to any single biomarker alone
2Measurement precision
If more biomarker parameters are integrated into the scoring function, then prediction accuracy improves, but test complexity and cost increase
Solution Approach 1:
The patent divides the comprehensive biomarker assessment into modular testing components that can be performed independently: immunohistochemistry for PD-L1 and spatial imaging for immune cell distribution, and genomic sequencing for TMB. Each module produces a specific parameter that feeds into the overall scoring function, allowing laboratories to implement the full panel or select subsets based on resource availability while maintaining prediction accuracy
Solution Approach 2:
The patent develops a universal scoring function framework that can accommodate multiple different biomarker parameters and input types through a standardized computational model. This multi-functional scoring system processes diverse inputs (continuous values, categorical data, spatial metrics) using consistent algorithms, enabling the system to maintain high prediction accuracy across varying levels of test complexity and different laboratory capabilities
Data Source
AI summary
Scoring functions for predicting response of a dMMR and/or MSI-H colorectal tumor to a PD-1 axis-directed therapy are disclosed, as well as methods and systems for evaluating tissue samples for the presence of feature metrics useful in computing such scoring functions. The scoring functions integrate one or more spatial relationships between cell types into a numerical indication of the likelihood that the tumor will respond to the PD-1 axis-directed therapy. Based on the output of the scoring function, a subject may then be selected to receive a PD-1 axis-directed therapy (if the scoring function indicates a sufficient likelihood of positive response) or an alternative therapy (if the scoring function indicates an insufficient likelihood of positive response).