Neoantigen Classifier for Immunotherapy Response Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting and selecting neoantigens are not effective in identifying cancer patients who are immunotherapy responders, and the existing methods fail to accurately identify cancer patients who are immunotherapy responders, and the existing methods fail to accurately identify cancer patients who are immunotherapy responders, and the existing methods fail to accurately identify cancer patients who are immunotherapy responders, and the existing methods fail to accurately identify cancer patients who are immunotherapy responders, and the existing methods are unable to accurately identify cancer patients who are immunotherapy responders, and the existing methods are unable to accurately identify cancer patients who are immunotherapy non-responders.
Innovation Solution
Perform whole exome sequencing and RNA sequencing on a tumor sample to quantify neoantigens, unique T- and B-cell receptors, and immune cell populations, and use machine learning models to identify cancer patients as immunotherapy responders, using customized panels of cancer genes and personalized vaccines based on neoantigen classifiers and immune cell enrichment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If tumor mutational burden (TMB) is used as a biomarker to predict immunotherapy response, then the number of cancer mutations can be quantified, but not all mutations produce neoantigens or elicit an immune response, making TMB an imperfect biomarker
Solution Approach 1:
The patent segments the TMB measurement into multiple components: (1) quantification of total mutations, (2) prediction of neoantigen presentation for each mutation, (3) assessment of immune cell infiltration, and (4) evaluation of T-cell receptor diversity. This segmentation allows identification of which mutations actually contribute to immune response, resolving the limitation that not all mutations produce functional neoantigens
Solution Approach 2:
The patent changes the predictive parameters from simple mutation count (TMB) to a multi-parameter model including neoantigen presentation scores, immune cell population proportions, and T-cell receptor diversity metrics. This parameter transformation enables more accurate prediction of immunotherapy response by capturing the biological complexity of immune recognition
2Measurement precision
If multiple sequencing methods (whole exome sequencing, whole genome sequencing, RNA sequencing) are performed to quantify neoantigens and immune cell populations, then the accuracy of identifying immunotherapy responders is improved, but the complexity and cost of the testing procedure increases
Solution Approach 1:
The patent employs a unified computational framework that processes data from multiple sequencing methods (whole exome sequencing, whole genome sequencing, RNA sequencing) simultaneously. This multi-functional system extracts neoantigen predictions, immune cell population estimates, and T-cell receptor diversity metrics from integrated data, reducing the need for separate analysis pipelines and simplifying the overall workflow despite using multiple sequencing technologies
Data Source
AI summary
A system and corresponding method are provided for identifying a subpopulation of cancer patients who are immunotherapy respondents. An effective method of assessing neoantigen presentation is provided. A vaccine composition is also provided. The vaccine composition is prepared by feeding data for a subject with a type of cancer into a predictive model and scoring neoantigens that occur in data for the subject for one or more parameters. One or more vaccine compositions to be administered to the subject are prepared for one or more somatic mutations for one or more neoantigens that satisfy an immune stimulation threshold.