Next-generation molecular profiling
Inventors
Abraham, Jim • Spetzler, David • Helmstetter, Anthony • Korn, Wolfgang Michael • Magee, Daniel
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11315673-B2
Publication Date
2022-04-26
Expiration Date
Abstract
Comprehensive molecular profiling provides a wealth of data concerning the molecular status of patient samples. Such data can be compared to patient response to treatments to identify biomarker signatures that predict response or non-response to such treatments. This approach has been applied to identify biomarker signatures that strongly correlate with response of colorectal cancer patients to FOLFOX. Described herein are data structures, data processing, and machine learning models to predict effectiveness of a treatment for a disease or disorder of a subject having a particular set of biomarkers, as well as an exemplary application of such a model to precision medicine, e.g., to methods for selecting a treatment based on a molecular profile, e.g., a treatment comprising administration of 5-fluorouracil/leucovorin combined with oxaliplatin (FOLFOX) or with irinotecan (FOLFIRI).
Core Innovation
The invention relates to a system for selecting a treatment for a colorectal cancer in a first subject. The system obtains a plurality of copy numbers generated from output data of a next generation sequencer, based on sequencing a biological sample comprising colorectal cancer cells from the first subject, and the plurality of copy numbers include copy number values for groups of genes and/or proximate genomic regions thereto, including Group 1 through Group 5.
Using these obtained copy numbers as input data, the system provides input to a predictive model that includes multiple machine learning models. Each machine learning model is configured to process the obtained copy numbers for one of the groups of genes, generating first data through fifth data that indicate whether the first subject is likely to benefit from a treatment that includes 5-fluorouracil/leucovorin combined with oxaliplatin (FOLFOX).
The system then determines whether a majority of the multiple machine learning classification models indicates that the first subject is likely to benefit from the treatment including FOLFOX. Based on this determination, the system identifies data that identifies the treatment including FOLFOX and provides output identifying the treatment. Additional embodiments specify expanding the analysis to a second subject and identifying an alternative treatment when the majority does not indicate likely benefit from FOLFOX.
Claims Coverage
The claim set includes one independent claim. The independent claim covers an ensemble predictive-model system that processes NGS-derived copy-number groups via multiple machine learning models and uses a majority indication to select whether the first subject is likely to benefit from FOLFOX, then outputs data identifying the treatment including FOLFOX.
NGS-derived copy numbers for gene groups
Obtain a plurality of copy numbers based on output data generated by a next generation sequencer, wherein the next generation sequencer generated the output data by sequencing a biological sample comprising colorectal cancer cells from the first subject, and wherein the plurality of copy numbers include a copy number for each of the following groups of genes or proximate genomic regions thereto: Group 1, Group 2, Group 3, Group 4, and Group 5.
Multiple machine learning models per gene group
Provide input data as input to a predictive model, wherein the input data includes the obtained plurality of copy numbers, wherein the predictive model includes multiple machine learning models, and wherein each machine learning model is configured to process the obtained copy numbers for one of Group 1 through Group 5.
Group-wise benefit predictions for FOLFOX
Process the input data that includes the obtained copy numbers for each group through one of the multiple machine learning models, to generate first data through fifth data indicating whether the first subject is likely to benefit from the treatment that includes 5-fluorouracil/leucovorin combined with oxaliplatin (FOLFOX).
Majority-vote model decision to identify FOLFOX
Determine whether a majority of the multiple machine learning classification models indicate that the first subject is likely to benefit from the treatment that includes FOLFOX; based on a determination that the majority indicate likely benefit, identify data that identifies the treatment that includes FOLFOX; and provide output that identifies the treatment that includes FOLFOX.
Overall, the independent claim requires NGS-derived plurality of copy numbers mapped to five gene-group sets, group-specific machine learning model processing, and an ensemble majority-vote decision to identify that the first subject is likely to benefit from a treatment including FOLFOX, followed by output identifying the treatment.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?