US 12,136,472 B2
Molecular evidence platform for auditable, continuous optimization of variant interpretation in genetic and genomic testing and analysis
Alexandre Colavin, Menlo Park, CA (US); Carlos L. Araya, Palo Alto, CA (US); and Jason A. Reuter, Palo Alto, CA (US)
Assigned to Laboratory Corporation of America Holdings, Burlington, NC (US)
Filed by Laboratory Corporation of America Holdings, Burlington, NC (US)
Filed on Sep. 14, 2023, as Appl. No. 18/368,375.
Application 18/368,375 is a continuation of application No. 17/946,942, filed on Sep. 16, 2022, granted, now 11,798,651.
Application 17/946,942 is a continuation of application No. 16/756,802, previously published as PCT/US2018/056304, filed on Oct. 17, 2018.
Claims priority of provisional application 62/573,458, filed on Oct. 17, 2017.
Prior Publication US 2024/0006021 A1, Jan. 4, 2024
Int. Cl. G16B 20/20 (2019.01); G06F 18/21 (2023.01); G06F 18/2113 (2023.01); G06N 20/00 (2019.01); G16B 5/00 (2019.01); G16B 20/00 (2019.01); G16B 30/00 (2019.01); G16B 40/00 (2019.01); G16B 50/00 (2019.01); G16B 50/10 (2019.01); H04L 9/06 (2006.01); H04L 67/10 (2022.01); H04L 9/00 (2022.01)
CPC G16B 20/20 (2019.02) [G06F 18/2113 (2023.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01); G16B 5/00 (2019.02); G16B 20/00 (2019.02); G16B 30/00 (2019.02); G16B 40/00 (2019.02); G16B 50/00 (2019.02); G16B 50/10 (2019.02); H04L 9/0637 (2013.01); H04L 9/0643 (2013.01); H04L 67/10 (2013.01); H04L 9/50 (2022.05)] 19 Claims
OG exemplary drawing
 
1. A computer implemented method for predicting a phenotypic impact of a molecular variant of interest, the method comprising:
(a) recording an evidence model comprising evidence data, wherein the evidence data comprises objects, algorithms, and/or functions that yield predictions of phenotypic impacts of molecular variants for a target entity, and wherein the target entity comprises a functional element;
(b) evaluating validation performance data for the evidence model based on production data, wherein the production data represents a set of molecular variants with associated phenotypic impacts derived from clinical data and/or population data, and wherein the validation performance data corresponds to a uniform set of performance metrics computed using the production data and evaluating validation performance data gives an unbiased estimate of the predictive performance of the evidence model at a given time;
(c) generating a hash value of supporting data for the evidence model, wherein the supporting data comprises the evidence data, the validation performance data, and/or the production data;
(d) evaluating test performance data for the evidence model based on the evidence data and test data in response to receiving the test data for the evidence model, wherein the test data comprises a set of molecular variants with associated phenotypic impacts derived from clinical data and/or population data, wherein said set of molecular variants are disjoint from those in the production data and includes phenotypic impacts for molecular variants of unknown phenotypic impacts at the time of evidence model generation, or unavailable at the time of evidence model generation, and wherein the test performance data corresponds to the uniform set of performance metrics computed using the test data and evaluating the test performance data gives an unbiased estimate of the predictive performance of the evidence model at a later time;
(e) ranking the evidence model in a set of evidence models for the target entity based on the validation performance data and the test performance data; and
(f) providing the predicted-phenotypic impact using a best-performing evidence model for the target entity based on the ranking in response to a query for the predicted phenotypic impact of the molecular-variant of interest for the target entity from a variant interpretation terminal;
wherein,
the hash value of the supporting data for the evidence model is stored in a database, wherein the database associates the hash value with the supporting data.