US 12,406,748 B2
Methods for context based compression of genomic data for immuno-oncology biomarkers
Fiona Hyland, San Mateo, CA (US); Asha Kamat, Reading, MA (US); and Timothy Looney, Austin, TX (US)
Assigned to Life Technologies Corporation, Carlsbad, CA (US)
Filed by Life Technologies Corporation, Carlsbad, CA (US)
Filed on Jun. 20, 2024, as Appl. No. 18/748,533.
Application 18/748,533 is a continuation of application No. 18/170,797, filed on Feb. 17, 2023, granted, now 12,040,048.
Application 18/170,797 is a continuation of application No. 16/851,472, filed on Apr. 17, 2020, granted, now 11,610,648, issued on Mar. 21, 2023.
Claims priority of provisional application 62/835,586, filed on Apr. 18, 2019.
Prior Publication US 2024/0428885 A1, Dec. 26, 2024
Int. Cl. G16B 20/20 (2019.01); G06F 16/2457 (2019.01); G06F 16/248 (2019.01); G06N 3/126 (2023.01)
CPC G16B 20/20 (2019.02) [G06F 16/24575 (2019.01); G06F 16/248 (2019.01); G06N 3/126 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a machine-readable memory; and
a processor in communication with the memory, wherein the processor is configured to execute machine-readable instructions, which, when executed by the processor, cause the system to perform a method, comprising:
receiving, at the processor, a plurality of numbers of reads for a plurality of targeted genes of a gene expression assay performed on a test sample, wherein the plurality of targeted genes are organized into a plurality of categories, wherein Nk targeted genes in a kth category are associated with a functional context;
for each kth category in the plurality of categories,
determining a number of reads for each targeted gene of the Nk targeted genes in the kth category to produce Nk numbers of reads corresponding to the Nk targeted genes;
compressing the Nk numbers of reads in the kth category to form a compressed value for the kth category, wherein the compressed value comprises a median value of the Nk numbers of reads for the kth category;
assigning a score to the kth category to form a kth score, wherein the kth score depends on the compressed value for the kth category to form a plurality of scores for the plurality of categories;
assigning the kth score to a biomarker;
determining a status of the biomarker based on the kth score; and
determining a predicted score corresponding to the biomarker based on the status of the biomarker.