Genome instability evaluation method and system based on machine learning

• Main Authors: JI XUWO, LI ZHE, SUN TIANQI
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a genome instability assessment method and system based on machine learning, and the method comprises the steps: collecting and receiving a biological sample, and processing the biological sample to obtain a genome sample; dividing the genome samples into a training set and a verification set, and performing modeling based on the training set and the verification set to obtain a genome instability evaluation model; forming a modeling standard based on a gene set formed by a plurality of HRR genes, and training a genome instability evaluation model; and evaluating the genome instability based on a plurality of genome instability indexes. According to the invention, a more complex and accurate machine learning model algorithm is adopted to replace an original direct addition algorithm; the modeling standard comprises BRCA1/2 and other HRR genes which have good performance in the aspects of mutation rate, association with genome instability and association with drug efficacy so as to be i