METHOD FOR ESTABLISHING GENOMIC SCAR MODEL

A method for establishing a genomic scar model and the use thereof, the method comprising: (1) collecting known positive samples and negative samples to form a training set; (2) analyzing the condition of CNVs in the training set and determining the types and the corresponding number of CNVs; (3) determining BRCAness positive events and BRCAness negative events; and (4) performing training according to the BRCAness positive events and BRCAness negative events in the training set by means of a machine learning method to obtain the weights of CNVs of different types determined in step (2), and then accumulating the weights of CNVs of different types to obtain a genomic scar model for calculating a GSS. By means of the method, the BRCAness status of samples under test can be accurately predicted and an interpretation result can be directly provided according to a genomic scar score.