Method for detecting mutation, electronic equipment and computer storage medium

Abstract

The invention relates to a method for detecting mutation, electronic equipment and a computer storage medium. The method comprises the following steps: acquiring comparison result information about asequence of a to-be-detected sample and a reference genome sequence, wherein the to-be-detected sample comprises at least one of a to-be-detected blood sample and a to-be-detected tissue sample; basedon the comparison result information, generating mutation site base information, wherein the mutation site base information comprises at least one of base mass and comparison quality; extracting feature values of mutation site base information based on a prediction model, the prediction model being generated by machine learning of a plurality of training samples; and predicting mutation information based on the extracted feature value. According to the invention, the mutation detection efficiency and accuracy can be effectively improved.

Description

technical field [0001] The present disclosure relates generally to biological information detection processing, and in particular, to methods, electronic devices, and computer storage media for detecting mutations. Background technique [0002] Mutations are divided into somatic mutations and germline mutations. For example, somatic mutations are mutations that occur in normal body cells, such as in the skin or organs. Sporadic forms of malignancy can arise through somatic mutations. The traditional scheme for detecting body mutations, especially cell mutations, is, for example: importing BAM files and reading IGV images, and manually judging whether the mutation is true or false. [0003] In the above-mentioned traditional mutation detection scheme, it takes a certain amount of time to import the BAM file and read the IGV image. In addition, the efficiency of manually judging true and false mutations is relatively low, and errors in judging true and false mutations may o...

AI Technical Summary

Problems solved by technology

[0003] In the above-mentioned traditional mutation detection scheme, it takes a certain amount of time to import the BAM file and read the IGV image

In addition, the efficiency of manually judging true and false mutations is relatively low, and errors in judging true and false mutations may occur due to fatigue and experience limitations.

Images