False positive gene mutation filtering method for targeted capture of gene sequencing data

Abstract

The invention discloses a false positive gene mutation filtering method for targeted capture of gene sequencing data. The false positive gene mutation filtering method comprises the following steps: preprocessing gene mutation detection data; selecting three different supervised learning algorithms based on a triple training method to construct three different initial classifiers H1, H2 and H3, namely selecting three different supervised learning automatons and a learner generated based on an initial training set; training the H1, H2 and H3 to obtain an extended training set, and updating themodel; and marking the unmarked sample set U by using the trained model, and filtering according to a marking result. The method solves the problem that the traditional method cannot effectively copewith the batch difference.

Description

technical field [0001] The invention belongs to the technical field of data science with the application background of precision medicine, and specifically relates to a method for filtering false positive gene mutations for targeted capture of gene sequencing data. Background technique [0002] Since the completion of the draft of the human genome, in the past two decades, gene sequencing technology has made many milestone breakthroughs and has quickly entered the market. Among them, the second generation sequencing technology (English name: Next Generation Sequencing, English abbreviation: NGS) is the most Mature. Targeted capture gene sequencing is a clinical application of NGS. Because of its high cost performance and strong scalability, it is currently one of the most widely used technologies in precise tumor diagnosis and treatment. In recent years, targeted capture gene sequencing has been gradually popularized in the routine diagnosis and treatment of tumors, and a l...

AI Technical Summary

Problems solved by technology

The disadvantage of the MF strategy is that the required large-scale training data is often difficult to obtain due to cost reasons, and the model is only suitable for situations where the data characteristics are similar to the data characteristic model of the training data, that is, it cannot cope with batch differences

In addition, because the target capture gene sequencing technology only sequences the target capture region, the target region is small (small sample set), and the number of potential gene mutations is 2-3 orders of magnitude less than that of whole genome sequencing, even It is difficult to provide training data that meets the requirements of the MF model regardless of cost

Images