T cell receptor sequence classification method based on semi-supervised learning framework

Abstract

The invention discloses a T cell receptor sequence classification method based on a semi-supervised learning framework, and the method comprises the steps: selecting a CDR3 beta region as input data,and carrying out the feature coding of T cell receptor data; according to the obtained data, selecting supervised learning algorithms of a support vector machine, a random forest and a decision tree to respectively construct initial classifiers C1, C2 and C3; training the initial classifiers C1, C2 and C3 to obtain expanded new training sets, repeatedly sampling the generated training sets to obtain three marked training sets, generating a classifier from each new training set, and iteratively updating the classifiers; and after the training is finished, using the three classifiers C1, C2 andC3 as a classifier integration through a voting mechanism. The method is suitable for the situation that T cell receptor sequence data is difficult to obtain, and the performance is remarkably superior to that of an existing method.

Description

Technical field [0001] The invention belongs to the field of data science technology, and specifically relates to a T cell receptor sequence classification method based on a semi-supervised learning framework. Background technique [0002] T cell receptor (English name: T cell receptor, English abbreviation: TCR) refers to a protein complex carried on the surface of T cells that can interact with the major histocompatibility complex on the host cell (English name: Majorhistocompatibility complex, English abbreviation: The antigenic epitope presented by MHC molecules—antigenic peptide-MHC molecular complex (English name: Peptide-MHC, English abbreviation: pMHC) combines to transmit the recognition signal on the surface of T cells to the nucleus of T cells, thereby activating T cell. In most cases, the affinity and binding specificity of T cell receptors for a given epitope can be determined using only the β chain. The main region where T cell receptors bind to the antigen peptid...

AI Technical Summary

Problems solved by technology

[0005] 1. Obtaining the epitope corresponding to the T cell receptor requires complex experiments;

Images