Incremental width and deep learning drug response prediction method, medium and equipment

Abstract

The invention provides a drug response prediction method based on incremental width and deep learning, a medium and equipment. The method comprises the following steps: performing text coding and position coding on a drug sequence to construct a drug information code; inputting the drug information code into a Transform encoder to excavate the structural features of the drug, inputting gene expression data into the feature representation of a multilayer perceptron learning gene, and splicing the drug features and the gene features together to form a drug-gene feature pair; and inputting the feature pair into a width learning system to obtain a predicted drug sensitivity regression value. The method can solve the problem of poor drug expression; drug expression and gene expression characteristics are fused by adopting a width learning system, so that the accuracy of a drug sensitivity prediction result is improved; the network weight is updated through an incremental learning algorithm, the model performance is improved, and the whole model does not need to be retrained.

Description

technical field [0001] The present invention relates to the technical field of drug response prediction, and more particularly, to a drug response prediction method, medium and device based on incremental width and deep learning. Background technique [0002] Cancer is an important disease that threatens human health and causes death. Personalized treatment of cancer patients is one of the most prominent research areas of precision medicine. In recent years, with the rapid development of pharmacogenomics and computational models, drug response prediction technology has gradually brought more convenience to personalized treatment research. Drug response prediction aims to extract and integrate gene expression information of drugs and cell lines to predict the sensitivity of cell lines to drugs. half-maximal inhibitory concentration (IC 50 ) can be used to reflect the drug response sensitivity of cell lines and is a commonly used predictor of drug response. Most of the trad...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings and deficiencies in the prior art, the object of the present invention is to provide a drug response prediction method, medium and equipment of incremental width and deep learning; the method learns the structural features of the drug SMILES sequence through a Transformer encoder, Solve the problem that different interaction information between different atoms and their associated chemical bonds in drug molecules cannot be distinguished; use a wide learning system to fuse drug representation and gene expression features to improve the accuracy of drug sensitivity prediction results; use incremental learning algorithms Update network weights to improve model performance without retraining the entire model

Images