Lead compound virtual screening method and device

Abstract

The invention discloses a lead compound virtual screening method and device. The method includes the steps of generation of molecular fingerprints of lead compounds on drug targets and bioactivity prediction of interaction between the lead compounds and the drug targets. The generation of the molecular fingerprints includes a molecular fingerprint part based on a module unit, a weighting molecularfingerprint part and a bioactivity part. During the bioactivity prediction, ligand molecular fingerprints and bioactivity values are utilized to serve as input of a random forest regression model, and a prediction model is constructed. Additionally, the device includes a universal tool for virtual screening on the basis of ligands, a prediction tool for the bioactivity generated when the lead compounds take effects on the drug targets, and a generation tool of the molecular fingerprints of the lead compounds on the drug targets. At present, molecular fingerprints which are excellent in performance and are used for the bioactivity prediction are often greater in length, and however, by adopting a designed deep learning algorithm, molecular fingerprints which are excellent in performance and smaller in length can be generated so that the best bioactivity prediction model of drug target ligands can be obtained.

Description

technical field [0001] The application relates to a method and device for virtual screening of lead compounds, belonging to the field of computer technology. Background technique [0002] With the rapid development of life sciences at the end of the last century, the completion of the Human Genome Project (HGP) and the implementation of the subsequent functional genome project, drug research and medical drug industry have entered a new historical period. [0003] As we all know, the research and development of new drugs is a high-input and low-efficiency work, including five steps: target identification and verification, biological detection, discovery and optimization of lead compounds, clinical verification, and marketing. Among them, the lead compound is a compound with certain biological activity and chemical structure obtained through various ways and means, which has pharmacological or biological activity, and can be used to develop new drugs to improve drug potency, s...

AI Technical Summary

Problems solved by technology

Moreover, since the number of compounds is often very large, it will be very time-consuming to construct a good machine learning-based ligand activity virtual screening model, and it is usually difficult to construct such a large virtual screening model in practical applications

Images