Antibacterial applications of fosinopril

By using machine learning models and molecular descriptor technology, the antibacterial activity of fosinopril was predicted and verified, solving the problem of discovering novel antibacterial compounds. Fosinopril with low toxicity and multiple inhibitory activities was discovered and can be used to prepare antibacterial drugs.

CN115376624BActive Publication Date: 2026-07-24KUNMING UNIV OF SCI & TECH
1 Cites 0 Cited by

Patent Information

Application Number
CN202111293485.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-03
Publication Date
2026-07-24
Estimated Expiration
2041-11-03

AI Technical Summary

Technical Problem

Existing technologies lack effective methods for discovering and validating novel antibacterial compounds, and there are no reports of antibacterial activity for fosinopril.

Method used

Machine learning methods were employed to construct support vector machines and random forest prediction models, combined with Pybel and PyDPI to generate molecular descriptors, predict the antibacterial activity of compounds, and use Pybel to calculate structural novelty, thereby screening out compounds with both antibacterial activity and novel structures.

Benefits of technology

It has enabled rapid screening of a library of hundreds of millions of compounds with an accuracy rate of over 91%, and discovered fosinopril, which has low toxicity and multiple antibacterial activities, providing a solution for novel antibacterial drugs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses antibacterial application of repaglinide, relates to the technical field of medicines, and comprises prediction of antibacterial activity of a compound and evaluation of structural novelty of the compound, and specifically comprises the following steps: step 1, collecting and collating high-throughput data of antibacterial activity to form antibacterial activity benchmark data; step 2, generating Daylight molecular fingerprint features of benchmark compounds by using Pybel and PyDPI and constructing an activity prediction model; step 3, predicting and evaluating antibacterial activity and structural novelty of a to-be-tested compound by using the model and fmcsR; and step 4, experimentally verifying repaglinide with high potential. The application can provide important ideas and guidance for research and development of novel antibacterial drugs, and more importantly, provides a novel antibacterial active compound repaglinide with low toxicity to cope with the increasingly serious crisis of bacterial drug resistance.
Need to check novelty before this filing date? Find Prior Art