CASTELO: clustered atom subtypes aided lead optimization—a combined machine learning and molecular modeling method

Background Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach t...

Full description

Saved in:
Bibliographic Details
Published in:BMC bioinformatics Vol. 22; no. 1; pp. 1 - 21
Main Authors: Zhang, Leili, Domeniconi, Giacomo, Yang, Chih-Chieh, Kang, Seung-gu, Zhou, Ruhong, Cong, Guojing
Format: Journal Article
Language:English
Published: London BioMed Central 22.06.2021
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Algorithms
Analysis
BASIC BIOLOGICAL SCIENCES
Bioinformatics
Biomedical and Life Sciences
Chemists
Clinical trials
Clustering
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Data collection
Drug discovery
Drugs
Feature extraction
Information management
Lead optimization
Learning algorithms
Life Sciences
Machine learning
Methods
Microarrays
Modelling
Molecular dynamics
Molecular dynamics simulation
Molecular modelling
Optimization
Pharmaceutical industry
Proteins
Simulation
Sucrose
Variational autoencoder
Workflow
United States
Lead optimization
Variational autoencoder
Drug discovery
Molecular dynamics simulation
Clustering
Machine learning
ISSN:1471-2105, 1471-2105
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach that partially automates lead optimization workflow in silico, providing suggestions for modification hot spots. Results The initial data collection is achieved with physics-based molecular dynamics simulation. Contact matrices are calculated as the preliminary features extracted from the simulations. To take advantage of the temporal information from the simulations, we enhanced contact matrices data with temporal dynamism representation, which are then modeled with unsupervised convolutional variational autoencoder (CVAE). Finally, conventional and CVAE-based clustering methods are compared with metrics to rank the submolecular structures and propose potential candidates for lead optimization. Conclusion With no need for extensive structure-activity data, our method provides new hints for drug modification hotspots which can be used to improve drug potency and reduce the lead optimization time. It can potentially become a valuable tool for medicinal chemists.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
USDOE
IBM
AC05-00OR22725
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-021-04214-4