Predicting Potent Compounds Using a Conditional Variational Autoencoder Based upon a New Structure–Potency Fingerprint

Prediction of the potency of bioactive compounds generally relies on linear or nonlinear quantitative structure–activity relationship (QSAR) models. Nonlinear models are generated using machine learning methods. We introduce a novel approach for potency prediction that depends on a newly designed mo...

Full description

Saved in:
Bibliographic Details
Published in:Biomolecules (Basel, Switzerland) Vol. 13; no. 2; p. 393
Main Authors: Janela, Tiago, Takeuchi, Kosuke, Bajorath, Jürgen
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 18.02.2023
MDPI
Subjects:
Algorithms
Bioactive compounds
Chemical properties
Chemistry
conditional variational autoencoder
Decision trees
Deep learning
Drugs
fingerprints
Health aspects
Ligands
Machine Learning
Neural networks
Neural Networks, Computer
Optimization
Organic compounds
Pharmaceutical research
Pharmaceutical sciences
potency prediction
Quantitative Structure-Activity Relationship
Structure
Structure-activity relationship (Pharmacology)
Structure-activity relationships
Germany
conditional variational autoencoder
bioactive compounds
potency prediction
machine learning
fingerprints
ISSN:2218-273X, 2218-273X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Prediction of the potency of bioactive compounds generally relies on linear or nonlinear quantitative structure–activity relationship (QSAR) models. Nonlinear models are generated using machine learning methods. We introduce a novel approach for potency prediction that depends on a newly designed molecular fingerprint (FP) representation. This structure–potency fingerprint (SPFP) combines different modules accounting for the structural features of active compounds and their potency values in a single bit string, hence unifying structure and potency representation. This encoding enables the derivation of a conditional variational autoencoder (CVAE) using SPFPs of training compounds and apply the model to predict the SPFP potency module of test compounds using only their structure module as input. The SPFP–CVAE approach correctly predicts the potency values of compounds belonging to different activity classes with an accuracy comparable to support vector regression (SVR), representing the state-of-the-art in the field. In addition, highly potent compounds are predicted with very similar accuracy as SVR and deep neural networks.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2218-273X
2218-273X
DOI:10.3390/biom13020393