DGMM: A Deep Learning-Genetic Algorithm Framework for Efficient Lead Optimization in Drug Discovery
Saved in:
| Title: | DGMM: A Deep Learning-Genetic Algorithm Framework for Efficient Lead Optimization in Drug Discovery |
|---|---|
| Authors: | Jiebin Fang, Churu Mao, Yuchen Zhu, Xiaoming Chen, Yun Huang, Wanjing Ding, Chang-Yu Hsieh, Zhongjun Ma |
| Publication Year: | 2025 |
| Collection: | Bath Spa University: Figshare |
| Subject Terms: | Biophysics, Medicine, Pharmacology, Biotechnology, Computational Biology, Space Science, Biological Sciences not elsewhere classified, Chemical Sciences not elsewhere classified, Information Systems not elsewhere classified, three diverse targets, novel rock2 inhibitors, novel computational framework, latent space organization, hdac8 ), reproducing, generating structurally diverse, extensive retrospective validation, evaluation results indicate, enables systematic exploration, multiobjective optimization strategy, maintaining structural diversity, known optimization pathways, efficient molecular optimization, efficient lead optimization, incorporates scaffold constraints, success establishes dgmm, dgmm achieves state, balance structural variation, genetic algorithm framework, drug discovery faces |
| Description: | Lead optimization in drug discovery faces the dual challenge of maintaining structural diversity while preserving core molecular features and optimizing the balance between biological activity and drug-like properties. To address these challenges, we introduce the Deep Genetic Molecule Modification (DGMM) algorithm, a novel computational framework that synergistically integrates deep learning architectures with genetic algorithms for efficient molecular optimization. DGMM leverages a variational autoencoder (VAE) with an enhanced representation learning strategy that incorporates scaffold constraints during training, significantly improving the latent space organization to balance structural variation with scaffold retention. A multiobjective optimization strategy, combining Monte Carlo search and Markov processes, enables systematic exploration of the trade-offs between drug likeness and target activity. Evaluation results indicate that DGMM achieves state-of-the-art performance in activity optimization, generating structurally diverse, yet pharmacologically relevant compounds. To rigorously establish its utility, we first demonstrated its generalizability through extensive retrospective validation on three diverse targets (CHK1, CDK2, and HDAC8), reproducing their known optimization pathways. Building on this validated generalizability, we deployed DGMM in a prospective campaign, which culminated in the wet-lab discovery of novel ROCK2 inhibitors with a notable 100-fold increase in biological activity. This success establishes DGMM as an effective tool for structural optimization of drug molecules. |
| Document Type: | article in journal/newspaper |
| Language: | unknown |
| DOI: | 10.1021/acs.jcim.5c01017.s001 |
| Availability: | https://doi.org/10.1021/acs.jcim.5c01017.s001 https://figshare.com/articles/journal_contribution/DGMM_A_Deep_Learning-Genetic_Algorithm_Framework_for_Efficient_Lead_Optimization_in_Drug_Discovery/29680327 |
| Rights: | CC BY-NC 4.0 |
| Accession Number: | edsbas.B65F0A3B |
| Database: | BASE |
Nájsť tento článok vo Web of Science | Abstract: | Lead optimization in drug discovery faces the dual challenge of maintaining structural diversity while preserving core molecular features and optimizing the balance between biological activity and drug-like properties. To address these challenges, we introduce the Deep Genetic Molecule Modification (DGMM) algorithm, a novel computational framework that synergistically integrates deep learning architectures with genetic algorithms for efficient molecular optimization. DGMM leverages a variational autoencoder (VAE) with an enhanced representation learning strategy that incorporates scaffold constraints during training, significantly improving the latent space organization to balance structural variation with scaffold retention. A multiobjective optimization strategy, combining Monte Carlo search and Markov processes, enables systematic exploration of the trade-offs between drug likeness and target activity. Evaluation results indicate that DGMM achieves state-of-the-art performance in activity optimization, generating structurally diverse, yet pharmacologically relevant compounds. To rigorously establish its utility, we first demonstrated its generalizability through extensive retrospective validation on three diverse targets (CHK1, CDK2, and HDAC8), reproducing their known optimization pathways. Building on this validated generalizability, we deployed DGMM in a prospective campaign, which culminated in the wet-lab discovery of novel ROCK2 inhibitors with a notable 100-fold increase in biological activity. This success establishes DGMM as an effective tool for structural optimization of drug molecules. |
|---|---|
| DOI: | 10.1021/acs.jcim.5c01017.s001 |