MoDeMol: A Decomposition-Based Evolutionary Framework for Multi-Objective Molecular Optimization
- 1School of Artificial Intelligence and Computer Science, Shaanxi Normal University, Xi’an 710119, China
Abstract
Lead compound multi-objective optimization requires balancing mutually restrictive drug-like properties, yet conventional latent generative and evolutionary optimization methods suffer from structural-function misalignment, population structural redundancy and low search efficiency under limited evaluation budgets. This work proposes a decomposition-based evolutionary framework built on a score-informed latent space (MoDeMol), with four core innovations: (1) Contrastive fine-tuned Transformer-VAE latent space supervised by predicted dual-target activity scores to improve the alignment between latent spatial proximity and predicted target-activity profiles. (2) Hybrid population initialization combining lead latent perturbation and high-quality molecular bank screening to balance local scaffold retention and global high predicted-activity region exploration. (3) Adaptive resource allocation mechanism for dynamic subproblem computation scheduling to boost optimization efficiency when the property evaluation budget is limited. (4) Dynamic Morgan fingerprint similarity penalization to suppress structural redundancy and maintain diverse molecular scaffolds in the population. Extensive benchmarks on single-target GSK3β and dual-target GSK3β/JNK3 kinase optimization tasks demonstrate that MoDeMol outperforms MolFinder, JANUS and MOMO in success rate, Pareto hypervolume and qualified molecular yield. Quantitative latent-space analyses, qualitative visualization, scaffold tracking, and ablation experiments provide complementary evidence for the contributions of the proposed components. The proposed framework addresses representation alignment, structural redundancy, and search-resource allocation within a computational multi-target lead-optimization workflow under limited evaluation budgets.
Related
- Toward objective brain monitoring of cancer-related cognitive impairment: an extracellular vesicle–based conceptual framework
- Actuator Transcription Factors Resolve Combinatorial Binding Into Productive Gene Expression : An Evolutionary and Functional Framework for Gene Activation by Combinatorial TF Assemblies
- A multi-objective sequence engineering framework for rational genetic vaccine design.
- Molecular Decomposition of the Area Compressibility Modulus of Lipid Membranes
- Stochastic Biophysics of Cellular Radiosensitivity: From Molecular Noise and Repair Kinetics to Evolutionary Demographics
BibTeX
@article{guo2026modemol,
title = {{MoDeMol: A Decomposition-Based Evolutionary Framework for Multi-Objective Molecular Optimization}},
author = {Chenbin Guo and Cai Dai},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = oct,
doi = {10.3390/ijms27198818},
url = {https://www.mdpi.com/1422-0067/27/19/8818},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - MoDeMol: A Decomposition-Based Evolutionary Framework for Multi-Objective Molecular Optimization
AU - Chenbin Guo
AU - Cai Dai
PY - 2026
DA - 2026/10/02
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms27198818
UR - https://www.mdpi.com/1422-0067/27/19/8818
AB - Lead compound multi-objective optimization requires balancing mutually restrictive drug-like properties, yet conventional latent generative and evolutionary optimization methods suffer from structural-function misalignment, population structural redundancy and low search efficiency under limited evaluation budgets. This work proposes a decomposition-based evolutionary framework built on a score-informed latent space (MoDeMol), with four core innovations: (1) Contrastive fine-tuned Transformer-VAE latent space supervised by predicted dual-target activity scores to improve the alignment between latent spatial proximity and predicted target-activity profiles. (2) Hybrid population initialization combining lead latent perturbation and high-quality molecular bank screening to balance local scaffold retention and global high predicted-activity region exploration. (3) Adaptive resource allocation mechanism for dynamic subproblem computation scheduling to boost optimization efficiency when the property evaluation budget is limited. (4) Dynamic Morgan fingerprint similarity penalization to suppress structural redundancy and maintain diverse molecular scaffolds in the population. Extensive benchmarks on single-target GSK3β and dual-target GSK3β/JNK3 kinase optimization tasks demonstrate that MoDeMol outperforms MolFinder, JANUS and MOMO in success rate, Pareto hypervolume and qualified molecular yield. Quantitative latent-space analyses, qualitative visualization, scaffold tracking, and ablation experiments provide complementary evidence for the contributions of the proposed components. The proposed framework addresses representation alignment, structural redundancy, and search-resource allocation within a computational multi-target lead-optimization workflow under limited evaluation budgets.
SN - 1422-0067
ER -