PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL
Journal of Chemical Information and Modeling · 2026
DOI: 10.1021/acs.jcim.6c01980 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Pablo Varas Pardo und 4 weiteren Autor:innen. Beteiligte Einrichtung: AItenea Biotech S.L. , Madrid28014, Spain. Hauptthemen laut MEDLINE: Drug Design, Proteins. Die Arbeit nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Comunidad de Madrid, European Commission, European Regional Development Fund.
Abstract (Originalsprache)
De novo drug design aims to generate molecules targeting specific protein pockets while retaining chemical plausibility and drug-like properties. Recent 3D structure-based generative methods explicitly model pocket-ligand geometry, but this does not always translate into chemically realistic or practically usable candidate molecules. Molecular language models provide a complementary sequence-based alternative. However, it remains unclear whether sequence-based pocket information can effectively guide ligand generation, whether multistage training improves pocket-specific generation, and whether docking-guided reinforcement learning can be integrated into a practical generation pipeline. We introduce PockLigGPT, a GPT-based framework for pocket-sequence-conditioned molecular generation. Rather than producing fixed 3D coordinates, PockLigGPT formulates ligand design as a sequence-generation problem conditioned on the amino acid composition of the protein pocket. The model is trained in four stages: large-scale chemical pretraining based on ZINC20; bioactivity-oriented adaptation based on ChEMBL; pocket-sequence-conditioned fine-tuning using binding-pocket amino acid sequences paired with ligands; and, finally, pocket-specific docking-guided reinforcement learning using AutoDock Vina-based rewards. PockLigGPT achieves competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility, favorable physicochemical profiles, and Lipinski-based drug-likeness. Docking studies on Alzheimer’s disease-associated targets and token-level analyses further support the utility of PockLigGPT for de novo drug design.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- AItenea Biotech S.L. , Madrid28014, Spain.
- Instituto de Ciencias Matemáticas (ICMAT-CSIC) , Madrid28049, Spain.
- Universidad Autónoma de Madrid, Escuela de Doctorado, Madrid28049, Spain.
- Centro de Investigaciones Biológicas Margarita Salas (CIB Margarita Salas-CSIC), Madrid28040, Spain.
ORCID-Profile: Pablo Varas Pardo, Guillermo Marcos-Ayuso, Nuria E Campillo
Förderung
- Comunidad de Madrid
- European Commission
- European Regional Development Fund
- Agencia Estatal de Investigaci?n
Zitieren
APA
Varas Pardo, P., Marcos-Ayuso, G., Ulzurrun, E., Ríos Insua, D., & Campillo, N. E. (2026). PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c01980
Vancouver
Varas Pardo P, Marcos-Ayuso G, Ulzurrun E, Ríos Insua D, Campillo NE. PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c01980
BibTeX
@article{VarasPardo2026,
author = {Varas Pardo, Pablo and Marcos-Ayuso, Guillermo and Ulzurrun, Eugenia and Ríos Insua, David and Campillo, Nuria E},
title = {PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.6c01980}
}
EUVIMED