EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL

Pablo Varas Pardo iD, Guillermo Marcos-Ayuso iD, Eugenia Ulzurrun, David Ríos Insua, Nuria E Campillo iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Drug DesignProteinsLigandsReinforcement Machine LearningLarge Language ModelsBinding SitesMolecular Docking SimulationGenerative Artificial Intelligence

Substanzen

LigandsProteins

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}
}
Kostenlos starten →