Hybrid fragment-SMILES tokenization for ADMET prediction in drug discovery

Par Conseil national de recherches du Canada

Téléchargement	Voir la version finale : Hybrid fragment-SMILES tokenization for ADMET prediction in drug discovery (PDF, 4.1 Mio)
DOI	Trouver le DOI : https://doi.org/10.1186/s12859-024-05861-z
Auteur	Rechercher : Aksamit, Nicholas; Rechercher : Tchagang, Alain¹Identifiant ORCID : https://orcid.org/0000-0001-8619-9441; Rechercher : Li, Yifeng; Rechercher : Ombuki-Berman, Beatrice
Affiliation	Conseil national de recherches Canada. Technologies numériques
Format	Texte, Article
Sujet	ADMET prediction; transformer; fragments; SMILES; drug discovery
Résumé	Abstract Background: Drug discovery and development is the extremely costly and time-consuming process of identifying new molecules that can interact with a biomarker target to interrupt the disease pathway of interest. In addition to binding the target, a drug candidate needs to satisfy multiple properties affecting absorption, distribution, metabolism, excretion, and toxicity (ADMET). Artificial intelligence approaches provide an opportunity to improve each step of the drug discovery and development process, in which the first question faced by us is how a molecule can be informatively represented such that the in-silico solutions are optimized. Results: This study introduces a novel hybrid SMILES-fragment tokenization method, coupled with two pre-training strategies, utilizing a Transformer-based model. We investigate the efficacy of hybrid tokenization in improving the performance of ADMET prediction tasks. Our approach leverages MTL-BERT, an encoder-only Transformer model that achieves state-of-the-art ADMET predictions, and contrasts the standard SMILES tokenization with our hybrid method across a spectrum of fragment library cutoffs. Conclusion: The findings reveal that while an excess of fragments can impede performance, using hybrid tokenization with high frequency fragments enhances results beyond the base SMILES tokenization. This advancement underscores the potential of integrating fragment- and character-level molecular features within the training of Transformer models for ADMET property prediction.
Date de publication	2024-08-01
Maison d’édition	BMC Springer
Licence	Creative Commons Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/deed.fr Creative Commons Renonciation à la dédicace du domaine public (CC0 1.0 Universel) https://creativecommons.org/publicdomain/zero/1.0/deed.fr
Dans	BMC Bioinformatics 25, 255 (1 septembre 2024).
Langue	anglais
Publications évaluées par des pairs	Oui
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	446a8004-6e24-4d13-8b84-a45c05be5eeb
Enregistrement créé	2024-08-21
Enregistrement modifié	2024-08-22

Date de modification :: 2026-01-18