Hybrid fragment-SMILES tokenization for ADMET prediction in drug discovery
Open Access
- 1 August 2024
- journal article
- research article
- Published by Springer Nature in BMC Bioinformatics
- Vol. 25 (1) , 1-25
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.Keywords
All Related Versions
Funding Information
- National Research Council Canada (AI4D-108, AI4D-108)
- Natural Sciences and Engineering Research Council of Canada (RGPIN-2021-03879, RGPIN-2022-05418)
- Canada Research Chair Program (2021-00214)
- Canada Foundation for Innovation (42115)
This publication has 56 references indexed in Scilit:
- Artificial Intelligence in Pharmaceutical SciencesEngineering, 2023
- MTGL-ADMET: A Novel Multi-task Graph Learning Framework for ADMET Prediction Enhanced by Status-Theory and Maximum Flow2023
- Few-shot learning with transformers via graph embeddings for molecular property predictionExpert Systems with Applications, 2023
- Opportunities and challenges in application of artificial intelligence in pharmacologyPharmacological Reports, 2023
- A survey of transformersAI Open, 2022
- A compact review of molecular property prediction with graph neural networksDrug Discovery Today: Technologies, 2020
- ADMET modeling approaches in drug discoveryDrug Discovery Today, 2019
- Molecular graph convolutions: moving beyond fingerprintsJournal of Computer-Aided Molecular Design, 2016
- On the Art of Compiling and Using 'Drug‐Like' Chemical Fragment SpacesChemMedChem, 2008
- PK/PD modelling and simulations: utility in drug developmentDrug Discovery Today, 2008