Text-Guided Molecule Generation with Diffusion Language Model
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (1) , 109-117
Abstract
Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods. TGM-DLM updates token embeddings within the SMILES string collectively and iteratively, using a two-phase diffusion generation process. The first phase optimizes embeddings from random noise, guided by the text description, while the second phase corrects invalid SMILES strings to form valid molecular representations. We demonstrate that TGM-DLM outperforms MolT5-Base, an autoregressive model, without the need for additional data resources. Our findings underscore the remarkable effectiveness of TGM-DLM in generating coherent and precise molecules with specific properties, opening new avenues in drug discovery and related scientific domains. Code will be released at: https://github.com/Deno-V/tgm-dlm.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionalsNature Communications, 2022
- MolGPT: Molecular Generation Using a Transformer-Decoder ModelJournal of Chemical Information and Modeling, 2021
- Artificial intelligence in drug discovery and developmentDrug Discovery Today, 2021
- Bidirectional Molecule Generation with Recurrent Neural NetworksJournal of Chemical Information and Modeling, 2020
- Automatic Chemical Design Using a Data-Driven Continuous Representation of MoleculesACS Central Science, 2018
- Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural NetworksACS Central Science, 2017
- Molecular Design of Benzodithiophene-Based Organic Photovoltaic MaterialsChemical Reviews, 2016
- ZINC 15 – Ligand Discovery for EveryoneJournal of Chemical Information and Modeling, 2015
- SMILES. 2. Algorithm for generation of unique SMILES notationJournal of Chemical Information and Computer Sciences, 1989
- SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rulesJournal of Chemical Information and Computer Sciences, 1988