MolGPT: Molecular Generation Using a Transformer-Decoder Model

By Viraj Bagal, Rishal Aggarwal, P. K. Vinod, U. Priyakumar. Journal of Chemical Information and Modeling, 2021

527 citations recorded by the source corpus.

Application of deep learning techniques for de novo generation of molecules, termed as inverse molecular design, has been gaining enormous traction in drug design. The representation of molecules in SMILES notation as a string of characters enables the usage of state of the art models in natural language processing, such as Transformers, for molecular design in general. Inspired by generative pre-training (GPT) models that have been shown to be successful in generating meaningful text, we train a transformer-decoder on the next token prediction task using masked self-attention for the generation of druglike molecules in this study. We show that our model, MolGPT, performs on par with other previously proposed modern machine learning frameworks for molecular generation in terms of generating valid, unique, and novel molecules. Furthermore, we demonstrate that the model can be trained conditionally to control multiple properties of the generated molecules. We also show that the model can be used to generate molecules with desired scaffolds as well as desired molecular properties by conditioning the generation on scaffold SMILES strings of desired scaffolds and property values. Using saliency maps, we highlight the interpretability of the generative process of the model.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/77805d75199e7b9e580b4827f56a069ba0ddd13f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Translation between Molecules and Natural Language (2022, background): “It is a homodetic cyclic peptide, a member of 1,3-oxazoles, a member of 1,3-thiazoles and a macrocycle. properties such as logP (the octanol-water partition coefﬁcient) (Bagal et al., 2021).”
Large Language Models on Graphs: A Comprehensive Survey (2023, methodology): “MolGPT [177] and MolXPT [169] are GPT-style models used for molecule classification and generation.”