A Deep Generative Model for Fragment-Based Molecule Generation

TL;DR

This paper introduces a fragment-based deep generative model for molecule creation that improves validity and diversity over traditional string-based models, achieving state-of-the-art results in molecule generation.

Contribution

The work proposes a novel fragment-based language model that enhances validity and diversity in molecule generation, outperforming existing string-based approaches.

Findings

Outperforms other language model-based methods in validity and uniqueness.

Achieves state-of-the-art performance comparable to graph-based models.

Generated molecules maintain properties similar to training data without explicit supervision.

Abstract

Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative approaches addressing the challenge belong to two broad categories, differing in how molecules are represented. One approach encodes molecular graphs as strings of text, and learns their corresponding character-based language model. Another, more expressive, approach operates directly on the molecular graph. In this work, we address two limitations of the former: generation of invalid and duplicate molecules. To improve validity rates, we develop a language model for small molecular substructures called fragments, loosely inspired by the well-known paradigm of Fragment-Based Drug Design. In other words, we generate molecules fragment by fragment, instead of atom by atom. To improve uniqueness rates, we present a frequency-based masking strategy that helps generate molecules with infrequent fragments. We show experimentally that our model largely outperforms other language model-based competitors, reaching state-of-the-art performances typical of graph-based approaches. Moreover, generated molecules display molecular properties similar to those in the training sample, even in absence of explicit task-specific supervision.