Gotta be SAFE: A New Framework for Molecular Design

Emmanuel Noutahi, Cristian Gabellini, Michael Craig, Jonathan Siu Chi Lim, Prudencio Tossou

Keywords: SMILES strings, scaffold decoration, linker design, generative model, GPT, drug design

TL;DR: SAFE is a new way to represent molecules using interconnected fragment blocks, simplifying molecule design. It's proposed with SAFE-GPT, a powerful large generative model that excels on fragment-constrained design tasks.

Abstract: Traditional molecular string representations, such as SMILES, often pose challenges for AI-driven molecular design due to their non-sequential depiction of molecular substructures. To address this issue, we introduce Sequential Attachment-based Fragment Embedding (SAFE), a novel line notation for chemical structures. SAFE reimagines SMILES strings as an unordered sequence of interconnected fragment blocks while maintaining full compatibility with existing SMILES parsers. It streamlines complex generative tasks, including scaffold decoration, fragment linking, polymer generation, and scaffold hopping, while facilitating autoregressive generation for fragment-constrained design, thereby eliminating the need for intricate decoding or graph-based models. We demonstrate the effectiveness of SAFE by training an 87-million-parameter GPT2-like model on a dataset containing 1.1 billion SAFE representations. Through extensive experimentation, we show that our SAFE-GPT model exhibits versatile and robust optimization performance. SAFE opens up new avenues for the rapid exploration of chemical space under various constraints, promising breakthroughs in AI-driven molecular design.

Submission Number: 20