Transformer-Based Approach for Automated Functional Group Replacement in Chemical Compounds

TL;DR

This paper introduces a two-stage transformer model for precise functional group replacement in chemical compounds, improving diversity, validity, and structural control over traditional rule-based methods.

Contribution

The work presents a novel sequential transformer approach for functional group modification, ensuring structural similarity and expanding chemical space exploration.

Findings

Generates chemically valid transformations

Maintains structural similarity during modifications

Scales effectively across different search sizes

Abstract

Functional group replacement is a pivotal approach in cheminformatics to enable the design of novel chemical compounds with tailored properties. Traditional methods for functional group removal and replacement often rely on rule-based heuristics, which can be limited in their ability to generate diverse and novel chemical structures. Recently, transformer-based models have shown promise in improving the accuracy and efficiency of molecular transformations, but existing approaches typically focus on single-step modeling, lacking the guarantee of structural similarity. In this work, we seek to advance the state of the art by developing a novel two-stage transformer model for functional group removal and replacement. Unlike one-shot approaches that generate entire molecules in a single pass, our method generates the functional group to be removed and appended sequentially, ensuring strict substructure-level modifications. Using a matched molecular pairs (MMPs) dataset derived from ChEMBL, we trained an encoder-decoder transformer model with SMIRKS-based representations to capture transformation rules effectively. Extensive evaluations demonstrate our method's ability to generate chemically valid transformations, explore diverse chemical spaces, and maintain scalability across varying search sizes.