FARM: Enhancing Molecular Representations with Functional Group Awareness

TL;DR

FARM introduces functional group-aware molecular representations that integrate chemical knowledge into SMILES and graph models, leading to improved performance in molecular property prediction tasks.

Contribution

The paper presents a novel foundation model that combines functional group annotations with SMILES and graph representations, enhancing molecular understanding for machine learning.

Findings

Achieved state-of-the-art results on 8 out of 13 MoleculeNet tasks.

Demonstrated strong generalization on a photostability dataset.

Improved transfer learning capabilities for drug discovery and materials science.

Abstract

We introduce Functional Group-Aware Representations for Small Molecules (FARM), a novel foundation model designed to bridge the gap between SMILES, natural language, and molecular graphs. The key idea behind FARM is the incorporation of functional group (FG) annotations at the atomic level, enabling both FG-enhanced SMILES and FG graphs. In this representation, SMILES strings are enriched with functional group information that identifies the group membership of each atom, while the FG graph captures molecular structure by representing how functional groups are connected. This tokenization injects chemical knowledge into SMILES and expands the effective molecular vocabulary, making the representation more suitable for Transformer-based models and more aligned with natural language structure. FARM learns molecular representations from two complementary perspectives to jointly encode functional and structural information. Masked language modeling on FG-enhanced SMILES captures atom-level features enriched with functional context, while graph neural networks model higher-level molecular topology through functional group connectivity. Contrastive learning is then used to align these two views into a unified embedding space, ensuring that both atom-level detail and functional group structure are jointly represented. We evaluate FARM on the MoleculeNet benchmark and achieve state-of-the-art performance on 8 out of 13 tasks. We further validate its generalization ability on a photostability dataset for quantum mechanical properties. These results demonstrate that FARM improves molecular representation learning, supports strong transfer learning across drug discovery and materials science, and enables broad applications in pharmaceutical research and functional material design.