ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery

TL;DR

ToolMol is an evolutionary framework combining genetic algorithms and LLMs for multi-objective drug discovery, achieving state-of-the-art results in ligand quality and binding affinity.

Contribution

It introduces a novel agentic framework that integrates LLMs with genetic algorithms for improved de novo drug design.

Findings

Achieves >10% stronger predicted binding affinity than existing methods.

Gains over 35% in absolute binding free energy scores.

State-of-the-art performance on multi-objective property optimization.

Abstract

Advances in large language models (LLMs) have recently opened new and promising avenues for small-molecule drug discovery. Yet existing LLM-based approaches for molecular generation often suffer from high rates of invalid and low-quality ligand candidates, a result of the syntactic limitations of current models with regard to molecular strings. In this paper, we introduce $\texttt{ToolMol}$, an evolutionary agentic framework for de novo drug design. $\texttt{ToolMol}$ combines a multi-objective genetic algorithm with an agentic LLM operator that iteratively updates the ligand population. We build a comprehensive toolbox of RDKit-backed functions that allows our agentic operator to consisently make precise ligand modifications. $\texttt{ToolMol}$ achieves state-of-the-art performance on multi-objective property optimization tasks, discovering drug-like and synthesizable ligands that have $>10\%$ stronger predicted binding affinity compared to existing methods, evaluated on three protein targets. $\texttt{ToolMol}$ ligands additionally achieve state-of-the-art results in gold-standard Absolute Binding Free Energy scores, gaining over existing methods by over $35\%$. By studying chain-of-thought reasoning traces, we observe that tool-calling enables the model to more faithfully execute its planned modifications, efficiently exploiting the strong chemical prior knowledge in LLMs.