Large Language Model Agent for Modular Task Execution in Drug Discovery

TL;DR

This paper introduces a modular LLM-based framework that automates key tasks in early drug discovery, including data retrieval, molecular generation, property prediction, and structure modeling, improving efficiency and accuracy.

Contribution

It presents a novel modular framework combining LLM reasoning with domain tools for comprehensive drug discovery tasks, enabling flexible integration and iterative molecular refinement.

Findings

Increased molecules with QED > 0.6 from 34 to 55 after refinement rounds.

Improved compliance with drug-likeness filters, e.g., Ghose filter from 32 to 55.

Generated 3D protein-ligand complexes with rapid binding affinity estimates.

Abstract

We present a modular framework powered by large language models (LLMs) that automates and streamlines key tasks across the early-stage computational drug discovery pipeline. By combining LLM reasoning with domain-specific tools, the framework performs biomedical data retrieval, literature-grounded question answering via retrieval-augmented generation, molecular generation, multi-property prediction, property-aware molecular refinement, and 3D protein-ligand structure generation. The agent autonomously retrieved relevant biomolecular information, including FASTA sequences, SMILES representations, and literature, and answered mechanistic questions with improved contextual accuracy compared to standard LLMs. It then generated chemically diverse seed molecules and predicted 75 properties, including ADMET-related and general physicochemical descriptors, which guided iterative molecular refinement. Across two refinement rounds, the number of molecules with QED > 0.6 increased from 34 to 55. The number of molecules satisfying empirical drug-likeness filters also rose; for example, compliance with the Ghose filter increased from 32 to 55 within a pool of 100 molecules. The framework also employed Boltz-2 to generate 3D protein-ligand complexes and provide rapid binding affinity estimates for candidate compounds. These results demonstrate that the approach effectively supports molecular screening, prioritization, and structure evaluation. Its modular design enables flexible integration of evolving tools and models, providing a scalable foundation for AI-assisted therapeutic discovery.