The Year in AI Papers
The year/Independent research

Paper 2511.08217

MADD: Multi-Agent Drug Discovery Orchestra

Gleb V. Solovev, Alina B. Zhidkovskaya, Anastasia Orlova, Nina Gubina, Anastasia Vepreva, Rodion Golovinskii, Ilya Tonkii, Ivan Dubrovsky, Ivan Gurev, Dmitry Gilemkhanov, Denis Chistiakov, Timur A. Aliev, et al.

Published
Nov 2025
Research lab
Independent
Citations
4
GitHub
Not linked

01 In brief

Summary

The paper introduces MADD, a multi-agent system for automated hit identification in early drug discovery.

MADD uses four specialized agents (Decomposer, Orchestrator, Summarizer, Chat Agent) to process natural language queries, decompose them into subtasks, generate molecules using GAN and transformer-based CVAE models, and predict properties like IC50 and docking scores.

The system integrates tools such as AutoML (FEDOT), RDKit filters, and databases like ChEMBL and BindingDB.

Evaluated on seven drug discovery cases, MADD achieved 79.8% final accuracy on complex queries, outperforming existing LLM-based solutions like ChemAgent, LlasMol, X-LoRA-Gemma, and ChemDFM.

The authors also created a benchmark with over 3 million molecules and 300+ queries, and applied MADD to five novel biological targets (STAT3, ABL, COMT, ACL, PCSK9), releasing identified hit molecules.

A case study on thrombocytopenia demonstrated MADD's ability to generalize to unseen targets, generating 132 hit molecules from 10k candidates, outperforming the SYK-FBRL approach in efficiency.

Limitations include dependence on user-provided datasets and the need for experimental validation.

02 From the paper

Abstract

Hit identification is a central challenge in early drug discovery, traditionally requiring substantial experimental resources. Recent advances in artificial intelligence, particularly large language models (LLMs), have enabled virtual screening methods that reduce costs and improve efficiency. However, the growing complexity of these tools has limited their accessibility to wet-lab researchers. Multi-agent systems offer a promising solution by combining the interpretability of LLMs with the precision of specialized models and tools. In this work, we present MADD, a multi-agent system that builds and executes customized hit identification pipelines from natural language queries. MADD employs four coordinated agents to handle key subtasks in de novo compound generation and screening. We evaluate MADD across seven drug discovery cases and demonstrate its superior performance compared to existing LLM-based solutions. Using MADD, we pioneer the application of AI-first drug design to five biological targets and release the identified hit molecules. Finally, we introduce a new benchmark of query-molecule pairs and docking scores for over three million compounds to contribute to the agentic future of drug design.