An LLM-based Multi-Agent Workflow for Cancer Drug Discovery

Author(s): Rahul V. Veettil, PhD

Originally published on Towards AI.

From Target Hypothesis to Hit Proposal: A Minimal Drug Discovery Demo

Triple-negative breast cancer (TNBC) is among the most aggressive forms of breast cancer. What sets TNBC apart and makes it particularly difficult to treat is its lack of expression of estrogen receptor (ER), progesterone receptor (PR), and HER2. As a result, many of the targeted therapies effective in other breast cancer subtypes are not viable options for TNBC.

This article discusses a workflow using large language model-powered agents in drug discovery, specifically focusing on immune escape mechanisms in triple-negative breast cancer (TNBC). The author elaborates on the process from target hypothesis to drug proposal, highlighting the contributions of different agents to summarizing literature, identifying gene targets, and proposing drug-like candidates. It addresses the challenges in TNBC treatment and emphasizes innovative strategies involving immune checkpoint inhibitors and comprehensive approaches to enhance therapeutic efficacy.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI