TSAssistant: A Human-in-the-Loop Agentic Framework for Automated Target Safety Assessment

TL;DR

TSAssistant is a multi-agent framework that streamlines Target Safety Assessment report drafting by integrating human expertise with AI-driven evidence synthesis across biomedical data sources.

Contribution

It introduces a modular, human-in-the-loop system that decomposes TSA report generation into specialized, interactive subagents for improved scalability and reproducibility.

Findings

Supports iterative report refinement with user edits and re-invocations.

Retrieves structured and unstructured biomedical data for evidence grounding.

Maintains conversational memory for continuous, context-aware assistance.

Abstract

Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic targets. This process is inherently iterative and expert-driven, posing challenges in scalability and reproducibility. We present TSAssistant, a multi-agent framework designed to support TSA report drafting through a modular, section-based, and human-in-the-loop paradigm. The framework decomposes report generation into a coordinated pipeline of specialised subagents, each targeting a single TSA section. Specialised subagents retrieve structured and unstructured data as well as literature evidence from curated biomedical sources through standardised tool interfaces, producing individually citable, evidence-grounded sections. Agent behaviour is governed by a hierarchical instruction architecture comprising system prompts, domain-specific skill modules, and runtime user instructions. A key feature is an interactive refinement loop in which users may manually edit sections, append new information, upload additional sources, or re-invoke agents to revise specific sections, with the system maintaining conversational memory across iterations. TSAssistant is designed to reduce the mechanical burden of evidence synthesis and report drafting, supporting a hybrid model in which agentic AI augments evidence synthesis while toxicologists retain final decision authority.