TRACEDD: A Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design
- 1Tata Consultancy Services
Abstract
Drug discovery depends on coordinated decisions across target validation, structure analysis, molecular design, developability assessment and synthetic feasibility, but current computational methods often operate as disconnected tools. Here, we introduce TRACEDD (Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design), a framework that makes three primary contributions: (1) It establishes a 'tool-first' multi agentic architecture where LLMs orchestrate validated computational tools rather than replace them, ensuring scientific rigor. (2) It implements a multi-agent system that mirrors expert discovery teams, enabling transparent and traceable decision-making through a Reason-Act-Observe loop. (3) It demonstrates an end-to-end workflow, from target validation to synthesis planning, that adaptively handles real-world data variability, such as the absence of experimental structures. The framework decomposes discovery into specialized agents for target validation, druggability assessment, molecular generation, lead optimization, ADMET evaluation, literature evidence integration and retrosynthesis, all operating through a Reason Act Observe workflow. Using JAK2 as a representative case, we show that the system can retrieve experimental protein structures, invoke AlphaFold when structures are unavailable, identify druggable pockets and perform de novo molecular generation. Known JAK2 inhibitors are used to define design hypotheses and guide reinforcement learning-based molecular generation, with docking scores/predicted pIC50 and other physicochemical/ADMET properties serving as reward and prioritization signals. The framework demonstrates a tool-first, reasoning-driven approach in which each major decision is linked to explicit tool invocation, intermediate evidence. By combining agentic orchestration with domain-specific computational tools, the system supports transparent, adaptable and human-verifiable molecular design workflows, providing a foundation for more reliable AI-assisted drug discovery.
Related
- LabWeaver: reliable agentic data analysis grounded in laboratory knowled
- OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells
- BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
- GenoMorph: Pathway-Grounded Genomic Disease Reasoning via Adaptive Latent Computation
- TIAgent: From Natural Language to Grounded Agentic Workflows for Computational Pathology
BibTeX
@misc{vangala2026tracedd,
title = {{TRACEDD: A Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design}},
author = {S. R. Vangala and V. V. Kasturi and N. Bung and A. Roy},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.12.751167},
url = {https://www.biorxiv.org/content/10.64898/2026.09.12.751167v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - TRACEDD: A Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design
AU - S. R. Vangala
AU - V. V. Kasturi
AU - N. Bung
AU - A. Roy
PY - 2026
DA - 2026/09/12
PB - bioRxiv
DO - 10.64898/2026.09.12.751167
UR - https://www.biorxiv.org/content/10.64898/2026.09.12.751167v1
AB - Drug discovery depends on coordinated decisions across target validation, structure analysis, molecular design, developability assessment and synthetic feasibility, but current computational methods often operate as disconnected tools. Here, we introduce TRACEDD (Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design), a framework that makes three primary contributions: (1) It establishes a 'tool-first' multi agentic architecture where LLMs orchestrate validated computational tools rather than replace them, ensuring scientific rigor. (2) It implements a multi-agent system that mirrors expert discovery teams, enabling transparent and traceable decision-making through a Reason-Act-Observe loop. (3) It demonstrates an end-to-end workflow, from target validation to synthesis planning, that adaptively handles real-world data variability, such as the absence of experimental structures. The framework decomposes discovery into specialized agents for target validation, druggability assessment, molecular generation, lead optimization, ADMET evaluation, literature evidence integration and retrosynthesis, all operating through a Reason Act Observe workflow. Using JAK2 as a representative case, we show that the system can retrieve experimental protein structures, invoke AlphaFold when structures are unavailable, identify druggable pockets and perform de novo molecular generation. Known JAK2 inhibitors are used to define design hypotheses and guide reinforcement learning-based molecular generation, with docking scores/predicted pIC50 and other physicochemical/ADMET properties serving as reward and prioritization signals. The framework demonstrates a tool-first, reasoning-driven approach in which each major decision is linked to explicit tool invocation, intermediate evidence. By combining agentic orchestration with domain-specific computational tools, the system supports transparent, adaptable and human-verifiable molecular design workflows, providing a foundation for more reliable AI-assisted drug discovery.
ER -