English

Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization

Biomolecules 2026-03-24 v1 Artificial Intelligence Machine Learning

Abstract

Emerging reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering reasoning steps from outcome data as a viable paradigm for enabling scientific reasoning, providing a scalable approach to accelerate scientific discovery.

Keywords

Cite

@article{arxiv.2603.20262,
  title  = {Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization},
  author = {Zequn Liu and Kehan Wu and Shufang Xie and Zekun Guo and Wei Zhang and Tao Qin and Renhe Liu and Yingce Xia},
  journal= {arXiv preprint arXiv:2603.20262},
  year   = {2026}
}

Comments

Work in progress, 37 pages

R2 v1 2026-07-01T11:30:18.210Z