Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization

• URL: http://arxiv.org/abs/2603.20262v1
• Date: Fri, 13 Mar 2026 06:25:27 GMT
• Title: Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization
• Abstract summary: We propose DESRO, a framework for deciphering scientific reasoning from outcomes.<n>By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic.<n>We instantiate this framework in molecule optimization, a pivotal stage in drug discovery.
• Score: 22.850204283344524
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning [103.788281428856]
  We introduce SciReasoner, a scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals.<n>SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary.<n>Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks.
  arXiv  Detail & Related papers  (2026-07-08T17:59:59Z)
• Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization [85.4863852505905]
  We introduce unsupervised reward optimization of protein language models (PLMs)<n>Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with semantic consistency informed by protein representation models, exhibit strong correlation with controllability measures across base models and temperature regimes.<n>Our framework provides a scalable pathway toward controllable biomolecular design in settings where labeled preferences or experimental feedback are scarce or unavailable.
  arXiv  Detail & Related papers  (2026-06-17T11:42:01Z)
• Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting [95.24017293537025]
  Causal Ensemble Agent (CEA) is a novel framework that aggregates structural insights from statistical discovery experts across different graph levels.<n>CEA achieves the strongest overall performance across a wide range of causal discovery methods.
  arXiv  Detail & Related papers  (2026-06-09T09:09:07Z)
• Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback [56.69850045068714]
  We introduce textitInfluence-Guided Regression (IGSR), a method that frames equation discovery as an iterative two-step process.<n>We demonstrate IGSRs effectiveness on a diverse suite of benchmarks, including LLM-SRBench, pharmacological PKPD models, an epidemiological simulation, and real-world genomic data.
  arXiv  Detail & Related papers  (2026-05-27T23:48:01Z)
• MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation [20.62843594129358]
  We introduce MolQuest, a novel agent-based evaluation framework for molecular structure elucidation.<n>Unlike existing datasets, MolQuest formalizes molecular structure elucidation as a multi-turn interactive task.<n>Results reveal that contemporary frontier models exhibit significant limitations in authentic scientific scenarios.
  arXiv  Detail & Related papers  (2026-03-26T09:57:17Z)
• Logos: An evolvable reasoning engine for rational molecular design [18.041008766322346]
  We present Logos, a compact molecular reasoning model that integrates multi-step logical reasoning with strict chemical consistency.<n>Across multiple benchmark datasets, Logos achieves strong performance in both structural accuracy and chemical validity.<n> Logos enables human inspection and assessment of the design logic underlying each generated structure.
  arXiv  Detail & Related papers  (2026-03-10T06:56:35Z)
• DrugR: Optimizing Molecular Drugs through LLM-based Explicit Reasoning [24.70952870676648]
  DrugR is a large language model that introduces explicit, step-by-step pharmacological reasoning into the optimization process.<n>Our approach integrates domain-specific continual pretraining, supervised fine-tuning via reverse data engineering, and self-balanced multi-granular reinforcement learning.<n> Experimental results demonstrate that DrugR achieves comprehensive enhancement across multiple properties without compromising structural similarity or target binding affinity.
  arXiv  Detail & Related papers  (2026-02-09T02:26:25Z)
• CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning [63.44477226386808]
  Chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks.<n>But it struggles in scientific domains where even advanced models often produce incorrect or superficial reasoning.<n>We propose CoT-Evo, an evolutionary CoT distillation framework to overcome this problem.
  arXiv  Detail & Related papers  (2025-10-15T05:29:56Z)
• Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery [0.0]
  Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles.<n>We present a systematic approach combining a reasoning-centric model architecture with Low-Rank Adaptation fine-tuning.<n> Evaluation reveals substantial improvements: the fine-tuned system achieves 96.3% format adherence, 97.4% chemical validity, and 74.4% synthesis feasibility.
  arXiv  Detail & Related papers  (2025-07-09T23:05:23Z)
• Causal Representation Learning from Multimodal Biomedical Observations [57.00712157758845]
  We develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets.<n>Key theoretical contribution is the structural sparsity of causal connections between modalities.<n>Results on a real-world human phenotype dataset are consistent with established biomedical research.
  arXiv  Detail & Related papers  (2024-11-10T16:40:27Z)
• Text-Guided Multi-Property Molecular Optimization with a Diffusion Language Model [20.250683535089617]
  We propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM)<n>By fusing physically and chemically detailed semantics with specialized molecular representations, TransDLM effectively integrates diverse information sources to guide precise optimization.
  arXiv  Detail & Related papers  (2024-10-17T14:30:27Z)
• Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization [147.7899503829411]
  AliDiff is a novel framework to align pretrained target diffusion models with preferred functional properties. It can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score.
  arXiv  Detail & Related papers  (2024-07-01T06:10:29Z)
• Differentiable Scaffolding Tree for Molecular Optimization [47.447362691543304]
  We propose differentiable scaffolding tree (DST) that utilizes a learned knowledge network to convert discrete chemical structures to locally differentiable ones. Our empirical studies show the gradient-based molecular optimizations are both effective and sample efficient.
  arXiv  Detail & Related papers  (2021-09-22T01:16:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.