From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation

TL;DR

The paper introduces CoDHy, an interactive AI system that leverages biomedical literature and databases to generate, validate, and refine drug combination hypotheses for cancer research, supporting researchers with transparent, human-in-the-loop reasoning.

Contribution

It presents a novel human-in-the-loop system that integrates knowledge graphs, embeddings, and reasoning for biomarker-guided drug hypothesis generation in oncology.

Findings

Effective hypothesis generation and ranking demonstrated

Supports transparent, iterative exploration for researchers

Applicable to translational oncology decision support

Abstract

The rapid growth of biomedical literature and curated databases has made it increasingly difficult for researchers to systematically connect biomarker mechanisms to actionable drug combination hypotheses. We present AI Co-Scientist (CoDHy), an interactive, human-in-the-loop system for biomarker-guided drug combination hypothesis generation in cancer research. CoDHy integrates structured biomedical databases and unstructured literature evidence into a task-specific knowledge graph, which serves as the basis for graph-based reasoning and hypothesis construction. The system combines knowledge graph embeddings with agent-based reasoning to generate, validate, and rank candidate drug combinations, while explicitly grounding each hypothesis in retrievable evidence. Through a web-based interface, users can configure the scientific context, inspect intermediate results, and iteratively refine hypotheses, enabling transparent and researcher-steerable exploration rather than automated decision-making. We demonstrate CoDHy as a system for exploratory hypothesis generation and decision support in translational oncology, highlighting its design, interaction workflow, and practical use cases.