Biomedical knowledge graphs help language models generate better hypotheses
HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge
Computation and LanguageArtificial Intelligence
Summary
It can be hard to tell if large language models make good guesses about biology by understanding real evidence or just sounding smart. The authors connected several biology databases into one big network to test how language models generate ideas about diseases and enzymes. They found that when models see the whole biological path, they make more evidence-based guesses, while partial information leads to less grounded but still interesting ideas. This shows that detailed scientific knowledge helps models reason more accurately.
What this means in practice
- •For biomedical data teams: Generate biologically plausible hypotheses linking enzymes to diseases by guiding language models with detailed biochemical data paths.
- •For drug discovery teams: Identify new therapeutic targets by using knowledge graphs that show mechanistic steps connecting biological elements and diseases.
Authors
Dominic Okonkwo, Adetayo Okunoye, Ismailcem Budak Arpinar
Abstract
Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply produce convincing-sounding ideas. To study this, we combine three major biological databases: the Kyoto Encyclopedia of Genes and Genomes (KEGG), Rhea, and UniProt, into a unified biochemical knowledge graph and construct a benchmark of 550 paths connecting enzyme sources to rare disease endpoints, yielding 13,200 hypotheses from six LLMs under four conditions varying the biological information each model receives: source enzyme only, full biological path, or source and disease endpoint only. Hypotheses are scored using an expert-derived five-criterion rubric on a 1-5 scale per criterion. We find that models given both the source and disease endpoint often produce the highest-scoring hypotheses, showing that LLMs can generate compelling ideas from minimal information. However, these hypotheses are less grounded in the evidence. In contrast, models given the full biological path generate hypotheses more consistent with known mechanistic relationships. We call this evidence-disciplined reasoning. To confirm this effect, we shuffled intermediate path steps while keeping endpoints fixed. Evidence grounding dropped significantly (delta = -0.793, p < 0.001), confirming models genuinely used path structure during reasoning. Our findings show that knowledge graphs support hypothesis generation in two ways: they identify biological endpoint pairs absent from the literature, and their mechanistic paths guide how LLMs reason between them.