arXiv:2611.25422v1 Announce Type: new
Abstract: Genomic foundation models provide variant-level evidence, but connecting that evidence to phenotype hypotheses requires accounting for uncertainty throughout structured reasoning. We introduce an uncertainty-conditioned path-energy framework that converts sequence predictions and calibrated predictive uncertainty into explicit distributions over graph-supported phenotype hypotheses, without patient-level phenotype supervision. An interpretable learned energy scores admissible gene–disease–phenotype routes, query uncertainty controls the target temperature, and path probabilities are aggregated into phenotype hypotheses. This formulation makes evidence quality an explicit determinant of hypothesis breadth while retaining traceable multi-path support. Exact normalization over enumerable candidate sets provides a reference for evaluating a Hastings-corrected learned revision operator. On AlzKB and Hetionet, phenotype-level entropy tracks upstream uncertainty, with Spearman correlations of 0.951 and 0.878, respectively; ablations identify the contribution of uncertainty conditioning. In masked-edge recovery, the model exceeds chance and degree-matched probability-permutation controls. Training the energy under the uncertainty-dependent temperature yields higher held-out recall@10 than training under a constant temperature of comparable magnitude. Under gene hold-out, recall@10 exceeds that of a trained DistMult embedding on 24 of 30 graph masks (0.183 versus 0.123); this difference is attributable mainly to three genes with many variants and is not established for all genes. These results establish an uncertainty-aware interface from genomic predictions to graph-supported phenotype hypotheses that combines interpretable probability allocation with held-out association recovery of explicitly stated scope.
Trending
- Google rolls out new search homepage with AI chat history and no search button
- How To Stream GTA 6 On Your iPhone, iPad Or Mac
- From Sequence Uncertainty to Phenotype Hypotheses: Uncertainty-Conditioned Inference over Biomedical Knowledge Graphs
- Meta reconsiders 2030 net-zero goal amid record emissions from AI data centers
- [2510.21798] Does AI Assistance Preserve or Collapse Disagreement? A Study of Pre-Annotations in Ambiguous Video Labeling
- Benchmarking and Enhancing Fine-Grained Visual Understanding with Multimodal Scene Graphs
- Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels
- YouTube is reportedly preparing to settle social media addiction claims for $3 billion
