{"id":"W4402559989","doi":"10.21203/rs.3.rs-5057842/v1","title":"BioPathNet: Enhancing Link Prediction in Biomedical Knowledge Graphs through Path Representation Learning","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Bundesministerium für Bildung und Forschung; National Institutes of Health; Joachim Herz Stiftung","keywords":"Interpretability; Computer science; Scalability; Artificial intelligence; Machine learning; Embedding; Node (physics); Graph; Representation (politics); Feature learning; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001217933,0.0015112,0.0008744464,0.003069418,0.0005681902,0.001406188,0.001559873,0.001529067,0.01119868],"category_scores_gemma":[0.006240064,0.0005935472,0.001026233,0.002485865,0.0004169013,0.003029448,0.001610157,0.001714584,0.002899328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007007395,"about_ca_system_score_gemma":0.001279337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008444756,"about_ca_topic_score_gemma":0.01466513,"domain_scores_codex":[0.9994874,0.0001241209,0.00002391072,0.0001760065,0.0001549043,0.00003355086],"domain_scores_gemma":[0.9978789,0.001374299,0.00007391669,0.000388381,0.0001965728,0.00008804847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008866923,0.0008626937,0.004927075,0.0009647008,0.0004920745,0.0004026683,0.0002148474,0.2313073,0.006634884,0.01691431,0.1149414,0.6214513],"study_design_scores_gemma":[0.0001089223,0.00006436823,0.0004582402,0.00004250968,0.00006839793,0.00006894484,0.00003616941,0.9621549,0.003082915,0.02496342,0.008936124,0.00001516363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08528945,0.001526765,0.792441,0.0020206,0.0007358641,0.0004265777,0.02462347,0.08462274,0.008313548],"genre_scores_gemma":[0.2755977,0.001102984,0.6623585,0.0004991899,0.0002592001,0.0003808361,0.04550014,0.003492558,0.0108088],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01119868,"threshold_uncertainty_score":0.03746331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03417946870331069,"score_gpt":0.372560997037947,"score_spread":0.3383815283346364,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}