{"id":"W4360608857","doi":"10.1101/2023.03.19.533306","title":"An Ensemble Learning Approach to perform Link Prediction on Large Scale Biomedical Knowledge Graphs for Drug Repurposing and Discovery","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Roche (Canada)","funders":"Genentech; Roche","keywords":"Knowledge graph; Computer science; Leverage (statistics); Repurposing; Theoretical computer science; Scalability; Graph; ENCODE; Curse of dimensionality; Feature learning; Vector space; Artificial intelligence; Machine learning; Mathematics","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":[0.001964611,0.001504767,0.0017605,0.003980122,0.0007892363,0.001199668,0.002326053,0.001932687,0.002917974],"category_scores_gemma":[0.006126183,0.0004974462,0.001692183,0.00362184,0.0006073976,0.002460246,0.001736086,0.002325731,0.00127175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008510829,"about_ca_system_score_gemma":0.001059539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007410979,"about_ca_topic_score_gemma":0.01260994,"domain_scores_codex":[0.9989675,0.0003261212,0.00006083628,0.0003007167,0.0002358517,0.0001088436],"domain_scores_gemma":[0.9962485,0.001874178,0.0003109103,0.0005719263,0.0008016269,0.0001927526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002405966,0.0005096809,0.007907758,0.0001766076,0.0003977046,0.0002997146,0.0001262913,0.6151513,0.003062913,0.0081098,0.01434063,0.3496771],"study_design_scores_gemma":[0.000005068369,0.00002688751,0.000241677,0.00001158168,0.00002661345,0.00001738762,0.00001762155,0.9910227,0.0004348923,0.007493254,0.0006966271,0.000005667255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07086549,0.002143709,0.9143706,0.001402923,0.000263493,0.0001825379,0.001947664,0.004782183,0.004041371],"genre_scores_gemma":[0.6832724,0.001208163,0.3001207,0.0007434827,0.0003799773,0.0002727054,0.008789564,0.0002549585,0.004958088],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007410979,"threshold_uncertainty_score":0.0147357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01087275831905892,"score_gpt":0.2289097232670573,"score_spread":0.2180369649479984,"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."}}