{"id":"W4400726464","doi":"10.1093/bioadv/vbae097","title":"Knowledge graph embeddings in the biomedical domain: are they useful? A look at link prediction, rule learning, and downstream polypharmacy tasks","year":2024,"lang":"en","type":"review","venue":"Bioinformatics Advances","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Engineering and Physical Sciences Research Council; UK Research and Innovation; Institute for Catastrophic Loss Reduction; Science and Technology Facilities Council; European Commission; Dell EMC; Accenture; Cisco Systems","keywords":"Computer science; Interpretability; Embedding; Machine learning; Artificial intelligence; Knowledge graph; Field (mathematics); Downstream (manufacturing); Graph; Data science; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008858414,0.0007985719,0.001214402,0.0007638651,0.0004010389,0.0004639722,0.00173404,0.0003453056,0.000006866334],"category_scores_gemma":[0.0001048795,0.0004711975,0.0004032169,0.001847938,0.0004118738,0.001264125,0.001093788,0.001509282,0.000143494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001459327,"about_ca_system_score_gemma":0.0001472483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002321181,"about_ca_topic_score_gemma":0.00002167198,"domain_scores_codex":[0.9962911,0.0002804732,0.001383458,0.0006760331,0.0006287269,0.0007401815],"domain_scores_gemma":[0.9974239,0.0007137192,0.0008578463,0.000697356,0.00007001123,0.000237196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005064158,0.00004918819,0.00006933852,0.008036601,0.00007904167,0.00004959047,0.002304575,0.00001970559,8.809108e-8,0.001157413,0.002543922,0.9856855],"study_design_scores_gemma":[0.0002706378,0.0001056607,0.00000716502,0.006511226,0.0001572979,0.0004281407,0.0002416374,0.005476393,3.145072e-7,0.003082555,0.9832287,0.0004902993],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001673349,0.9891195,0.007153403,0.0002077809,0.001095705,0.001004393,0.00009886292,0.0003474573,0.0009561108],"genre_scores_gemma":[0.0000315685,0.9894068,0.009514823,0.0001126472,0.0003510161,0.0002182613,0.0001178312,0.00004431693,0.0002027239],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9851952,"threshold_uncertainty_score":0.999774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02197307786622078,"score_gpt":0.3223211017238577,"score_spread":0.3003480238576369,"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."}}