{"id":"W3158513288","doi":"10.2196/28277","title":"Drug-Drug Interaction Predictions via Knowledge Graph and Text Embedding: Instrument Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Baidu","keywords":"Computer science; Knowledge graph; Embedding; Graph; Binary classification; Machine learning; Drug-drug interaction; Big data; Data mining; Theoretical computer science; Drug; Artificial intelligence; Support vector machine; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000924693,0.0001675879,0.0002069446,0.0002188776,0.0002027945,0.0002886648,0.0003889914,0.00006388901,0.00005292063],"category_scores_gemma":[0.0002259795,0.000156616,0.00006353483,0.000720996,0.00006742345,0.001538605,0.0006566704,0.000368436,0.00004568217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047162,"about_ca_system_score_gemma":0.0003539583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007480197,"about_ca_topic_score_gemma":0.00002346424,"domain_scores_codex":[0.9975545,0.0002738242,0.0007104793,0.0002115659,0.001033646,0.0002159716],"domain_scores_gemma":[0.9984614,0.0004864848,0.0001843003,0.000370014,0.0002293128,0.0002685438],"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":[0.00002581861,0.003391921,0.004225709,0.0004198356,0.00029442,0.00004807393,0.1498387,0.01048273,0.00004236364,0.01757625,0.01222266,0.8014315],"study_design_scores_gemma":[0.0008009202,0.00007461662,0.00492807,0.0001056176,0.00002060126,0.0001279175,0.005455539,0.9801657,0.0003960054,0.002535646,0.005179021,0.0002103647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4424327,0.00003762032,0.5525877,0.0007472481,0.0009580871,0.000351313,0.000002730643,0.0001536669,0.002728919],"genre_scores_gemma":[0.9691262,0.0000277966,0.030163,0.000285849,0.0001175491,0.00009940528,0.00002744594,0.000008941055,0.000143846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9696829,"threshold_uncertainty_score":0.6386614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02468633374167057,"score_gpt":0.3544232595842591,"score_spread":0.3297369258425885,"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."}}