{"id":"W4200599555","doi":"10.1109/tcbb.2021.3135978","title":"NMTF-DTI: A Nonnegative Matrix Tri-factorization Approach With Multiple Kernel Fusion for Drug-Target Interaction Prediction","year":2021,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada; University of Saskatchewan","keywords":"Computer science; Receiver operating characteristic; Artificial intelligence; Kernel (algebra); Cross-validation; Similarity (geometry); Regularization (linguistics); Area under curve; Set (abstract data type); Machine learning; Pattern recognition (psychology); Mathematics; Image (mathematics); Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002161161,0.001524169,0.001891231,0.002278122,0.0006624411,0.0009131695,0.00154874,0.001405861,0.001757371],"category_scores_gemma":[0.00494658,0.0004664884,0.002380832,0.001960111,0.0006032768,0.001809369,0.001166179,0.001883937,0.001112559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009329279,"about_ca_system_score_gemma":0.001750531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009629032,"about_ca_topic_score_gemma":0.008243755,"domain_scores_codex":[0.9987352,0.0003491977,0.00009967027,0.0002811025,0.0003866601,0.0001480597],"domain_scores_gemma":[0.9981679,0.0007514684,0.0002709471,0.0002223808,0.0004578484,0.0001294675],"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":[0.0004944548,0.0004525549,0.005317711,0.0004650587,0.0004303061,0.0003645631,0.0002112456,0.395475,0.02399158,0.009972572,0.01834866,0.5444763],"study_design_scores_gemma":[0.000009970458,0.00005197972,0.0004124264,0.000008749171,0.00002032634,0.00008002375,0.00001243245,0.9933423,0.001614284,0.003323059,0.001099979,0.00002452839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01021073,0.0007630712,0.9860601,0.0001929986,0.0000687322,0.00007715618,0.0003341824,0.001613211,0.000679773],"genre_scores_gemma":[0.3074089,0.001085808,0.684607,0.0003649024,0.0001747211,0.0003006388,0.003129469,0.0002495989,0.002679079],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009629032,"threshold_uncertainty_score":0.01914597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02271619689469421,"score_gpt":0.2972851945128064,"score_spread":0.2745689976181122,"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."}}