{"id":"W4388248410","doi":"10.1101/2023.10.31.564943","title":"A general prediction model for substrates of transport proteins","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Deutsche Forschungsgemeinschaft; European Commission","keywords":"Python (programming language); Transporter; Computer science; Function (biology); Substrate specificity; Computational biology; Artificial intelligence; Machine learning; Biology; Biochemistry; Gene; Cell biology; Programming language","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":[0.001236907,0.000854112,0.000764524,0.0009927251,0.0002985186,0.001008993,0.001431812,0.001206441,0.003666582],"category_scores_gemma":[0.00225834,0.0004130325,0.0009149401,0.0009623969,0.000691249,0.001521106,0.0006545662,0.0009440059,0.0009199515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0013721,"about_ca_system_score_gemma":0.001083545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007392436,"about_ca_topic_score_gemma":0.004915511,"domain_scores_codex":[0.9996873,0.00006534598,0.00001790529,0.0001306736,0.00005102757,0.00004783459],"domain_scores_gemma":[0.999306,0.0003906732,0.00006480808,0.00004597944,0.0001494669,0.00004310711],"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":[0.0001216055,0.00005327491,0.002783422,0.00006427228,0.0000314549,0.000122521,0.00001745867,0.9713773,0.002045549,0.006665117,0.001310305,0.01540777],"study_design_scores_gemma":[0.000004475184,0.000007792447,0.000109538,0.000001991427,0.000004542391,0.00001349574,0.000001618112,0.9969132,0.0002480989,0.002506361,0.0001863626,0.000002487788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3057607,0.001270182,0.6744856,0.001836116,0.0001367776,0.0001781716,0.004210127,0.002109177,0.01001308],"genre_scores_gemma":[0.9388921,0.0005579963,0.04686138,0.0002491733,0.00006246578,0.0002183022,0.002297367,0.0001036403,0.01075751],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007392436,"threshold_uncertainty_score":0.0146988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04097979840468212,"score_gpt":0.2684199389075194,"score_spread":0.2274401405028372,"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."}}