{"id":"W4402898771","doi":"10.1371/journal.pbio.3002807","title":"SPOT: A machine learning model that predicts specific substrates for transport proteins","year":2024,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"H2020 European Research Council; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Python (programming language); Biology; Transporter; Computational biology; Computer science; Function (biology); Machine learning; Artificial intelligence; Membrane transport protein; Substrate specificity; Web server; Bioinformatics; The Internet; Biochemistry; Gene; Cell biology","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":[0.0007273683,0.0008731268,0.0008076948,0.0005700016,0.0002937703,0.0006453829,0.001297361,0.001004848,0.003231385],"category_scores_gemma":[0.002057374,0.0003872706,0.0008269614,0.0005516042,0.0003042197,0.0009544871,0.0007435707,0.0009754369,0.0009176728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005537231,"about_ca_system_score_gemma":0.001550138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003350341,"about_ca_topic_score_gemma":0.003871345,"domain_scores_codex":[0.9998596,0.00003617316,0.00000816226,0.00004037998,0.00003848791,0.00001720205],"domain_scores_gemma":[0.9995866,0.0002549521,0.00002704628,0.0000283018,0.00007346558,0.00002952102],"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":[0.0005839664,0.0002279331,0.006055669,0.0004120551,0.0002314093,0.0002497084,0.00003953958,0.8404142,0.006918011,0.0058837,0.02267703,0.1163067],"study_design_scores_gemma":[0.00002204411,0.00004587162,0.0001553437,0.000005045692,0.00001256224,0.00004015577,0.000003188026,0.994949,0.001371284,0.002045022,0.001343806,0.00000668776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1377901,0.001710738,0.8253829,0.001594834,0.0003022789,0.000285433,0.008076381,0.01741515,0.007442007],"genre_scores_gemma":[0.6682341,0.001441213,0.3002092,0.0007859882,0.0001724561,0.0007695233,0.01685526,0.0009358862,0.0105963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003350341,"threshold_uncertainty_score":0.01081002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07347171942761031,"score_gpt":0.3011818458396393,"score_spread":0.227710126412029,"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."}}