{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003884296,0.0001591807,0.0001948316,0.0001421172,0.00008713513,0.00007364474,0.0004826814,0.00008755152,0.00001412574],"category_scores_gemma":[0.00003481166,0.0001346732,0.0001059703,0.0002254808,0.00005953301,0.0002585978,0.00006786243,0.0002131238,0.0000222061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003437798,"about_ca_system_score_gemma":0.0001359991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008960687,"about_ca_topic_score_gemma":0.000008949552,"domain_scores_codex":[0.9987223,0.0001005213,0.0001999501,0.0005579855,0.0001222899,0.000296992],"domain_scores_gemma":[0.9992203,0.0004238018,0.00003952741,0.0002085678,0.00004450355,0.00006337028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001192693,0.0002971822,0.005358925,0.0004306592,0.000251751,0.00006930582,0.002746305,0.2385587,0.05052841,0.6454693,0.0002246195,0.05594552],"study_design_scores_gemma":[0.0001528511,0.0001292333,0.000548458,0.00003403064,0.000008950041,0.00001245052,0.000003801946,0.9247829,0.007490875,0.06365132,0.003039252,0.0001458227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1575349,0.001137982,0.8390169,0.0008217944,0.0002428012,0.0004288431,0.00005584816,0.0003572256,0.000403717],"genre_scores_gemma":[0.8466508,0.00004669964,0.1526774,0.00005680626,0.0001090452,0.0001275145,0.00008002773,0.000017006,0.0002347132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6891159,"threshold_uncertainty_score":0.5491815,"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."}}