{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001132541,0.0004284317,0.0005397425,0.0003683068,0.000107058,0.0001248125,0.001251152,0.0003462475,0.000001648088],"category_scores_gemma":[0.0001261273,0.000483137,0.0002928517,0.0006137394,0.00008015375,0.0003752203,0.0003637498,0.0003762515,0.000005748523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001411001,"about_ca_system_score_gemma":0.0014403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003884022,"about_ca_topic_score_gemma":0.000003582644,"domain_scores_codex":[0.9969988,0.0001083282,0.0007625937,0.001126553,0.000558547,0.0004452162],"domain_scores_gemma":[0.9973217,0.0001452227,0.0004680397,0.00119992,0.000700427,0.0001646876],"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":[0.0000414826,0.0002270822,0.002004266,0.001096181,0.0002127202,0.00001318824,0.00005989264,0.7544928,0.2048063,0.03687612,0.0001635355,0.000006494882],"study_design_scores_gemma":[0.0003247375,0.00004624934,0.04041485,0.0001882091,0.0000474664,6.278813e-9,3.579889e-7,0.8639957,0.09412108,0.0004313172,0.00005236452,0.0003776231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3335283,0.00007430414,0.663299,0.0001360878,0.0007249856,0.001075762,0.0006749575,0.0004850045,0.000001606686],"genre_scores_gemma":[0.641946,0.00002329196,0.3570607,0.00002870364,0.0001986273,0.0006607513,0.00000116378,0.00006922212,0.000011553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3084176,"threshold_uncertainty_score":0.9997621,"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."}}