{"id":"W6893158151","doi":"10.5281/zenodo.14825943","title":"SPOT: A machine learning model that predicts specific substrates for transport proteins","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Python (programming language); Function (biology); Web server; Transporter; Membrane transport protein; Set (abstract data type); Training set; Protein function prediction","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":[0.0005904446,0.0001795263,0.000125208,0.000127592,0.0008799045,0.0004052414,0.000535721,0.0001121672,0.0008418403],"category_scores_gemma":[0.0001800713,0.0001773415,0.00009543894,0.0001925471,0.0001007443,0.00002737262,0.000246102,0.0003170568,0.000458893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000377184,"about_ca_system_score_gemma":0.000009556385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004299566,"about_ca_topic_score_gemma":6.476932e-7,"domain_scores_codex":[0.998694,0.00008594093,0.000235999,0.0003952746,0.0002429536,0.0003458303],"domain_scores_gemma":[0.9993032,0.00001110328,0.00006528068,0.0003092106,0.0001877456,0.0001234927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001251262,0.0005095545,0.0002829168,0.002977327,0.0006265499,0.00005994553,0.006764722,0.05522307,0.5292396,0.01576044,0.1937582,0.1935465],"study_design_scores_gemma":[0.0003724785,0.0003918044,0.0001131247,0.00004841157,0.00001678297,0.00007463396,0.00006842102,0.09512058,0.009774438,0.0001062795,0.8937049,0.0002081626],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3300627,0.002510287,0.5525967,0.001477093,0.000360371,0.00333165,0.001753197,0.002497686,0.1054103],"genre_scores_gemma":[0.9837796,0.0003132998,0.0035603,0.00005906844,0.0002148789,4.220937e-7,0.007657686,0.001069682,0.003345073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6999467,"threshold_uncertainty_score":0.9217561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02885701052006852,"score_gpt":0.2426682998927335,"score_spread":0.213811289372665,"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."}}