{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006855626,0.0009623602,0.0007262006,0.0005392377,0.0003002792,0.0006976553,0.001213871,0.0009966685,0.003283897],"category_scores_gemma":[0.001691438,0.0003882695,0.0007796001,0.0004985537,0.0002974351,0.0009565987,0.0007317589,0.0009677731,0.001259809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005227398,"about_ca_system_score_gemma":0.001306789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002882492,"about_ca_topic_score_gemma":0.003164266,"domain_scores_codex":[0.9998586,0.00003093903,0.000007560067,0.00004846675,0.00003672707,0.00001775551],"domain_scores_gemma":[0.999634,0.0002118313,0.00002504106,0.00002912937,0.00007379742,0.00002622425],"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":[0.0007100613,0.0002633004,0.008316304,0.0003974384,0.0002567378,0.0003029218,0.00005168144,0.7992451,0.01411773,0.00635903,0.02657494,0.1434048],"study_design_scores_gemma":[0.00001812711,0.00003823391,0.0002160491,0.000004629333,0.00001119856,0.00004039434,0.000003377342,0.9940929,0.002075321,0.00210629,0.001386553,0.000006937129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1320693,0.001135469,0.8333053,0.0010052,0.0002559627,0.0001934245,0.00714087,0.01924059,0.005653889],"genre_scores_gemma":[0.6390664,0.001049968,0.3245316,0.0006035695,0.0001596573,0.0006068093,0.01974231,0.001139908,0.01309968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003283897,"threshold_uncertainty_score":0.01098567,"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."}}