{"id":"W1496257230","doi":"10.1186/s12859-015-0586-0","title":"ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidad de San Buenaventura","keywords":"Computer science; Data mining; Sequence (biology); Java; Feature (linguistics); Sequence alignment; Software; Key (lock); Protein function prediction; Artificial intelligence; Theoretical computer science; Machine learning; Programming language; Protein function; Peptide sequence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003449909,0.0002323421,0.0002770669,0.00008531394,0.00006992371,0.00007063879,0.0002792291,0.000173934,0.000001838739],"category_scores_gemma":[0.0004456703,0.0001876369,0.00007704661,0.0001525246,0.0001370003,0.00001889954,0.0002175604,0.00009953089,0.000003777455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001888569,"about_ca_system_score_gemma":0.0002062964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001940417,"about_ca_topic_score_gemma":0.000009259032,"domain_scores_codex":[0.9986406,0.00003576148,0.0005885141,0.0001657095,0.0002487717,0.0003206695],"domain_scores_gemma":[0.9988888,0.00001777544,0.0002735941,0.0003256272,0.000239656,0.0002545796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003608525,0.001333566,0.08849426,0.0152456,0.00100378,0.000004983217,0.0225468,0.08221702,0.03315035,0.01483366,0.09274741,0.6448141],"study_design_scores_gemma":[0.002004338,0.00556362,0.001350482,0.00008645164,0.00006371437,0.00009327011,0.000580967,0.7749156,0.02197147,0.0004769226,0.1921245,0.0007686365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1694367,0.0001430437,0.8243211,0.00016136,0.0002413293,0.004615882,0.00008232175,0.00009896783,0.000899306],"genre_scores_gemma":[0.0294172,0.000006242099,0.9695728,0.000285419,0.0001232041,0.0002726596,0.0001400592,0.00002406393,0.0001582973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6926986,"threshold_uncertainty_score":0.765161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03172182749760137,"score_gpt":0.3074146386683912,"score_spread":0.2756928111707899,"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."}}