{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000921294,0.00197396,0.001180804,0.001577127,0.0006821202,0.001611743,0.003393234,0.0008122323,0.01924598],"category_scores_gemma":[0.002821401,0.0008704077,0.001480144,0.001314862,0.0007749814,0.001300351,0.00181157,0.001913603,0.007015446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009782778,"about_ca_system_score_gemma":0.002075069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003987206,"about_ca_topic_score_gemma":0.004626581,"domain_scores_codex":[0.9995553,0.00005726512,0.00004025893,0.0001173375,0.0001846722,0.00004516701],"domain_scores_gemma":[0.9989989,0.0005514036,0.00009885585,0.0001161388,0.0001554156,0.00007927413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002949845,0.0007214478,0.01411512,0.00500753,0.0008516621,0.002281714,0.001183389,0.1249902,0.06044621,0.03737951,0.4020338,0.3480395],"study_design_scores_gemma":[0.0008164975,0.0002326472,0.003520774,0.0001695486,0.0001250432,0.0009654064,0.0001664942,0.7871431,0.04317873,0.01579446,0.147713,0.0001742181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.03212856,0.0005221481,0.602225,0.0003423773,0.0001707876,0.0005495641,0.02817761,0.3256285,0.01025536],"genre_scores_gemma":[0.1552056,0.0009853867,0.7140734,0.0005010827,0.00007174152,0.003373537,0.07688837,0.03901942,0.009881601],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01924598,"threshold_uncertainty_score":0.06438422,"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."}}