{"id":"W3150158916","doi":"10.1109/bibm.2012.6392682","title":"Identifying protein binding functionality of protein family sequences by Aligned Pattern clusters","year":2012,"lang":"en","type":"article","venue":"","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein family; Computational biology; Representation (politics); Computer science; Protein sequencing; Protein function prediction; Protein structure; Probabilistic logic; Peptide sequence; Cluster (spacecraft); Amino acid residue; Protein function; Data mining; Biology; Biochemistry; Artificial intelligence","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":[0.0003626869,0.0004077375,0.000468772,0.002633597,0.0004921932,0.0006308438,0.0006288919,0.0005232462,0.002702495],"category_scores_gemma":[0.002144634,0.0002796329,0.0005538051,0.00274015,0.0003148351,0.0007643011,0.0005065714,0.0004194903,0.0008649292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003880973,"about_ca_system_score_gemma":0.0005948396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00230451,"about_ca_topic_score_gemma":0.003005604,"domain_scores_codex":[0.9996667,0.00004315187,0.00002471188,0.0001215318,0.0001039382,0.00004008839],"domain_scores_gemma":[0.9991788,0.0002982171,0.0001312428,0.0001398258,0.0002011126,0.00005083264],"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":[0.002092759,0.0005791848,0.05808512,0.0006397549,0.0002563262,0.0007774761,0.0008179929,0.0881867,0.2803197,0.01218614,0.007006716,0.5490522],"study_design_scores_gemma":[0.00009246467,0.0002975395,0.02564359,0.00005102387,0.000115873,0.0008509821,0.0004226938,0.8787286,0.06646475,0.01701596,0.01025682,0.00005957728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5905774,0.000296181,0.3980722,0.0001318295,0.00003128404,0.0002874819,0.003491585,0.003556483,0.003555716],"genre_scores_gemma":[0.5649697,0.0002084391,0.4263029,0.00004324342,0.00001399246,0.0002598838,0.006223227,0.0004062168,0.001572372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002702495,"threshold_uncertainty_score":0.009040773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01600699276221967,"score_gpt":0.2574140300015513,"score_spread":0.2414070372393317,"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."}}