{"id":"W2337408142","doi":"10.1093/bioinformatics/btw211","title":"Partitioning and correlating subgroup characteristics from Aligned Pattern Clusters","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"A priori and a posteriori; Sequence alignment; Multiple sequence alignment; Biology; Class (philosophy); Similarity (geometry); Function (biology); Computational biology; Conserved sequence; Divergence (linguistics); Sequence (biology); In silico; Protein superfamily; Structural Classification of Proteins database; Rank (graph theory); Cluster analysis; Phylogenetic tree; Computer science; Artificial intelligence; Genetics; Protein structure; Peptide sequence; Mathematics; Gene; Combinatorics","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":[0.0002002916,0.0001979176,0.0001733,0.00004315672,0.0001364654,0.00007788582,0.0001561226,0.0001625331,0.00004990478],"category_scores_gemma":[0.0002821519,0.0001475642,0.0000511259,0.00004620521,0.0001026854,0.00002791522,0.0002036064,0.00006590096,0.0000852767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001830405,"about_ca_system_score_gemma":0.00002785127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002012466,"about_ca_topic_score_gemma":0.00001375661,"domain_scores_codex":[0.9988592,0.00003240054,0.0005127162,0.0001480698,0.0001665648,0.0002810595],"domain_scores_gemma":[0.9991183,0.00006877931,0.0003054792,0.0003317882,0.00005726564,0.0001183344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00009431229,0.0000545726,0.4238164,0.0002242015,0.0002022948,0.000005192598,0.002469858,0.00003580058,0.0304886,0.0002195528,0.005528423,0.5368608],"study_design_scores_gemma":[0.0110348,0.002058177,0.4002516,0.001755512,0.0003807576,0.0002862843,0.003135419,0.3510695,0.04083915,0.0005423028,0.1840727,0.00457375],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8116853,0.00007333377,0.1858615,0.0002787388,0.00030565,0.0001817486,0.0001426454,0.00005746316,0.001413609],"genre_scores_gemma":[0.9816289,0.0001890472,0.01661547,0.0007668461,0.0002153501,0.000010413,0.0003470301,0.00002582374,0.0002011397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.532287,"threshold_uncertainty_score":0.6017492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006556936634770645,"score_gpt":0.2177660405102531,"score_spread":0.2112091038754825,"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."}}