{"id":"W2119894516","doi":"10.1186/1471-2105-8-286","title":"CLUSS: Clustering of protein sequences based on a new similarity measure","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Cluster analysis; Similarity (geometry); Phylogenetic tree; Biological data; Similarity measure; Computer science; Matching (statistics); Protein sequencing; Measure (data warehouse); Data mining; Protein family; Computational biology; Artificial intelligence; Bioinformatics; Biology; Genetics; Peptide sequence; Mathematics; Gene","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":[0.001017313,0.0002376635,0.0002233201,0.0001263142,0.00008456973,0.00003443387,0.0003666396,0.0002616708,0.00002540363],"category_scores_gemma":[0.0005948492,0.0002070505,0.0001323712,0.0001887809,0.00009909893,0.00001485855,0.0001230229,0.0002193028,0.00002039777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000297473,"about_ca_system_score_gemma":0.0003042101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002837742,"about_ca_topic_score_gemma":0.0001545135,"domain_scores_codex":[0.9983229,0.00003614865,0.0007148825,0.0001401762,0.0004323917,0.0003535103],"domain_scores_gemma":[0.9987206,0.00004445445,0.0004058685,0.0005559868,0.0001168698,0.0001561808],"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":[0.005757379,0.001216584,0.07344097,0.01188861,0.0005380636,0.00001861823,0.006559812,0.5918657,0.09511126,0.003254154,0.01787026,0.1924786],"study_design_scores_gemma":[0.001614077,0.001071434,0.002181116,0.0003028718,0.00002980002,0.00001683102,0.0004380817,0.9236535,0.05510894,0.00006741103,0.01496541,0.0005505423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02681541,0.00005820972,0.950364,0.00009670801,0.0001360415,0.0005706084,0.00002223953,0.00005153245,0.02188526],"genre_scores_gemma":[0.3386598,0.000006188012,0.6598012,0.0007280024,0.000176696,0.000006917991,0.0001189352,0.00002954666,0.0004727351],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3317878,"threshold_uncertainty_score":0.8443273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01812383730328375,"score_gpt":0.2674233571612362,"score_spread":0.2492995198579524,"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."}}