{"id":"W2032345031","doi":"10.1186/1471-2105-13-174","title":"A novel hierarchical clustering algorithm for gene sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Hierarchical clustering; DNA sequencing; Complete-linkage clustering; Single-linkage clustering; DNA microarray; Tuple; Similarity (geometry); Phylogenetic tree; Pattern recognition (psychology); Measure (data warehouse); Sequence (biology); Correlation clustering; Data mining; Computational biology; Computer science; Artificial intelligence; Biology; Gene; Mathematics; CURE data clustering algorithm; Genetics; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001237891,0.0009691502,0.001046119,0.003465899,0.00126041,0.001303461,0.002047461,0.001230528,0.003545573],"category_scores_gemma":[0.003638061,0.0005685957,0.001533291,0.003816693,0.0007171315,0.001713472,0.001189715,0.001255105,0.00304374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001547896,"about_ca_system_score_gemma":0.00195647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006124612,"about_ca_topic_score_gemma":0.006720611,"domain_scores_codex":[0.9982417,0.0002429627,0.0001314641,0.0005035836,0.000779329,0.0001010097],"domain_scores_gemma":[0.9987047,0.0003273727,0.0001322192,0.0001948104,0.0005846898,0.00005623142],"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":[0.0001310302,0.00007231584,0.001615373,0.0004092684,0.0001824502,0.0001261028,0.0004075107,0.1072247,0.02197375,0.02716596,0.01390447,0.8267872],"study_design_scores_gemma":[0.00005483035,0.00007790898,0.001299002,0.00005567744,0.00005768067,0.0003924201,0.0000871134,0.923986,0.00987009,0.03584906,0.02820642,0.00006385435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002149756,0.0002264959,0.995706,0.00006768511,0.00004939468,0.00007161329,0.0001692596,0.000882152,0.0006775482],"genre_scores_gemma":[0.0188205,0.0001404224,0.9787677,0.0000508289,0.00004247789,0.0001583644,0.0005916258,0.0001582278,0.001269723],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006124612,"threshold_uncertainty_score":0.01217794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02575875611595342,"score_gpt":0.2702451143211852,"score_spread":0.2444863582052318,"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."}}