{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002101822,0.0001314374,0.0001307784,0.00004404066,0.00009516269,0.00003275721,0.0001600694,0.0001234548,0.000008875407],"category_scores_gemma":[0.0000622595,0.0001084187,0.0001394743,0.00008369269,0.00007204024,0.0000231316,0.00009373828,0.00005380358,0.00002132716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001296933,"about_ca_system_score_gemma":0.00005403224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001359488,"about_ca_topic_score_gemma":0.00001470502,"domain_scores_codex":[0.9991598,0.000007979218,0.0002658112,0.0001020366,0.0001175956,0.000346777],"domain_scores_gemma":[0.9994997,0.00001876392,0.00008971609,0.0002099756,0.00005190153,0.0001299882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001671315,0.0005503755,0.006991779,0.0005769123,0.0004887915,0.00000112466,0.001473859,0.002688182,0.6122001,0.0006246175,0.003199089,0.371038],"study_design_scores_gemma":[0.001024669,0.0003360126,0.0008309467,0.0000237575,0.0001038789,0.0001265583,0.000642905,0.8479165,0.1107835,0.0001084935,0.03747248,0.0006302913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02055869,0.0002551935,0.9781356,0.00003568517,0.0001477677,0.0001563926,0.00007272096,0.00001608513,0.000621788],"genre_scores_gemma":[0.0509169,0.00005790173,0.9472769,0.0004674952,0.0005363974,0.00004212959,0.0003199549,0.00001417986,0.0003680671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8452284,"threshold_uncertainty_score":0.4421185,"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."}}