{"id":"W2156995746","doi":"10.1186/1471-2105-10-316","title":"Unsupervised statistical clustering of environmental shotgun sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":111,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Burroughs Wellcome Fund","keywords":"Cluster analysis; Computer science; Shotgun sequencing; Dimensionality reduction; Unsupervised learning; Pairwise comparison; Statistical model; Pattern recognition (psychology); Artificial intelligence; Computational biology; Data mining; Genome; Biology; Genetics","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":[0.00007784682,0.0001066329,0.0001239101,0.00002123843,0.00004355293,0.00001007715,0.0001245296,0.00006232572,0.00001891873],"category_scores_gemma":[0.00001809107,0.00009475338,0.00004701555,0.00002526668,0.00008271301,0.000001220273,0.00006349886,0.00003173561,0.000006825957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006770009,"about_ca_system_score_gemma":0.00002807767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002114048,"about_ca_topic_score_gemma":0.000006250747,"domain_scores_codex":[0.9993703,0.00001153149,0.000273054,0.00009282796,0.00009815818,0.0001540972],"domain_scores_gemma":[0.9996771,0.00001109606,0.0000709723,0.0001821261,0.00001124083,0.00004748885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002083641,0.0002523105,0.02340457,0.0002338224,0.0001493066,0.000002378546,0.001461549,0.005043972,0.9061434,0.0009357831,0.001071738,0.06109283],"study_design_scores_gemma":[0.004230156,0.004951234,0.5525525,0.00009124674,0.0002007269,0.0001190818,0.005729376,0.2244996,0.1813654,0.001989639,0.02236191,0.001909087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9197177,0.0006163467,0.07554837,0.00003422161,0.000105474,0.0001994653,0.0002378866,0.000004798731,0.00353579],"genre_scores_gemma":[0.8919619,0.0002189711,0.1075342,0.0001421588,0.0000422017,0.000001998809,0.00005093668,0.00000484677,0.00004276383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7247779,"threshold_uncertainty_score":0.3863931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362830568214565,"score_gpt":0.229514811453265,"score_spread":0.2158865057711194,"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."}}