{"id":"W2566001817","doi":"10.1093/bioinformatics/btw793","title":"A new method for decontamination of <i>de novo</i> transcriptomes using a hierarchical clustering algorithm","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; U.S. Department of Agriculture","keywords":"Human decontamination; Computer science; Cluster analysis; Documentation; Sample (material); Scripting language; Identification (biology); Hierarchical clustering; Algorithm; Data mining; Biology; Artificial intelligence; Engineering; Programming language; Chemistry","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":[0.0001817139,0.00009263989,0.0001310173,0.00003496874,0.00003865049,0.000008717157,0.00009712444,0.00007624691,0.000002418244],"category_scores_gemma":[0.00004162369,0.00006936645,0.00008679889,0.00003347129,0.00002515502,0.000002054249,0.00004155314,0.00001873754,4.120512e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000146241,"about_ca_system_score_gemma":0.00009855252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001045132,"about_ca_topic_score_gemma":0.00001151779,"domain_scores_codex":[0.9994209,0.00001275761,0.0002539124,0.00008569714,0.00005804926,0.000168635],"domain_scores_gemma":[0.9996402,0.00003336869,0.00008799362,0.000125948,0.00005883287,0.00005369955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003449256,0.00001048705,0.000132765,0.00005102757,0.00005615794,8.907242e-8,0.0003516677,0.00004441588,0.6842701,0.0000858596,0.0001474564,0.3148154],"study_design_scores_gemma":[0.004116868,0.0008528653,0.001432942,0.0001053206,0.0001317554,0.00007900743,0.0003885611,0.1150659,0.8317382,0.001134814,0.04444612,0.0005076178],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07541172,0.0001646658,0.9238852,0.00009148485,0.00009000124,0.0001654741,0.00007108984,0.000002382832,0.0001179498],"genre_scores_gemma":[0.09440015,0.0001093791,0.9051173,0.00009607901,0.0001130018,0.000008166478,0.000007350068,0.00001137397,0.0001371891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3143078,"threshold_uncertainty_score":0.2828681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01805888345734189,"score_gpt":0.2906607890563882,"score_spread":0.2726019055990463,"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."}}