{"id":"W2537032285","doi":"10.1101/081026","title":"Gist – an ensemble approach to the taxonomic classification of metatranscriptomic sequence data","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Hospital for Sick Children; University of Toronto; Genome Canada","keywords":"Computer science; Taxonomic rank; Sequence (biology); Biological classification; Annotation; Profiling (computer programming); Computational biology; Metagenomics; Artificial intelligence; Machine learning; Data mining; Biology; Information retrieval; Taxon; Evolutionary biology; Gene; Ecology; Genetics; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00521479,0.00155086,0.001277709,0.007185949,0.001108993,0.001677541,0.00185404,0.001261536,0.001823237],"category_scores_gemma":[0.01117672,0.0005875483,0.002256524,0.003837263,0.0007491254,0.001780425,0.002049496,0.002223539,0.001151004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006894091,"about_ca_system_score_gemma":0.001123127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002282192,"about_ca_topic_score_gemma":0.003700266,"domain_scores_codex":[0.9975306,0.0007154893,0.0002466017,0.0006647546,0.0006901101,0.0001524586],"domain_scores_gemma":[0.9955727,0.001894989,0.0004647393,0.0007637331,0.001030918,0.0002729577],"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":[0.0005171071,0.0002754516,0.01757841,0.000395194,0.0007011508,0.000480919,0.0007643135,0.1468247,0.03212802,0.007234846,0.008809464,0.7842904],"study_design_scores_gemma":[0.00001512621,0.00007390181,0.001535559,0.00002626984,0.00003876758,0.00008229567,0.0001014545,0.9749768,0.005777031,0.01439727,0.00294864,0.00002690071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01813755,0.0001098026,0.9732434,0.0001136081,0.00006250952,0.0001632411,0.0009229112,0.006900617,0.0003463149],"genre_scores_gemma":[0.08429512,0.00008633818,0.9108554,0.00007030741,0.00007807693,0.0002739071,0.003426957,0.0004804831,0.000433452],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007185949,"threshold_uncertainty_score":0.02757883,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06546195279623097,"score_gpt":0.2596564772162537,"score_spread":0.1941945244200228,"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."}}