{"id":"W2180921306","doi":"10.1093/bioinformatics/btv587","title":"CSSSCL: a python package that uses combined sequence similarity scores for accurate taxonomic classification of long and short sequence reads","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Government of Ontario; Ontario Institute for Cancer Research","keywords":"Python (programming language); Sequence (biology); Computer science; Similarity (geometry); R package; Computational biology; Artificial intelligence; Biology; Programming language; Genetics","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":[0.0002739556,0.0001533102,0.0001930369,0.00003409869,0.00006529775,0.00003390181,0.0001603471,0.0001128228,5.059967e-7],"category_scores_gemma":[0.0001418402,0.0001382216,0.00005005261,0.00004513717,0.0001797373,0.000007260145,0.0001206379,0.00004150081,0.000001094205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002016557,"about_ca_system_score_gemma":0.0001132548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001604985,"about_ca_topic_score_gemma":0.00005083059,"domain_scores_codex":[0.9992329,0.00001942536,0.0003117925,0.0001588998,0.00009355003,0.0001833984],"domain_scores_gemma":[0.9992273,0.00003014307,0.0001801542,0.0003113628,0.0001642938,0.00008670757],"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":[0.0005429211,0.0001260802,0.2147214,0.0007422511,0.0002845291,0.000002089521,0.001495021,0.000262816,0.7599082,0.001347558,0.004774486,0.01579261],"study_design_scores_gemma":[0.003035057,0.002411683,0.2149399,0.0001590369,0.0002387721,0.0000607145,0.003254053,0.03584927,0.7262693,0.001296938,0.01117489,0.001310392],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899694,0.000348908,0.008465943,0.00008322561,0.0001115284,0.0004497073,0.0002224334,0.000006751851,0.0003421119],"genre_scores_gemma":[0.9878116,0.0004661827,0.01136786,0.00008259815,0.00003876438,0.00003849824,0.0001466477,0.00001288929,0.00003498913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03558646,"threshold_uncertainty_score":0.5636511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1431642840583145,"score_gpt":0.3136729286223924,"score_spread":0.1705086445640779,"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."}}