{"id":"W4296207299","doi":"10.1101/2022.09.13.507819","title":"Deep6: Classification of Metatranscriptomic Sequences into Cellular Empires and Viral Realms Using Deep Learning Models","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Tula Foundation; University of British Columbia","funders":"Tula Foundation","keywords":"Coding (social sciences); Deep learning; ENCODE; Computational biology; Scripting language; Sequence (biology); Range (aeronautics); Artificial intelligence; Biology; Computer science; Genetics; Gene; Mathematics; Engineering","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":[0.001046201,0.001591363,0.0005905688,0.0009299075,0.0004153116,0.001553315,0.001545722,0.001713912,0.005302471],"category_scores_gemma":[0.001879134,0.000581457,0.001185786,0.0007702488,0.0005382138,0.001834827,0.00146218,0.002569586,0.002605877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001340324,"about_ca_system_score_gemma":0.001098021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006285007,"about_ca_topic_score_gemma":0.007147555,"domain_scores_codex":[0.9995913,0.0000807562,0.0000195847,0.0001359303,0.0001007461,0.00007179298],"domain_scores_gemma":[0.9994652,0.0001809379,0.00004577254,0.0001013633,0.0001399682,0.0000667961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008501058,0.0004937815,0.01215523,0.0005475862,0.000367571,0.0002767233,0.0002114714,0.4971603,0.04886873,0.01296786,0.06442272,0.3616779],"study_design_scores_gemma":[0.00001597697,0.00003272688,0.00047454,0.00001852859,0.00001006074,0.00002544119,0.00001869946,0.9823232,0.008536914,0.005948121,0.002584206,0.00001151628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2390008,0.002849928,0.6808485,0.002218567,0.0005606638,0.000184344,0.01973003,0.04465924,0.009948051],"genre_scores_gemma":[0.5542622,0.0009816588,0.3901328,0.001048359,0.0001671052,0.0002268451,0.03764102,0.001423117,0.01411697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006285007,"threshold_uncertainty_score":0.01773852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02682014492727301,"score_gpt":0.2374456807797402,"score_spread":0.2106255358524672,"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."}}