{"id":"W1931014516","doi":"10.1109/cibcb.2015.7300324","title":"Assembly independent functional annotation of short-read data using SOFA: Short-ORF functional annotation","year":2015,"lang":"en","type":"article","venue":"","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Annotation; MIT License; ORFS; Data deduplication; Pipeline (software); Retargeting; Data mining; Information retrieval; Software; Artificial intelligence; Open reading frame; Database; Programming language; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002622228,0.002857994,0.001413834,0.002660175,0.001584395,0.001596629,0.001594078,0.0009821029,0.00468497],"category_scores_gemma":[0.005711201,0.0009109666,0.002889591,0.001757948,0.0006861943,0.001518861,0.001390231,0.001697636,0.004775746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008395516,"about_ca_system_score_gemma":0.001682063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002318769,"about_ca_topic_score_gemma":0.003273429,"domain_scores_codex":[0.9988863,0.0001696921,0.0001434363,0.0003775202,0.0003104279,0.0001126245],"domain_scores_gemma":[0.9970042,0.00110361,0.0003869437,0.0005934343,0.0007794073,0.0001322772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002983697,0.0004146747,0.02678632,0.003305439,0.0007095516,0.0009715338,0.001318934,0.02477932,0.6317107,0.01035118,0.04005442,0.2566143],"study_design_scores_gemma":[0.0001368667,0.0004314717,0.01381828,0.0002611528,0.0002472962,0.0006665181,0.0003369483,0.4128647,0.493515,0.01677001,0.06058867,0.0003631411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07925722,0.0005890665,0.821268,0.0002196561,0.0002839435,0.0003449433,0.03413621,0.06127926,0.002621671],"genre_scores_gemma":[0.1565899,0.0003652597,0.7468629,0.0001951396,0.00007850304,0.0008273402,0.08592466,0.006404632,0.002751609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00468497,"threshold_uncertainty_score":0.01567286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2100306006330303,"score_gpt":0.3208009349368049,"score_spread":0.1107703343037746,"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."}}