{"id":"W2072234624","doi":"10.1109/isit.2013.6620505","title":"Optimal DNA shotgun sequencing: Noisy reads are as good as noiseless reads","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Shotgun sequencing; DNA sequencing; Computer science; Shotgun; Noise (video); Sequence (biology); DNA; Channel (broadcasting); Algorithm; Computational biology; Biology; Genetics; Artificial intelligence; Computer network; Gene","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01040226,0.001065189,0.002380034,0.001775378,0.001022193,0.004102527,0.002036873,0.003825855,0.00232274],"category_scores_gemma":[0.06387004,0.001154699,0.0008915497,0.00162414,0.008211701,0.009243697,0.004610148,0.004184717,0.0007716979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001567228,"about_ca_system_score_gemma":0.001051549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004754467,"about_ca_topic_score_gemma":0.0002787069,"domain_scores_codex":[0.9894001,0.003082051,0.0005555365,0.002148318,0.003990605,0.0008234513],"domain_scores_gemma":[0.9456411,0.04387609,0.002914275,0.004498184,0.002035918,0.001034549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008777285,0.000136756,0.002684714,0.0008202743,0.0001184198,0.0003817918,0.0005644379,0.1259549,0.03967746,0.7866334,0.002679314,0.039471],"study_design_scores_gemma":[0.00004026271,0.0001661584,0.000783986,0.0001005281,0.00003694157,0.0003458394,0.0001021765,0.1844322,0.02197188,0.7893319,0.002621429,0.00006674471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1703094,0.004899999,0.8040449,0.002767903,0.0003945903,0.00008327519,0.0005257964,0.0007490752,0.01622508],"genre_scores_gemma":[0.8732585,0.003023587,0.1169335,0.002167291,0.0005147257,0.0002907723,0.0005145465,0.0004220648,0.002874818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01040226,"threshold_uncertainty_score":0.05501306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02801162172109875,"score_gpt":0.2691731575295082,"score_spread":0.2411615358084094,"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."}}