{"id":"W2949137682","doi":"10.48550/arxiv.1203.6233","title":"Information Theory of DNA Shotgun Sequencing","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"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; Sequence (biology); Sequencing by ligation; k-mer; Algorithm; Hybrid genome assembly; DNA; Sequence assembly; Computational biology; Computer science; Biology; Genetics; Base sequence; Genomic library; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004046055,0.0001825271,0.0002187255,0.0002080632,0.0000861252,0.00006317447,0.001464889,0.000196385,0.00003792755],"category_scores_gemma":[0.00002510148,0.000186599,0.0001149461,0.0002749438,0.00006383372,0.001944414,0.002557392,0.0003095536,0.00006745323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001423001,"about_ca_system_score_gemma":0.00017795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007602555,"about_ca_topic_score_gemma":0.000001739132,"domain_scores_codex":[0.9990779,0.0001094781,0.0002109719,0.0002721664,0.0001002498,0.0002292652],"domain_scores_gemma":[0.9982389,0.00007993732,0.0003508512,0.00108089,0.0001420232,0.0001073875],"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":[0.00002357371,0.00004250176,0.0005553052,0.0001576969,0.00005759022,0.00001634045,0.001627229,0.03461883,0.0001549465,0.950798,0.0002653896,0.01168257],"study_design_scores_gemma":[0.0006084323,0.00005335711,0.002698743,0.0003627709,0.0001014001,0.00001049736,0.0005223943,0.8015845,0.002642419,0.1874794,0.003106636,0.0008294873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1016328,0.0000447234,0.8933343,0.00001043646,0.0005363418,0.00013248,0.00002777323,0.0001114304,0.0041697],"genre_scores_gemma":[0.9948887,0.00005953814,0.004707364,0.00005097506,0.00005019595,3.511853e-7,0.00004437247,0.000005296835,0.0001932165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8932559,"threshold_uncertainty_score":0.7609287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07011755826983199,"score_gpt":0.1810735353863428,"score_spread":0.1109559771165108,"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."}}