{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005586324,0.001096268,0.001960788,0.00320753,0.0008549323,0.003513034,0.0023419,0.0024394,0.002878118],"category_scores_gemma":[0.0205592,0.000673401,0.001151771,0.002885859,0.003831846,0.004481819,0.002137049,0.003283888,0.001152187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003015447,"about_ca_system_score_gemma":0.001705362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001897,"about_ca_topic_score_gemma":0.00056496,"domain_scores_codex":[0.9950846,0.001950263,0.0002946598,0.0005711878,0.001781843,0.0003174803],"domain_scores_gemma":[0.9817926,0.01437859,0.0007206444,0.001342006,0.001521354,0.0002448226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004020115,0.00002196913,0.0003466844,0.0003616314,0.00004199483,0.000128857,0.0001114587,0.07199891,0.0008241814,0.9049904,0.00292418,0.01820954],"study_design_scores_gemma":[0.000009493695,0.00002222313,0.0001443519,0.00006428747,0.000009937377,0.00007443941,0.00001947837,0.1530962,0.0003478941,0.8427301,0.0034569,0.00002479862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00828453,0.008953434,0.963685,0.00185253,0.0003641611,0.00008249155,0.0006421634,0.0002759038,0.01585973],"genre_scores_gemma":[0.5824299,0.03088074,0.3580971,0.002799621,0.003028059,0.001225875,0.002374887,0.0004031827,0.01876069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005586324,"threshold_uncertainty_score":0.0295437,"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."}}