{"id":"W2952553535","doi":"10.48550/arxiv.1304.2798","title":"Optimal DNA shotgun sequencing: Noisy reads are as good as noiseless reads","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Shotgun sequencing; Shotgun; DNA sequencing; Sequence (biology); DNA; Computational biology; Noise (video); Computer science; Channel (broadcasting); Algorithm; Biology; Genetics; Artificial intelligence; Gene; Computer network","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":[0.01083783,0.001026666,0.002297178,0.001852651,0.001053055,0.004195828,0.00211518,0.00391879,0.002280897],"category_scores_gemma":[0.06928849,0.001136654,0.0008965787,0.001730646,0.008185172,0.009514344,0.004617072,0.004196557,0.0008032072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001684356,"about_ca_system_score_gemma":0.001136208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005066024,"about_ca_topic_score_gemma":0.0003007393,"domain_scores_codex":[0.9894246,0.003198683,0.0005736499,0.002144066,0.00386959,0.0007893718],"domain_scores_gemma":[0.941139,0.04759594,0.003099324,0.004994596,0.002113418,0.001057756],"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":[0.0009037902,0.0001323215,0.002874045,0.0007765796,0.000121495,0.0003522349,0.0005796182,0.1298485,0.03284805,0.7861652,0.00280675,0.04259148],"study_design_scores_gemma":[0.0000384699,0.0001532547,0.0007116692,0.00009710647,0.00003421323,0.0003054584,0.00009775522,0.1891986,0.01821688,0.7885718,0.002514352,0.00006055727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1664844,0.004728788,0.8081664,0.003166228,0.0004295662,0.00008485177,0.0005702388,0.0007442042,0.0156253],"genre_scores_gemma":[0.867853,0.002887951,0.1221909,0.002257352,0.0005479733,0.0002828221,0.0005561018,0.0003977443,0.003026192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01083783,"threshold_uncertainty_score":0.05731666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06393007705734222,"score_gpt":0.1989365968999761,"score_spread":0.1350065198426339,"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."}}