{"id":"W1965359119","doi":"10.1186/1748-7188-6-23","title":"ReCoil - an algorithm for compression of extremely large datasets of dna data","year":2011,"lang":"en","type":"article","venue":"Algorithms for Molecular Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data compression; Redundancy (engineering); Algorithm; Encoding (memory); Compression (physics); Volume (thermodynamics); Data compression ratio; Lossless compression; Compression ratio; Sequence (biology); Data mining; Image compression; Artificial intelligence; Biology; Physics","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":[0.0008921148,0.001077848,0.000677414,0.001671132,0.0007472382,0.001313506,0.001433713,0.0009189962,0.003210205],"category_scores_gemma":[0.003529226,0.000371209,0.0006262138,0.002134346,0.0007154148,0.001947244,0.001478166,0.001427954,0.002221529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005089333,"about_ca_system_score_gemma":0.0007632228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008228245,"about_ca_topic_score_gemma":0.001034855,"domain_scores_codex":[0.9991944,0.00008505272,0.00009562844,0.0001401242,0.0004215297,0.00006324489],"domain_scores_gemma":[0.9987438,0.0004818324,0.0001294765,0.0002732238,0.000326083,0.00004558335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006719611,0.0001318007,0.001512824,0.0004115705,0.0001012566,0.0003824309,0.0003780956,0.02956651,0.07874899,0.02233595,0.0179166,0.8478421],"study_design_scores_gemma":[0.0002282465,0.0004014613,0.001756431,0.0001280813,0.0000649136,0.001940447,0.0002125974,0.5980841,0.3018737,0.02373678,0.07145295,0.0001202701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01121667,0.0008912312,0.9815403,0.0001986695,0.0001191556,0.0001419781,0.0003397593,0.004326735,0.001225478],"genre_scores_gemma":[0.05098758,0.0007941766,0.9413339,0.0001348529,0.00007784322,0.0003526822,0.001749144,0.0006590328,0.003910717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003210205,"threshold_uncertainty_score":0.01073927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1004202575440594,"score_gpt":0.3489168214591663,"score_spread":0.2484965639151069,"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."}}