{"id":"W2147492358","doi":"10.1093/bioinformatics/18.12.1696","title":"DNACompress: fast and effective DNA sequence compression","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":210,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bioinformatics Solutions (Canada); Western University","funders":"National Science Foundation","keywords":"Compression (physics); Sequence (biology); DNA; Computer science; DNA sequencing; Data compression; Computational biology; Algorithm; Genetics; Biology; Materials science; Composite material","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":[0.0007324831,0.001168656,0.000558182,0.002020124,0.0005509713,0.0008478376,0.00125131,0.0007845041,0.0144094],"category_scores_gemma":[0.002705283,0.0005453086,0.0004075319,0.001817557,0.000492989,0.00103201,0.00120727,0.001170706,0.007305346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000450183,"about_ca_system_score_gemma":0.0007034313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009566056,"about_ca_topic_score_gemma":0.001350841,"domain_scores_codex":[0.9994324,0.00007205144,0.00004557052,0.0001039102,0.0003052807,0.00004085179],"domain_scores_gemma":[0.9991201,0.0003545757,0.00008737313,0.000165911,0.000213797,0.00005820177],"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":[0.0007889232,0.0001256345,0.0008934613,0.0005627236,0.00007034222,0.0004213182,0.0001618163,0.01275641,0.08729523,0.01486977,0.1096655,0.7723889],"study_design_scores_gemma":[0.0005099918,0.0003192596,0.001916713,0.0001508771,0.00007012073,0.00132957,0.00009356661,0.3799454,0.471835,0.02325881,0.1204643,0.0001064242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03246675,0.002087807,0.8701677,0.0007798751,0.0004759717,0.0003362939,0.005522962,0.07769547,0.01046714],"genre_scores_gemma":[0.1188221,0.0009165324,0.8488306,0.0003600698,0.000240984,0.0007202437,0.01241429,0.003737742,0.01395739],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0144094,"threshold_uncertainty_score":0.04820424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02148647027400059,"score_gpt":0.238584043247377,"score_spread":0.2170975729733765,"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."}}