{"id":"W2012680439","doi":"10.1109/51.940049","title":"A compression algorithm for DNA sequences","year":2001,"lang":"en","type":"article","venue":"IEEE Engineering in Medicine and Biology Magazine","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Hong Kong; City University of Hong Kong","keywords":"Data compression; Compression (physics); Algorithm; Benchmark (surveying); Computer science; Matching (statistics); DNA sequencing; DNA; DNA computing; Mathematics; Biology; Genetics; Physics; Computation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005337106,0.0009762071,0.000643562,0.001911051,0.0006964838,0.0009750935,0.0009314274,0.001256578,0.004106347],"category_scores_gemma":[0.003101591,0.0003256897,0.0005126274,0.002646521,0.0006622931,0.001434162,0.0009200164,0.0009654854,0.002018429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005459511,"about_ca_system_score_gemma":0.0007675677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001399163,"about_ca_topic_score_gemma":0.00108658,"domain_scores_codex":[0.999193,0.00008289819,0.00006699147,0.0001341918,0.0004715549,0.00005139339],"domain_scores_gemma":[0.9991628,0.0002639149,0.00006762671,0.0001968124,0.0002812853,0.00002749959],"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":[0.000259745,0.00005812765,0.0004766479,0.0002333596,0.00004482672,0.0002081197,0.0001291938,0.03197046,0.04499648,0.02249699,0.010392,0.888734],"study_design_scores_gemma":[0.0001793662,0.0005969045,0.00154379,0.000174031,0.00009581251,0.003960522,0.0001303376,0.6654543,0.2089555,0.03963121,0.07917127,0.0001069701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01095981,0.001206713,0.9824101,0.0002353662,0.0002208199,0.0001770209,0.0002823606,0.001997418,0.002510438],"genre_scores_gemma":[0.05532803,0.000898138,0.9367779,0.0002606962,0.0001475854,0.0003231622,0.001075045,0.0002082592,0.004981156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004106347,"threshold_uncertainty_score":0.01373708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03680986124003464,"score_gpt":0.2978930809314662,"score_spread":0.2610832196914316,"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."}}