{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002743586,0.0001385971,0.0002419317,0.0001663781,0.00004328055,0.00001270287,0.0002996794,0.00008623773,0.00000663521],"category_scores_gemma":[0.00004504891,0.00009507135,0.00001823365,0.0002223009,0.00006063917,0.0001563757,0.00007936682,0.0001193593,0.000003187067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001189758,"about_ca_system_score_gemma":0.00001099445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002175032,"about_ca_topic_score_gemma":0.000003002207,"domain_scores_codex":[0.9991498,0.00001855905,0.0002111654,0.0003082316,0.00006002766,0.0002521952],"domain_scores_gemma":[0.9994644,0.0001854329,0.00003935409,0.0002049324,0.0000319522,0.00007394508],"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":[0.00002329852,0.00008699087,0.002410171,0.00007663673,0.00003001491,0.00009486858,0.0004252522,0.000852007,0.0836068,0.004572535,0.01198783,0.8958336],"study_design_scores_gemma":[0.001347021,0.0004260615,0.002906639,0.0001818775,0.000004971056,0.00009515448,0.000008480581,0.9160757,0.000458655,0.0009460784,0.07736477,0.0001845676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02000068,0.0009796889,0.9769934,0.0009741589,0.0006885107,0.0001506457,0.000004126189,0.00009985234,0.0001089712],"genre_scores_gemma":[0.3527358,0.003050052,0.6397606,0.001390394,0.002237295,0.000172559,0.0001165419,0.00003900169,0.0004978229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9152237,"threshold_uncertainty_score":0.3876897,"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."}}