{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001193897,0.0001708158,0.0001764739,0.00008412843,0.0002248146,0.0002554013,0.0006145733,0.00007364666,0.00002590631],"category_scores_gemma":[0.00002556237,0.0001314849,0.00003371138,0.000190399,0.00007764463,0.001573849,0.0006807072,0.0001414352,0.0001471081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002409514,"about_ca_system_score_gemma":0.000007257479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007805942,"about_ca_topic_score_gemma":4.270295e-7,"domain_scores_codex":[0.9989472,0.00003578318,0.0002707783,0.0001985672,0.0002867859,0.0002608841],"domain_scores_gemma":[0.9990066,0.0001112664,0.0001313754,0.0005524023,0.00005228383,0.0001461258],"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":[0.000003643261,0.00007185995,0.0001776538,0.0001054138,0.00001525547,0.00001216761,0.003080603,0.00009029593,0.000985178,0.005785489,0.01157638,0.9780961],"study_design_scores_gemma":[0.0003522176,0.00008035877,0.0009750561,0.00009714007,0.000004155529,0.00004943498,0.00005306657,0.9814395,0.001191696,0.0003502422,0.01520043,0.000206682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01014077,0.0004212996,0.9797127,0.0002464429,0.0004198195,0.0004226744,0.00003044639,0.0003308486,0.008274978],"genre_scores_gemma":[0.4831351,0.0004203085,0.5148339,0.0009265328,0.0001521107,0.00004883166,0.00002694529,0.00002064825,0.000435598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9813492,"threshold_uncertainty_score":0.5361799,"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."}}