{"id":"W2538355508","doi":"10.1038/nmeth.4037","title":"Comparison of high-throughput sequencing data compression tools","year":2016,"lang":"en","type":"article","venue":"Nature Methods","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Throughput; Computer science; Benchmarking; Benchmark (surveying); Raw data; Data compression; Data set; DNA sequencing; Data mining; Set (abstract data type); Biology; Artificial intelligence; Operating system","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":[0.006209938,0.001219767,0.000948347,0.003917733,0.000777176,0.002280289,0.001979571,0.001410725,0.003659627],"category_scores_gemma":[0.02357206,0.0005153536,0.001002294,0.004154898,0.000559311,0.0021404,0.000996041,0.001088243,0.001389969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001141872,"about_ca_system_score_gemma":0.001494321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001296501,"about_ca_topic_score_gemma":0.00138007,"domain_scores_codex":[0.9957175,0.0008810699,0.0005105743,0.0004467567,0.002213574,0.0002305774],"domain_scores_gemma":[0.9817107,0.01156197,0.0007034947,0.001754979,0.003962076,0.0003068195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006605809,0.001079648,0.01371658,0.001991258,0.0006963049,0.0005454808,0.0005716322,0.08548509,0.1375825,0.01284079,0.01398408,0.7249008],"study_design_scores_gemma":[0.0004337538,0.001758645,0.01744241,0.0003351515,0.0003734433,0.0012248,0.0004368345,0.5890589,0.3583408,0.01053396,0.01976531,0.0002959987],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4339515,0.007536049,0.5144504,0.001380578,0.0009373322,0.0007242431,0.005651392,0.02677994,0.008588707],"genre_scores_gemma":[0.4106236,0.003272119,0.5680375,0.0004204992,0.0001896404,0.0007321677,0.01198735,0.001687251,0.003049819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006209938,"threshold_uncertainty_score":0.03284168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1614176675957748,"score_gpt":0.4801760690923179,"score_spread":0.3187584014965431,"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."}}