{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001501057,0.0001871476,0.0004471701,0.00009483483,0.000118702,0.00008326065,0.003255871,0.0003115117,0.00003448227],"category_scores_gemma":[0.0006596757,0.0001085785,0.0000499696,0.0003486197,0.00007295461,0.001674712,0.002843047,0.0004387317,0.00001128018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005586594,"about_ca_system_score_gemma":0.0000986911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000414412,"about_ca_topic_score_gemma":0.000002342342,"domain_scores_codex":[0.99753,0.000562173,0.0004347248,0.0007279907,0.0004620928,0.0002829808],"domain_scores_gemma":[0.9952176,0.001277655,0.0002973994,0.002967181,0.0001411918,0.00009896495],"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":[0.00001045822,0.0000454972,0.0002528309,0.00001923121,0.00001574902,0.000003779506,0.0001089121,0.0000162609,0.09580701,0.027665,0.009334454,0.8667208],"study_design_scores_gemma":[0.001428167,0.0002021204,0.006191769,0.0007704207,0.00003845968,0.00002904789,0.00005051258,0.1409686,0.6595998,0.0272716,0.1627463,0.0007031083],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001804791,0.001630083,0.9936386,0.0006107857,0.00141691,0.0001307416,0.00009109429,0.0001362472,0.0005407609],"genre_scores_gemma":[0.1966445,0.00002782088,0.8029561,0.0001265448,0.0001376898,0.000002656537,0.00002999709,0.000009826364,0.00006486694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8660177,"threshold_uncertainty_score":0.6050273,"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."}}