{"id":"W2905575949","doi":"10.1093/bioinformatics/bty1015","title":"SPRING: a next-generation compressor for FASTQ data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Cancer Institute; University of Illinois at Urbana-Champaign; National Institutes of Health; Sunnybrook Research Institute; Silicon Valley Community Foundation","keywords":"Computer science; Lossless compression; Scalability; Lossy compression; Data compression; Data mining; Redundancy (engineering); Identifier; Compression (physics); Database; Artificial intelligence; Computer network; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002101411,0.00162748,0.0006736658,0.001727622,0.001282047,0.001512046,0.003015341,0.001190771,0.02184419],"category_scores_gemma":[0.008034871,0.0005950392,0.0008668639,0.002509367,0.001198091,0.003465723,0.002374373,0.00181802,0.009098105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069935,"about_ca_system_score_gemma":0.001629075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003078847,"about_ca_topic_score_gemma":0.003242033,"domain_scores_codex":[0.9981984,0.0001615736,0.0001679425,0.0003119562,0.001014224,0.000145968],"domain_scores_gemma":[0.9966069,0.0009193017,0.0001896208,0.000920224,0.001223359,0.0001406303],"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":[0.002930821,0.0003050132,0.004287962,0.001234687,0.000266272,0.0007021545,0.0007338182,0.01410287,0.06632976,0.02156779,0.3759215,0.5116174],"study_design_scores_gemma":[0.0009558438,0.000643967,0.00314173,0.0003235227,0.0001379192,0.001304596,0.0003212249,0.2697725,0.3561509,0.02458731,0.3423069,0.0003536525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03717218,0.001932525,0.7046961,0.002084502,0.001280655,0.0009322666,0.0195895,0.2201468,0.01216541],"genre_scores_gemma":[0.1668357,0.00144597,0.7144243,0.001831378,0.0007037866,0.001995744,0.06849612,0.01438631,0.02988072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02184419,"threshold_uncertainty_score":0.07307607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1701892097079504,"score_gpt":0.3126197987859841,"score_spread":0.1424305890780337,"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."}}