{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002455123,0.0001020647,0.0001053807,0.00005304708,0.0002309875,0.0004143114,0.001615253,0.00004817103,0.000007584535],"category_scores_gemma":[0.00005604016,0.00008337503,0.00002297803,0.0001220508,0.00004068995,0.002564783,0.00107119,0.00004526722,0.000114568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001333426,"about_ca_system_score_gemma":0.00005016436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001745193,"about_ca_topic_score_gemma":0.00001215012,"domain_scores_codex":[0.9991232,0.000009366649,0.0002783006,0.0001858727,0.0001951138,0.0002081593],"domain_scores_gemma":[0.9982447,0.00004069951,0.0001242868,0.001402306,0.0001146819,0.00007329384],"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":[0.00001671717,0.0001263812,0.00009604392,0.0001706575,0.0000408863,0.000001303498,0.001805887,0.00005845347,0.002642712,0.04581898,0.229166,0.7200559],"study_design_scores_gemma":[0.0001982898,0.00006237585,0.00005742482,0.00001173194,0.000003321231,0.00000279969,0.00001605878,0.7751544,0.0009569521,0.000131585,0.2233081,0.00009697581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007469283,0.00006026925,0.9971479,0.0001937039,0.0007101656,0.0002338085,0.00007962579,0.0001207788,0.0007068199],"genre_scores_gemma":[0.01607756,0.00001521055,0.9824967,0.0004456157,0.00062257,0.00001078417,0.0002209022,0.000006815025,0.0001038278],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7750959,"threshold_uncertainty_score":0.3995215,"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."}}