{"id":"W2158139747","doi":"10.1111/j.1365-2443.2012.01615.x","title":"Mass spectrum sequential subtraction speeds up searching large peptide <scp>MS</scp>/<scp>MS</scp> spectra datasets against large nucleotide databases for proteogenomics","year":2012,"lang":"en","type":"article","venue":"Genes to Cells","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministrstvo za visoko šolstvo, znanost in tehnologijo; Ministry of Education, Science and Technology; Japan Science and Technology Agency; Ministère de la Santé et des Services sociaux; Japan Society for the Promotion of Science; Uddannelses- og Forskningsministeriet","keywords":"Proteogenomics; Sequence database; Peptide; Database search engine; Biology; Subtraction; Computational biology; Database; Set (abstract data type); Identification (biology); Computer science; Genome; Gene; Genetics; Genomics; Biochemistry; Search engine; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087509,0.0006270276,0.0005223294,0.0001883733,0.0007048339,0.0002098482,0.0008272477,0.0002376448,0.0001549989],"category_scores_gemma":[0.0001950728,0.0007056847,0.0002832369,0.0003000047,0.00006999546,0.0007310859,0.000511069,0.0006422027,0.0003984121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003582849,"about_ca_system_score_gemma":0.0001325297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008653993,"about_ca_topic_score_gemma":0.00009033562,"domain_scores_codex":[0.9958132,0.00005616633,0.0007547796,0.001004293,0.0004380304,0.001933541],"domain_scores_gemma":[0.9969602,0.0003739225,0.0004535475,0.001500018,0.00008755003,0.00062478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001881559,0.0003231379,0.0007103804,0.0002214115,0.00007781514,0.0000084635,0.000266495,0.0002549299,0.9747357,0.002700065,0.02015252,0.0005302518],"study_design_scores_gemma":[0.0003978837,0.00002635911,0.00003273874,0.00003297752,0.00005198384,0.00001144464,0.0002744793,0.0004098999,0.557109,0.0004127379,0.4411001,0.0001404235],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6438199,0.000337908,0.3243478,0.0001171263,0.0003856866,0.00253419,0.02277573,0.0005144969,0.005167229],"genre_scores_gemma":[0.3653186,0.002012976,0.573225,0.001135137,0.007996832,0.002478801,0.03056662,0.0008614303,0.01640464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4209475,"threshold_uncertainty_score":0.9995394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02899961839279357,"score_gpt":0.300620737685328,"score_spread":0.2716211192925345,"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."}}