{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001364827,0.0006951559,0.0008835942,0.001348235,0.0003124591,0.0006335081,0.0008367606,0.0002707702,0.002058557],"category_scores_gemma":[0.001945967,0.0004389338,0.0006452377,0.001270971,0.0002673036,0.0009583046,0.000665369,0.0003991381,0.001263581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002873802,"about_ca_system_score_gemma":0.0006086447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009893365,"about_ca_topic_score_gemma":0.002243953,"domain_scores_codex":[0.9993953,0.0001174034,0.00006641628,0.00016301,0.000225397,0.00003257284],"domain_scores_gemma":[0.998934,0.0005447534,0.000126987,0.000134178,0.0001926405,0.00006742507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001335126,0.0002133872,0.008266132,0.000293401,0.0001922536,0.0002252434,0.00007349078,0.005929342,0.7564048,0.0006725271,0.00236703,0.2240272],"study_design_scores_gemma":[0.0002677342,0.0007264463,0.02754796,0.00002062541,0.000148861,0.001405759,0.0001092366,0.3525137,0.6025472,0.002652472,0.01195366,0.0001063727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4770225,0.0008777644,0.5034212,0.0003610198,0.00005438958,0.0001738985,0.002092574,0.01445428,0.001542293],"genre_scores_gemma":[0.3372023,0.0003334237,0.6567219,0.0001729903,0.00004773613,0.0001602885,0.004107838,0.0004474641,0.0008060752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002058557,"threshold_uncertainty_score":0.007218003,"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."}}