{"id":"W3005183537","doi":"10.1038/s41467-020-14608-2","title":"A synthetic peptide library for benchmarking crosslinking-mass spectrometry search engines for proteins and protein complexes","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Österreichischen Akademie der Wissenschaften; Austrian Science Fund; European Commission","keywords":"Identification (biology); Benchmarking; Database search engine; False discovery rate; Mass spectrometry; Search engine; Computational biology; Computer science; Combinatorial chemistry; Peptide; Chemistry; Data mining; Biochemical engineering; Information retrieval; Biochemistry; Chromatography; Biology; Engineering","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":[0.0001149926,0.0001782018,0.0002086906,0.00005391901,0.0006098859,0.0001227203,0.0009477271,0.0002682467,0.00003293835],"category_scores_gemma":[0.0002001958,0.0001841584,0.000102663,0.0002465684,0.0001645264,0.0001640166,0.000350066,0.0008225875,0.000001129941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002838168,"about_ca_system_score_gemma":0.00006427101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002506132,"about_ca_topic_score_gemma":0.000004877915,"domain_scores_codex":[0.9990061,0.00001768302,0.0002614455,0.0003504995,0.0001091366,0.00025512],"domain_scores_gemma":[0.9982625,0.0004169224,0.0001153339,0.000980705,0.0001152689,0.0001092956],"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":[0.00007268068,0.0001030318,0.000353025,0.0005607538,0.00005200655,2.499233e-7,0.0002828403,0.00002125069,0.8273685,0.1675299,0.001270381,0.002385336],"study_design_scores_gemma":[0.0006708335,0.0001236351,0.00005104542,0.000239073,0.00004875362,0.000005337707,0.0001726111,0.02312744,0.6450935,0.02994617,0.3000315,0.0004901758],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06301852,0.00937965,0.833869,0.07258842,0.00003067004,0.009694959,0.002908992,0.001899847,0.006609905],"genre_scores_gemma":[0.4432762,0.0001281161,0.553384,0.0001834796,0.0001202984,0.00241287,0.0003173684,0.00004299817,0.0001346839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3802576,"threshold_uncertainty_score":0.7509762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02699835108265377,"score_gpt":0.3093610783249551,"score_spread":0.2823627272423013,"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."}}