{"id":"W2054353708","doi":"10.1021/ac8009017","title":"Sequential Interval Motif Search: Unrestricted Database Surveys of Global MS/MS Data Sets for Detection of Putative Post-Translational Modifications","year":2008,"lang":"en","type":"article","venue":"Analytical Chemistry","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ontario Genomics Institute; Genome Canada","keywords":"Database search engine; Proteome; Chemistry; Computational biology; False positive paradox; Tandem mass spectrometry; Sequence database; Search engine; Data mining; Computer science; Mass spectrometry; Information retrieval; Artificial intelligence; Biochemistry; Biology; Chromatography; Gene","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002453327,0.001011319,0.001168615,0.003261217,0.0004236565,0.0009571831,0.00134346,0.0005084482,0.001855453],"category_scores_gemma":[0.004008741,0.0002994005,0.0006852729,0.002945793,0.0003445783,0.001066685,0.001257762,0.0004635018,0.0006461266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003196171,"about_ca_system_score_gemma":0.001020545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008757121,"about_ca_topic_score_gemma":0.001820255,"domain_scores_codex":[0.9990286,0.0002186553,0.0001084435,0.0003350498,0.0002364997,0.00007269105],"domain_scores_gemma":[0.9987374,0.0006582871,0.0002061134,0.0001413518,0.0001638514,0.0000930613],"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":[0.002769309,0.0005531789,0.04112583,0.001006976,0.0004640546,0.0005532271,0.0005235677,0.03400753,0.2198414,0.004683669,0.006252114,0.6882192],"study_design_scores_gemma":[0.0001890836,0.001068359,0.01401962,0.00005320607,0.0001754832,0.001159504,0.0003803674,0.8475397,0.1185827,0.00788623,0.008860298,0.00008540141],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3912409,0.001390299,0.5879019,0.0001680344,0.00003204131,0.0003778539,0.004101919,0.01269246,0.002094542],"genre_scores_gemma":[0.4416024,0.000314867,0.55137,0.00007217547,0.00002092373,0.0002853945,0.005438793,0.0002921281,0.0006032886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003261217,"threshold_uncertainty_score":0.01297456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1054292874879158,"score_gpt":0.3714334196807012,"score_spread":0.2660041321927854,"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."}}