{"id":"W3116735265","doi":"10.1101/2020.12.22.423928","title":"Systematic detection of functional proteoform groups from bottom-up proteomic datasets","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"SystemsX.ch; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Proteome; Computational biology; Proteomics; Alternative splicing; Human proteome project; Context (archaeology); Genome; Bottom-up proteomics; Gene; Biology; Bioinformatics; Chemistry; Genetics; Tandem mass spectrometry; Mass spectrometry; Messenger RNA","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001939206,0.0009991813,0.0009734376,0.003891694,0.000622221,0.001702215,0.0006755898,0.0006298216,0.0005032223],"category_scores_gemma":[0.003534628,0.000418922,0.0008755745,0.002402877,0.0005748369,0.000967981,0.001742921,0.001229806,0.0005484968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003140081,"about_ca_system_score_gemma":0.0004737547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005028441,"about_ca_topic_score_gemma":0.0009777904,"domain_scores_codex":[0.9986278,0.0002246274,0.0001287933,0.000430246,0.0004702318,0.0001183647],"domain_scores_gemma":[0.9969482,0.0009331914,0.0004810994,0.0005683115,0.0008479385,0.0002212765],"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":[0.0005813788,0.0002082852,0.03332869,0.0007676184,0.0004453734,0.0005559928,0.0002069128,0.003844255,0.9085627,0.0008676868,0.002017194,0.04861384],"study_design_scores_gemma":[0.00008481328,0.0005028762,0.179833,0.0001430854,0.0006433413,0.001931635,0.0005775113,0.1745332,0.6152278,0.01036005,0.01589986,0.0002627963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7517043,0.002343911,0.2217955,0.0004981708,0.000153879,0.0004459074,0.01701232,0.004084263,0.001961716],"genre_scores_gemma":[0.610379,0.0008611737,0.3602745,0.0004567343,0.00009764037,0.0003621685,0.02656965,0.0004459344,0.000553064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.003891694,"threshold_uncertainty_score":0.01025563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0154156963784426,"score_gpt":0.2262551279158735,"score_spread":0.210839431537431,"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."}}