{"id":"W2021901733","doi":"10.1016/s1672-0229(07)60022-9","title":"FragAnchor: A Large-Scale Predictor of Glycosylphosphatidylinositol Anchors in Eukaryote Protein Sequences by Qualitative Scoring","year":2007,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":125,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Université du Québec à Montréal","funders":"National Center for Research Resources; National Institutes of Health","keywords":"Eukaryote; UniProt; Proteome; Computational biology; Hidden Markov model; Protein sequencing; Human proteome project; Computer science; Noise (video); Scale (ratio); Biology; Artificial intelligence; Proteomics; Bioinformatics; Machine learning; Pattern recognition (psychology); Genetics; Peptide sequence; Gene; Genome","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002643641,0.0004554936,0.000520987,0.000309382,0.0001431494,0.00006501823,0.0006951342,0.0004635383,0.00001342864],"category_scores_gemma":[0.0003522986,0.0004666939,0.000161749,0.0004648083,0.0002291156,0.0000618427,0.0003528618,0.000521903,0.00001815137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713998,"about_ca_system_score_gemma":0.0003010232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005418401,"about_ca_topic_score_gemma":0.0001538361,"domain_scores_codex":[0.9964401,0.00009051995,0.001807125,0.00035214,0.0004376876,0.0008724454],"domain_scores_gemma":[0.9978416,0.00005653072,0.001026636,0.0006537841,0.0002071098,0.0002143525],"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":[0.001301895,0.0005563817,0.02000463,0.001864291,0.0002874444,0.000008683857,0.06429885,0.002399663,0.9005675,0.001895712,0.001402692,0.005412253],"study_design_scores_gemma":[0.002901311,0.001002325,0.000842332,0.000302417,0.00003676283,0.00002565549,0.01205171,0.03370461,0.9393394,0.0006386949,0.008085943,0.00106881],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8401929,0.0003459692,0.155951,0.00004884595,0.0001552633,0.00164409,0.0003497473,0.00003502191,0.00127715],"genre_scores_gemma":[0.7004365,0.000161504,0.2981883,0.0002191739,0.0001407092,0.00007888321,0.0004610317,0.00006534826,0.0002485537],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1422373,"threshold_uncertainty_score":0.9997784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00645521733399634,"score_gpt":0.2699390928318512,"score_spread":0.2634838754978549,"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."}}