{"id":"W2118938750","doi":"10.1074/mcp.o111.014902","title":"De Novo Sequencing and Homology Searching","year":2011,"lang":"en","type":"article","venue":"Molecular & Cellular Proteomics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":187,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computational biology; Homology (biology); Computer science; DNA sequencing; Sequence database; Proteomics; Sequence (biology); Genome; Sequence analysis; Biology; Genetics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001911006,0.0001789481,0.0001623462,0.00005066185,0.0001497963,0.00003372084,0.0002519923,0.0001744678,0.0001146043],"category_scores_gemma":[0.00003388512,0.0002011469,0.00006266357,0.00008075648,0.0001259586,0.00006016604,0.0001838745,0.000391486,0.000009466946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001206772,"about_ca_system_score_gemma":0.00008130223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008842098,"about_ca_topic_score_gemma":0.000001814656,"domain_scores_codex":[0.998923,0.00002606432,0.0002073555,0.0003644776,0.00009329472,0.0003858032],"domain_scores_gemma":[0.9992837,0.00001327174,0.00008882869,0.0004433913,0.00003960328,0.0001312353],"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":[0.00001186866,0.00002119556,0.0003884964,0.00004894192,0.00001558473,0.0001185402,0.0003339554,0.00001707154,0.9816732,0.01623949,0.000001812302,0.001129806],"study_design_scores_gemma":[0.0001699067,0.00001964307,0.000007340808,0.00002255443,0.00001679223,0.0001559317,0.0000635196,0.0009629352,0.9578065,0.04018886,0.000370798,0.0002152289],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5953311,0.0001209445,0.3975903,0.00003469747,0.00000513338,0.0001775903,0.000005307983,0.0001088405,0.006625989],"genre_scores_gemma":[0.620721,0.00002929978,0.3787717,0.0001010233,0.00002256121,0.00016105,0.00001049569,0.00004012788,0.0001426624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0253899,"threshold_uncertainty_score":0.8202531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02146770040343689,"score_gpt":0.2430870829234059,"score_spread":0.221619382519969,"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."}}