{"id":"W4291033104","doi":"10.1016/j.compbiolchem.2022.107753","title":"PeSA 2.0: A software tool for peptide specificity analysis implementing positive and negative motifs and motif-based peptide scoring","year":2022,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Peptide; Computational biology; Sequence motif; Motif (music); Computer science; Bioinformatics; Biology; Biochemistry; DNA","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":[0.0002545037,0.0001527472,0.0001828473,0.00004209739,0.0004783168,0.00002945503,0.00008057371,0.00007443113,0.00003924155],"category_scores_gemma":[0.0001792193,0.0001643126,0.00006761124,0.00009332084,0.0001533262,0.000005130261,0.0002644698,0.0001464699,1.620922e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001856978,"about_ca_system_score_gemma":0.00004912943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080767,"about_ca_topic_score_gemma":0.000003333726,"domain_scores_codex":[0.9991052,0.00005058426,0.0002245835,0.0003475169,0.00007106365,0.0002010263],"domain_scores_gemma":[0.9993912,0.0002197478,0.0001541108,0.00009674645,0.00008445761,0.000053733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004492328,0.0001172315,0.8575354,0.0003983581,0.001415918,0.000004673373,0.0006583969,0.06183175,0.06893646,0.000473136,0.0004977629,0.007681659],"study_design_scores_gemma":[0.00647702,0.001189746,0.4999355,0.00005634809,0.001073125,0.0002148664,0.002410518,0.4039888,0.06700085,0.007139648,0.008579188,0.001934352],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9393763,0.0001895473,0.0596114,0.0001235051,0.00001687121,0.0001427842,0.0004033206,0.00001382413,0.0001224509],"genre_scores_gemma":[0.974153,0.000008797805,0.02330993,0.0002183207,0.00006795149,0.00004080789,0.002072212,0.000009423959,0.0001195784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3575999,"threshold_uncertainty_score":0.6700475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006541357027320561,"score_gpt":0.2623197141176653,"score_spread":0.2557783570903447,"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."}}