{"id":"W4290660596","doi":"10.1089/cmb.2021.0520","title":"Computing Maximal Covers for Protein Sequences","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Substring; Cover (algebra); String (physics); Context (archaeology); Computer science; Software; Fragment (logic); Sequence (biology); Theoretical computer science; Biology; Algorithm; Mathematics; Data structure; Genetics; Programming language; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0006242758,0.000075614,0.0001714663,0.0001361079,0.000302324,0.00004265044,0.0007093785,0.0000236593,0.00002240028],"category_scores_gemma":[0.00004672093,0.00006359294,0.0000932617,0.000160175,0.00004116771,0.0002245748,0.0003167914,0.0001693732,0.000001611845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006204817,"about_ca_system_score_gemma":0.0002603124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000408815,"about_ca_topic_score_gemma":1.184934e-7,"domain_scores_codex":[0.9989678,0.0001355876,0.0003652527,0.0001487871,0.0002295903,0.000153038],"domain_scores_gemma":[0.9989319,0.0002563419,0.0004584695,0.00008381608,0.0002180528,0.0000514559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002003409,0.0002264814,0.0005042335,0.00001800048,0.0001132532,0.00005307166,0.0003982095,0.5733098,0.01118076,0.3048569,0.00604945,0.1030894],"study_design_scores_gemma":[0.001590572,0.002073531,0.001281607,0.00002084256,0.00000850283,0.0007830663,0.0001032333,0.5945138,0.0005925374,0.3534278,0.04537496,0.0002295302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09282789,0.0001375143,0.904765,0.001434434,0.0006163672,0.000124065,0.00002960513,0.00001546229,0.00004970917],"genre_scores_gemma":[0.7099292,8.386011e-7,0.2895608,0.0003286604,0.0001404213,0.000004462737,0.0000176459,0.000003082755,0.0000148711],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6171013,"threshold_uncertainty_score":0.2593245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0211608068130309,"score_gpt":0.2910424347732892,"score_spread":0.2698816279602583,"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."}}