{"id":"W4281773586","doi":"10.1038/s41598-022-12843-9","title":"Flexible protein database based on amino acid k-mers","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre hospitalier de l'Université Laval; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Computer science; Identification (biology); Computational biology; Database; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009639384,0.0007132347,0.001303334,0.002897517,0.0006596508,0.001757709,0.001678004,0.000599497,0.003271057],"category_scores_gemma":[0.002552925,0.0004390834,0.0006110604,0.00386917,0.0003884379,0.002753217,0.001777182,0.0009095619,0.003369551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004236026,"about_ca_system_score_gemma":0.000677911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006683609,"about_ca_topic_score_gemma":0.0006273558,"domain_scores_codex":[0.9991533,0.00009106471,0.0001764087,0.0002821464,0.0002328197,0.00006428343],"domain_scores_gemma":[0.9988357,0.0002059961,0.0001280338,0.0004623734,0.0002627526,0.0001051176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005811432,0.0003926368,0.006843135,0.001724509,0.0003389602,0.001786795,0.0006284164,0.0162357,0.2078318,0.05755695,0.06032766,0.6405221],"study_design_scores_gemma":[0.0006293606,0.0009259732,0.01145407,0.0004565057,0.0002638195,0.006854871,0.0004349885,0.2505783,0.2743266,0.09573717,0.3578427,0.0004957247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1142844,0.004892257,0.7602345,0.0004490872,0.000331278,0.0004077016,0.03402697,0.0740215,0.01135227],"genre_scores_gemma":[0.2593409,0.002061272,0.6668938,0.0002765025,0.00008927198,0.0004575575,0.06301641,0.001953307,0.005910918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003271057,"threshold_uncertainty_score":0.01094276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01900280278097792,"score_gpt":0.2464431968589034,"score_spread":0.2274403940779255,"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."}}