{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001958311,0.0001500288,0.0001364872,0.0002820053,0.001285708,0.0005148029,0.0009603106,0.00002200517,0.000424921],"category_scores_gemma":[0.00006917872,0.0001348268,0.00007405443,0.001012343,0.00009575077,0.0005985201,0.001187716,0.0002280943,0.00005427702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009017529,"about_ca_system_score_gemma":0.0003239313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003198807,"about_ca_topic_score_gemma":0.000001262585,"domain_scores_codex":[0.9965379,0.0001145373,0.0003453641,0.00124664,0.001377571,0.0003779544],"domain_scores_gemma":[0.9966176,0.00002132561,0.0002479605,0.002879624,0.00006911741,0.0001643342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005972016,0.001488811,0.0007653617,0.0000755186,0.00002141032,0.00724486,0.0005703274,0.01347876,0.3978629,0.008341203,0.4640841,0.1060071],"study_design_scores_gemma":[0.000258591,0.0001680801,0.0001227862,0.0000421561,0.000004544408,0.0001690778,0.00003588862,0.206359,0.184481,0.003903604,0.6040567,0.0003984871],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04622656,0.0002148887,0.9100174,0.001577086,0.02749305,0.001647693,0.0001098792,0.001068925,0.01164448],"genre_scores_gemma":[0.9049445,3.713859e-7,0.07915201,0.0005726902,0.0001005798,0.0003348796,0.0005411716,0.00002593197,0.01432785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.858718,"threshold_uncertainty_score":0.9888755,"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."}}