{"id":"W4390605283","doi":"10.1038/s41598-023-50991-8","title":"Optimizing strategy for the discovery of compositionally-biased or low-complexity regions in proteins","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Set (abstract data type); Relevance (law); Parsing; Boundary (topology); Artificial intelligence; Sequence (biology); Cover (algebra); Algorithm; Computational biology; Pattern recognition (psychology); Biology; Mathematics; Genetics","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":[0.002094856,0.001196904,0.0008756841,0.001179328,0.000506304,0.0008641013,0.000922791,0.0007886385,0.0006946881],"category_scores_gemma":[0.005006905,0.0006362073,0.0008070085,0.0008522438,0.0007534074,0.001161573,0.001262759,0.0009083923,0.000488902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008071958,"about_ca_system_score_gemma":0.001202167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001334429,"about_ca_topic_score_gemma":0.002710301,"domain_scores_codex":[0.9991733,0.0002541116,0.00006554212,0.0002331753,0.0001909014,0.00008288446],"domain_scores_gemma":[0.9983552,0.0008371848,0.0002544495,0.0002231579,0.0002480879,0.00008187681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008010413,0.0004463665,0.01369042,0.0005301102,0.000179668,0.0003540243,0.0006329882,0.1794164,0.5804152,0.007173486,0.00103474,0.2153256],"study_design_scores_gemma":[0.00004819845,0.0002885227,0.00312669,0.00003095767,0.0001018908,0.0002196198,0.0001455455,0.8454545,0.1429889,0.005801138,0.00174794,0.00004617331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1772707,0.0002150229,0.8194404,0.00008528448,0.000006186683,0.000154423,0.0001330183,0.001890881,0.00080403],"genre_scores_gemma":[0.2955497,0.0001715039,0.7024411,0.0000737871,0.000006596856,0.0002891955,0.0004755333,0.0005214217,0.0004710651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002094856,"threshold_uncertainty_score":0.01107877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04840443691522524,"score_gpt":0.2960674806376974,"score_spread":0.2476630437224722,"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."}}