{"id":"W2770091706","doi":"10.1186/s12859-017-1906-3","title":"fLPS: Fast discovery of compositional biases for the protein universe","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computational biology; Contig; Asparagine; Biology; Residue (chemistry); Metagenomics; Sequence (biology); Amino acid; Computer science; Genetics; Biochemistry; Genome; Gene","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001625627,0.00008936567,0.00009402853,0.00001582463,0.0002924564,0.00007276968,0.0003630032,0.00007008628,0.000006791203],"category_scores_gemma":[0.0001781127,0.00006097151,0.0001062934,0.00001206717,0.0001337042,0.00002064138,0.0001468333,0.00002551942,0.000004228853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004544784,"about_ca_system_score_gemma":0.00007530065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008427681,"about_ca_topic_score_gemma":0.00001474262,"domain_scores_codex":[0.9995158,0.00001312712,0.0001812613,0.00007156754,0.000101814,0.0001164075],"domain_scores_gemma":[0.9991389,0.00004497914,0.0002453706,0.0004828653,0.00006459429,0.00002332463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005949045,0.0001244795,0.0003245072,0.0004294234,0.0001806194,5.418362e-7,0.0001934436,0.0005202792,0.9616267,0.01569411,0.002208085,0.0181029],"study_design_scores_gemma":[0.0007653137,0.0003182216,0.0007842364,0.0001127664,0.00004180453,0.000005881038,0.0006386644,0.0086922,0.9789454,0.0005416293,0.008959577,0.0001942485],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2035813,0.0001704373,0.7912169,0.0002469993,0.0002048406,0.001275297,0.0005257486,0.00001009725,0.002768359],"genre_scores_gemma":[0.8957244,0.00005454696,0.1021108,0.0000906751,0.0001821727,0.00008308074,0.000136905,0.00001578935,0.001601606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6921431,"threshold_uncertainty_score":0.2486346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0337259252113284,"score_gpt":0.2678833599472348,"score_spread":0.2341574347359064,"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."}}