{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004207295,0.002986595,0.001827208,0.005088677,0.001738679,0.002736376,0.002924029,0.002301972,0.008158216],"category_scores_gemma":[0.01101264,0.001633003,0.003143136,0.002689891,0.001335473,0.004375802,0.003659938,0.00306618,0.005135271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00147317,"about_ca_system_score_gemma":0.001568803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001564353,"about_ca_topic_score_gemma":0.002087858,"domain_scores_codex":[0.9985678,0.0002842694,0.0000813797,0.000511301,0.0004482569,0.0001069012],"domain_scores_gemma":[0.996585,0.001926707,0.0005206239,0.0004405664,0.0003509668,0.0001761482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002794924,0.0003847,0.04913163,0.004484783,0.001878542,0.001110285,0.001799765,0.07408097,0.194145,0.02846188,0.09181368,0.5499139],"study_design_scores_gemma":[0.0003806118,0.0002835013,0.009875851,0.0002599107,0.00030463,0.0009772842,0.0002768083,0.8010766,0.06006608,0.07316389,0.05311031,0.0002245094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08293641,0.001537572,0.7845118,0.0008176015,0.0001832036,0.0003304679,0.009790567,0.116553,0.003339457],"genre_scores_gemma":[0.1267954,0.0006793109,0.845636,0.0004377906,0.000134216,0.0009340917,0.01418233,0.009819524,0.001381378],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008158216,"threshold_uncertainty_score":0.02729189,"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."}}