{"id":"W4400966344","doi":"10.1101/2024.07.22.604688","title":"Boosting the Predictive Power of Protein Representations with a Corpus of Text Annotations","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"UniProt; Computer science; Boosting (machine learning); Artificial intelligence; Machine learning; Predictive power; Protein sequencing; Context (archaeology); Natural language processing; Biology; Peptide sequence; Genetics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002792083,0.001437906,0.0009231889,0.001603564,0.0003334135,0.001264087,0.001124932,0.001358183,0.001597978],"category_scores_gemma":[0.01118715,0.0004688062,0.0007201182,0.001198916,0.0006730555,0.002802102,0.001192037,0.002195281,0.001256601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006666941,"about_ca_system_score_gemma":0.0006189428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005400972,"about_ca_topic_score_gemma":0.005698356,"domain_scores_codex":[0.9992892,0.0002954939,0.00003204925,0.0002124362,0.0001032364,0.00006752273],"domain_scores_gemma":[0.9914791,0.006519695,0.0004240567,0.0008633803,0.0005263845,0.0001873318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001828524,0.0009718579,0.01689473,0.0004301564,0.0003315203,0.0003541263,0.0002117994,0.6360245,0.02194951,0.00256133,0.02271792,0.295724],"study_design_scores_gemma":[0.00001835132,0.00004677726,0.0005858017,0.00001165523,0.00001858513,0.00001428829,0.00001394974,0.9950376,0.002377769,0.001477523,0.0003885451,0.000009118701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8439073,0.002814741,0.127903,0.003439367,0.0004503696,0.0001049488,0.004466681,0.01164922,0.005264236],"genre_scores_gemma":[0.9523357,0.0005885966,0.0372173,0.0004819082,0.0002317237,0.00008196995,0.006539782,0.0002909531,0.002232165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005400972,"threshold_uncertainty_score":0.01476616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009236484526108094,"score_gpt":0.2222772359455744,"score_spread":0.2130407514194663,"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."}}