{"id":"W2968362167","doi":"10.1101/730481","title":"Augmenting protein network embeddings with sequence information","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Representation (politics); Computer science; Abstraction; Protein function prediction; Function (biology); Sequence (biology); Artificial intelligence; Task (project management); Simple (philosophy); Property (philosophy); Protein function; Key (lock); Machine learning; Natural language processing; Theoretical computer science; Computational biology; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006862042,0.0005509622,0.0003870332,0.0001136222,0.0001713567,0.0003317026,0.0006278965,0.0006244422,0.00001982525],"category_scores_gemma":[0.0002243735,0.0005369639,0.0001097474,0.0002522828,0.00009955943,0.00004641415,0.0007898482,0.0007936917,0.0001168041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001041866,"about_ca_system_score_gemma":0.0005764395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002478811,"about_ca_topic_score_gemma":0.000001678543,"domain_scores_codex":[0.9977356,0.00009000461,0.0005953239,0.0005336405,0.000412711,0.000632722],"domain_scores_gemma":[0.9971988,0.00001223466,0.0008862466,0.001289816,0.0004550864,0.0001578204],"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":[0.0002686723,0.0000895695,0.03698626,0.003137629,0.0006226672,0.0000153582,0.00005281354,0.06549672,0.8891165,0.000928249,0.003263918,0.00002162472],"study_design_scores_gemma":[0.003238463,0.001189006,0.04471383,0.004399559,0.0003849302,4.678e-7,0.00002611577,0.04543743,0.7017933,0.000005282773,0.1931722,0.005639466],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9676764,0.0002262366,0.02934053,0.0001028227,0.0005622102,0.001572829,0.00009890271,0.000225077,0.0001950071],"genre_scores_gemma":[0.9471125,0.00004336176,0.05163142,0.0003950707,0.000501795,0.0001879529,0.000009615785,0.00009183267,0.0000264243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1899083,"threshold_uncertainty_score":0.9997082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006772824951950272,"score_gpt":0.2123965605752332,"score_spread":0.205623735623283,"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."}}