{"id":"W3157437194","doi":"10.1002/cpz1.113","title":"Learned Embeddings from Deep Learning to Visualize and Predict Protein Sets","year":2021,"lang":"en","type":"article","venue":"Current Protocols","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Workflow; Artificial intelligence; Pipeline (software); ENCODE; Classifier (UML); Protocol (science); Machine learning; Inference; Natural language processing; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007139348,0.001393491,0.0005751596,0.001434029,0.000428728,0.001676405,0.001623043,0.001057479,0.01053414],"category_scores_gemma":[0.003347323,0.0007552081,0.001050729,0.001178894,0.0005732384,0.002408264,0.001976218,0.002568513,0.00553411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191633,"about_ca_system_score_gemma":0.001176305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003472286,"about_ca_topic_score_gemma":0.006103168,"domain_scores_codex":[0.9995579,0.00008046791,0.00002886264,0.0001419482,0.0001429519,0.00004787166],"domain_scores_gemma":[0.9992213,0.0002591516,0.0000747583,0.0001869602,0.0002025011,0.00005523251],"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":[0.0004135763,0.0003484861,0.003618317,0.000655591,0.0001587293,0.0002833323,0.0002347306,0.2534106,0.0445236,0.04580276,0.07313441,0.5774159],"study_design_scores_gemma":[0.00002482113,0.00005734394,0.0004442754,0.00005436307,0.00001760961,0.00006367943,0.0000494412,0.9251221,0.02157043,0.03724796,0.01531694,0.00003102109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03358988,0.000866631,0.9234171,0.0008367017,0.0002698507,0.0001940244,0.007308989,0.02668626,0.006830618],"genre_scores_gemma":[0.2101495,0.001284682,0.7468584,0.0004410359,0.00006985745,0.0006188597,0.02615808,0.002953771,0.0114658],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01053414,"threshold_uncertainty_score":0.03524017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02184703544408889,"score_gpt":0.3633679176334731,"score_spread":0.3415208821893843,"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."}}