{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002322891,0.0002091428,0.0001964519,0.00003643999,0.0001277662,0.0001371744,0.0001816957,0.0001292588,0.0001097422],"category_scores_gemma":[0.0008306727,0.000207637,0.00006085936,0.000118993,0.00004236887,0.000009800011,0.0004192276,0.0003126245,0.00004917585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001549274,"about_ca_system_score_gemma":0.00007578169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004732027,"about_ca_topic_score_gemma":0.000005329493,"domain_scores_codex":[0.99861,0.0001519948,0.0003034358,0.000426393,0.0002144573,0.0002937848],"domain_scores_gemma":[0.9992104,0.00001708995,0.0001320796,0.0003365644,0.0001222208,0.0001816986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004570693,0.0003655942,0.04560076,0.0009958436,0.0001577162,0.0000168524,0.002129208,0.0008737925,0.6254632,0.0003657942,0.00402983,0.3195443],"study_design_scores_gemma":[0.001423141,0.0006246667,0.004115373,0.0004840041,0.00001761387,0.00001520742,0.000169927,0.004880822,0.1408153,0.0001702017,0.8467857,0.0004980848],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.938684,0.0004983468,0.01486524,0.0003544708,0.0001422734,0.04360462,0.00003605671,0.0001326999,0.001682285],"genre_scores_gemma":[0.7334429,0.0001315328,0.05110348,0.001037089,0.00158062,0.2049755,0.00231997,0.0002837708,0.005125082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8427559,"threshold_uncertainty_score":0.8467189,"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."}}