{"id":"W3088687225","doi":"10.1073/pnas.2011795117","title":"Deep learning of immune cell differentiation","year":2020,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Division of Intramural Research, National Institute of Allergy and Infectious Diseases","keywords":"Chromatin; Computational biology; Enhancer; Deep learning; Sequence (biology); Biology; Massively parallel; Computer science; Artificial neural network; DNA sequencing; Sequence motif; Immune system; Artificial intelligence; DNA; Transcription factor; Gene; Genetics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002675751,0.0000476294,0.00008183341,0.00002523302,0.00005992701,0.000006884344,0.0003455835,0.00004682069,0.000004289891],"category_scores_gemma":[0.0002025815,0.00003237898,0.00006266062,0.0001831832,0.0001169592,0.00001575481,0.0001295461,0.00006303448,2.887933e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002349777,"about_ca_system_score_gemma":0.00000928912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.811459e-7,"about_ca_topic_score_gemma":3.532708e-9,"domain_scores_codex":[0.9993232,0.000002706867,0.0002457304,0.00008370542,0.0002843975,0.00006020956],"domain_scores_gemma":[0.9994527,0.000008063554,0.0003958402,0.000004245783,0.0001261988,0.0000129483],"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":[0.00001106567,0.0000138358,0.004207109,0.00007794236,0.000008068612,1.004204e-10,0.0001654974,0.0003870715,0.9932279,0.001607066,0.00003062442,0.000263838],"study_design_scores_gemma":[0.0001329371,0.00009242529,0.03224576,0.00001200809,0.000006549248,5.126372e-7,0.0003093293,0.00975736,0.9567747,0.0004776998,0.0001521614,0.00003857445],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952559,0.0003148192,0.00002796246,0.0005653151,0.000005236704,0.00006452349,0.000001685496,0.000001721702,0.003762821],"genre_scores_gemma":[0.9990128,0.00007183655,0.0007720566,0.00006320669,0.00002999908,0.000001627085,6.696857e-7,0.000002068323,0.00004573467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03645319,"threshold_uncertainty_score":0.1320376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02312079285389574,"score_gpt":0.247616875719808,"score_spread":0.2244960828659123,"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."}}