{"id":"W4318071523","doi":"10.1038/s41587-022-01624-4","title":"A universal deep-learning model for zinc finger design enables transcription factor reprogramming","year":2023,"lang":"en","type":"article","venue":"Nature Biotechnology","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pontifical Institute of Mediaeval Studies; University of Toronto","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; National Institutes of Health; Compute Canada; U.S. Department of Health and Human Services","keywords":"Zinc finger; Reprogramming; Computational biology; Transcription factor; Biology; Haploinsufficiency; Deep learning; Gene; Genetics; Computer science; Artificial intelligence; Phenotype","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":[0.0001462656,0.0001549207,0.000130571,0.000160326,0.0001035915,0.00001463694,0.0001819767,0.001230929,0.000003206469],"category_scores_gemma":[0.0001802444,0.0001602931,0.00009538589,0.0002248395,0.00004846422,0.000003406713,0.00005619287,0.0003800071,0.000003967501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001700629,"about_ca_system_score_gemma":0.00002776412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001863943,"about_ca_topic_score_gemma":0.00001248938,"domain_scores_codex":[0.9990133,0.00001780098,0.0001243426,0.0004220209,0.00007017133,0.0003523333],"domain_scores_gemma":[0.9996111,0.00002009522,0.00003734346,0.0002441047,0.00004875068,0.00003859497],"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":[0.00005854522,0.00001124105,0.00002450942,0.00002606277,0.00003833655,0.000002949135,0.00007473039,0.02404843,0.9445834,0.0003993907,0.0003943871,0.030338],"study_design_scores_gemma":[0.0005168203,0.000278536,0.00005878304,0.00001108839,0.00002337945,0.000009993194,0.0001493424,0.2062063,0.7277651,0.0002571464,0.06447185,0.0002516211],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1316723,0.001680869,0.865292,0.0005028166,0.0001881852,0.0003100843,0.0000109558,0.0003206963,0.00002213807],"genre_scores_gemma":[0.9704298,0.0004467801,0.0279625,0.0000492262,0.0001014939,0.00004341534,0.000106542,0.00003870656,0.0008215345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8387575,"threshold_uncertainty_score":0.9494054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01281029572412205,"score_gpt":0.2832129755429256,"score_spread":0.2704026798188035,"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."}}