{"id":"W4387877566","doi":"10.1101/2023.10.22.563484","title":"Towards AI-designed genomes using a variational autoencoder","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Autoencoder; Genome; ENCODE; Binary number; Computer science; Set (abstract data type); Artificial intelligence; Computational biology; Theoretical computer science; Gene; Machine learning; Artificial neural network; Biology; Mathematics; Genetics","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":[0.000794356,0.000784985,0.0005565966,0.0003255333,0.0002488666,0.0006068266,0.0009219957,0.001339091,0.0008842414],"category_scores_gemma":[0.001827088,0.0006037027,0.0006482546,0.0002252679,0.001043712,0.0007859403,0.0008140121,0.001482254,0.00030111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205009,"about_ca_system_score_gemma":0.001060309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007532665,"about_ca_topic_score_gemma":0.006899766,"domain_scores_codex":[0.9998312,0.00005450693,0.000006332863,0.000044525,0.00004288625,0.00002048844],"domain_scores_gemma":[0.9994826,0.0003181669,0.00004615369,0.00004085151,0.00008145286,0.00003074308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001524891,0.00001031159,0.0002044834,0.00001594318,0.00001268017,0.00001732208,0.00002600561,0.9824361,0.003184146,0.00541202,0.0001943601,0.008471421],"study_design_scores_gemma":[0.00000129424,0.000003230527,0.000009879118,0.000001025229,6.126808e-7,0.000001863688,0.000001210825,0.9983821,0.0003371881,0.001173191,0.00008757719,8.360213e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02384682,0.00009625649,0.9742125,0.0002329086,0.00002188142,0.00002359506,0.00003791049,0.0004260819,0.001102095],"genre_scores_gemma":[0.4498298,0.0001580956,0.5448322,0.0003335633,0.00003461704,0.0001530048,0.0002597493,0.0002636529,0.004135358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007532665,"threshold_uncertainty_score":0.01497763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0252349830042905,"score_gpt":0.2459607570344622,"score_spread":0.2207257740301717,"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."}}