{"id":"W4365999366","doi":"10.1101/2023.04.13.536789","title":"The Power of Two: integrating deep diffusion models and variational autoencoders for single-cell transcriptomics analysis","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Embedding; Computer science; Scalability; Artificial intelligence; Semantics (computer science); Representation (politics); Deep learning; Generative model; Expression (computer science); Feature learning; Generative grammar; Theoretical computer science; Machine learning; Pattern recognition (psychology); Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006390014,0.0004323776,0.0004944883,0.0001845859,0.0002730206,0.0001573838,0.0004596095,0.0004732601,0.00000241067],"category_scores_gemma":[0.0001368677,0.0003838102,0.0004055247,0.0003403724,0.0001754087,0.00001177179,0.0001934677,0.0003099534,6.085601e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005924648,"about_ca_system_score_gemma":0.0002539041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008189149,"about_ca_topic_score_gemma":0.00006988548,"domain_scores_codex":[0.9977631,0.0001042995,0.0006397599,0.000824529,0.0002632908,0.0004050153],"domain_scores_gemma":[0.9981038,0.0001230606,0.0004066298,0.000739485,0.0004934676,0.000133581],"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":[0.0001122905,0.00013764,0.002011185,0.0001442899,0.0006222309,0.000001160122,0.00005095543,0.009610395,0.9864708,0.0008046728,0.00003089473,0.000003554029],"study_design_scores_gemma":[0.002413355,0.000397005,0.005494239,0.0001689665,0.001825293,2.627974e-8,0.00006380869,0.4030454,0.584347,0.0001667248,0.0007434515,0.00133468],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5840867,0.0009699559,0.4133351,0.00009864628,0.0005990815,0.0005135757,0.0003317117,0.00005498835,0.00001016282],"genre_scores_gemma":[0.9805064,0.0004345605,0.01858225,0.00007312774,0.000161849,0.0001139071,0.000009469776,0.0001064215,0.00001208134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4021237,"threshold_uncertainty_score":0.9998614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01939436193232641,"score_gpt":0.2242866045261597,"score_spread":0.2048922425938333,"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."}}