{"id":"W4367602258","doi":"10.1101/2023.04.30.538439","title":"scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI","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":175,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Generative grammar; Inference; Synthetic biology; Computer science; Transformer; Systems biology; Artificial intelligence; Generative model; Codebase; Annotation; Computational biology; Biology; Software; Engineering; 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":[0.0005352391,0.0007427951,0.0006110782,0.0002263342,0.0003339569,0.0003514415,0.0005909919,0.00101699,0.000002805567],"category_scores_gemma":[0.0002051092,0.0008759835,0.0003793648,0.0002363501,0.0001337116,0.00002295024,0.0004535477,0.000500521,0.000008039124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003099082,"about_ca_system_score_gemma":0.001103676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008049155,"about_ca_topic_score_gemma":0.00001618596,"domain_scores_codex":[0.9967304,0.00009624502,0.0006825951,0.001484448,0.0002823942,0.0007238534],"domain_scores_gemma":[0.9974951,0.00002386504,0.0004348044,0.001006153,0.0008036583,0.0002364927],"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":[0.0001116762,0.0002395976,0.0003097068,0.0003540572,0.0001565528,0.000004975249,0.00001960795,0.03608451,0.9625523,0.00006732268,0.00009418645,0.000005481518],"study_design_scores_gemma":[0.0008590381,0.0000943798,0.0000953567,0.0001046652,0.000135024,2.162275e-8,0.000002319468,0.3561772,0.6413161,0.00000634238,0.0005013194,0.0007082432],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4747638,0.0002866105,0.5223972,0.00007514066,0.001137033,0.0008064992,0.0004024384,0.0001296914,0.000001594524],"genre_scores_gemma":[0.823835,0.0001679254,0.174106,0.0003840744,0.0009317252,0.0002124211,0.00001587407,0.0003142586,0.00003275861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3490711,"threshold_uncertainty_score":0.9993691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06310696845906083,"score_gpt":0.2756270159142196,"score_spread":0.2125200474551587,"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."}}