{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001874756,0.0009358685,0.001096077,0.001307448,0.0005488296,0.001730989,0.002487775,0.001361539,0.00363526],"category_scores_gemma":[0.005896997,0.0009127133,0.002424357,0.001573455,0.001540945,0.001858258,0.002559287,0.002921978,0.001912915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001433594,"about_ca_system_score_gemma":0.002176736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007520764,"about_ca_topic_score_gemma":0.01038392,"domain_scores_codex":[0.9995437,0.0001330251,0.00002336202,0.0001355011,0.0001141556,0.00005017214],"domain_scores_gemma":[0.9977119,0.001458203,0.0000941976,0.0003592319,0.0002647648,0.0001117663],"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":[0.00008027846,0.00004358209,0.002300714,0.0001543627,0.0001507111,0.0001952133,0.0001373786,0.8855478,0.004144426,0.04743947,0.007687679,0.05211841],"study_design_scores_gemma":[0.000004162333,0.00000530641,0.00005584542,0.000005963546,0.000006079873,0.00001629646,0.000005502795,0.9789053,0.0004061535,0.01966561,0.0009199919,0.000003694078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006824202,0.0001567239,0.9873629,0.0002874235,0.00004217752,0.00004401712,0.0007738477,0.003288597,0.001220172],"genre_scores_gemma":[0.3669571,0.0006882772,0.6132713,0.001027051,0.0001432014,0.0007022942,0.009290703,0.002176919,0.00574319],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007520764,"threshold_uncertainty_score":0.01495397,"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."}}