{"id":"W4407272669","doi":"10.1101/2025.02.05.636714","title":"scGPT-spatial: Continual Pretraining of Single-Cell Foundation Model for Spatial Transcriptomics","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Foundation (evidence); Computer science; Transcriptome; Artificial intelligence; Geography; Biology; Gene expression; Genetics; Archaeology","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":[0.0005424923,0.0007006488,0.0007932138,0.0002271366,0.0001567967,0.0001268532,0.0007027261,0.001131984,0.000008493288],"category_scores_gemma":[0.0002047395,0.000844365,0.0004783569,0.0001687507,0.0001991999,0.00001631704,0.0002142066,0.0004470489,0.000001763072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167898,"about_ca_system_score_gemma":0.001135354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001582321,"about_ca_topic_score_gemma":0.0000765352,"domain_scores_codex":[0.9967673,0.0001093687,0.0009747117,0.001222802,0.0003169232,0.0006088934],"domain_scores_gemma":[0.9972241,0.00005177611,0.0006106341,0.001064801,0.0008666173,0.0001820727],"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":[0.0004303389,0.000389236,0.0007788124,0.0008926656,0.000208018,0.000001268331,0.00004754575,0.003036489,0.9938906,0.0001092187,0.0001436157,0.00007213784],"study_design_scores_gemma":[0.002004945,0.0003240504,0.0004552084,0.0003129235,0.0003015795,9.431195e-9,0.000004358003,0.07917396,0.9142399,0.000006996795,0.002355938,0.0008201291],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4599101,0.0004283188,0.5361903,0.00004552664,0.001182992,0.001083355,0.001038067,0.00008243196,0.00003888995],"genre_scores_gemma":[0.9760329,0.0001688235,0.02255658,0.0001854941,0.0005995042,0.0002215679,0.00002678458,0.0001483122,0.00006010384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5161227,"threshold_uncertainty_score":0.9994007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02211071630333974,"score_gpt":0.2303110830226678,"score_spread":0.208200366719328,"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."}}