{"id":"W4400325784","doi":"10.1101/2024.07.02.601790","title":"Spatial gene expression at single-cell resolution from histology using deep learning with GHIST","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Health and Medical Research Council; Innovation and Technology Commission; University of Sydney; University of Guelph","keywords":"Histology; Deep learning; Artificial intelligence; Computational biology; Gene; Biology; Computer science; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002288928,0.0007276068,0.000575753,0.000175933,0.0003206739,0.0001463513,0.0004527482,0.001150934,0.0000415374],"category_scores_gemma":[0.00006600444,0.0007432365,0.0002169272,0.0001697421,0.0002252095,0.000008605974,0.0008959029,0.0009568646,0.00003631257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004980028,"about_ca_system_score_gemma":0.0003777613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005268279,"about_ca_topic_score_gemma":0.0001019324,"domain_scores_codex":[0.9965776,0.0002371703,0.0005470047,0.001658019,0.0003434952,0.0006367548],"domain_scores_gemma":[0.9979994,0.00002606394,0.0004166023,0.001028652,0.0002769479,0.0002522864],"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":[0.00038429,0.000165204,0.005585412,0.0002149238,0.0001035897,0.00008644435,0.00001868665,0.001922245,0.9914151,0.000003625969,0.00009518661,0.000005286618],"study_design_scores_gemma":[0.0007644604,0.0002736776,0.001506447,0.0003310942,0.000262101,1.93692e-7,0.00000313608,0.003585873,0.9855084,0.000001536351,0.006831451,0.0009315855],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9592276,0.007804255,0.03044938,0.00003545646,0.001690397,0.0004053341,0.000167481,0.0001895576,0.00003060176],"genre_scores_gemma":[0.9805169,0.0002350333,0.01752012,0.00008461907,0.001264832,0.00005304582,0.0000218881,0.0002636392,0.00003992071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02128937,"threshold_uncertainty_score":0.9995019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361296325315766,"score_gpt":0.1974918315750944,"score_spread":0.1838788683219367,"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."}}