{"id":"W4392198237","doi":"10.1038/s41588-024-01664-3","title":"BANKSY unifies cell typing and tissue domain segmentation for scalable spatial omics data analysis","year":2024,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":224,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Graduiertenakademie, Technische Universität Dresden; National Research Foundation Singapore; National Medical Research Council; Medical Research Council; Agency for Science, Technology and Research; National Research Foundation","keywords":"Biology; Computational biology; Segmentation; Domain (mathematical analysis); Scalability; Spatial analysis; Evolutionary biology; Computer science; Artificial intelligence; Database; Remote sensing","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":[],"consensus_categories":[],"category_scores_codex":[0.0001739483,0.0001498808,0.0001438606,0.00008182957,0.00008598377,0.0001160499,0.0002192989,0.0003516566,0.000007615233],"category_scores_gemma":[0.00001720466,0.0001468254,0.00005562557,0.0001807956,0.00004575403,0.000006007851,0.0001037821,0.0001563782,0.000001665219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001204626,"about_ca_system_score_gemma":0.00005999194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002170538,"about_ca_topic_score_gemma":0.0002285543,"domain_scores_codex":[0.9990407,0.0000248359,0.0001700722,0.0004902416,0.00008891565,0.0001852257],"domain_scores_gemma":[0.9994245,0.00002326286,0.00003386497,0.0004046201,0.00005762926,0.0000561759],"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":[0.00008506262,0.00004083628,0.002986028,0.0002083606,0.0003561268,0.000002537595,0.0001284798,0.0005125813,0.9706299,0.00005622472,0.002448576,0.02254534],"study_design_scores_gemma":[0.0006431022,0.0002450735,0.001007541,0.00001801449,0.00079527,0.000005650645,0.0001119069,0.02421327,0.7818962,0.0004349415,0.1902346,0.0003944128],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7421647,0.02590967,0.2296885,0.000191831,0.0007429311,0.0003456666,0.0006673053,0.00002862992,0.0002607305],"genre_scores_gemma":[0.9586698,0.001600935,0.03529501,0.0001937027,0.000520488,0.000008424827,0.003185141,0.00003312761,0.0004933532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2165051,"threshold_uncertainty_score":0.5987368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296471587263343,"score_gpt":0.2770406330188843,"score_spread":0.2640759171462508,"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."}}