{"id":"W4410934547","doi":"10.1101/2025.05.29.656851","title":"Automated registration of spatial expression data scales multimodal integration to large cohorts","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; Vector Institute; Lunenfeld-Tanenbaum Research Institute; Ontario Institute for Cancer Research; Institute of Cancer Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Benchmarking; Computer science; Artificial intelligence; Protein expression; Modalities; Spatial analysis; Image registration; Data integration; Data mining; Pattern recognition (psychology); Remote sensing; Geography; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007698761,0.001530986,0.002064049,0.002793604,0.0009518036,0.002629691,0.002448401,0.001679233,0.003882436],"category_scores_gemma":[0.01409845,0.0009838364,0.002608913,0.00354948,0.001033971,0.001453555,0.004410293,0.002295159,0.003685949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231091,"about_ca_system_score_gemma":0.002625604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004757565,"about_ca_topic_score_gemma":0.00811832,"domain_scores_codex":[0.9938695,0.001375176,0.0004155404,0.002889356,0.001091601,0.0003588692],"domain_scores_gemma":[0.9946533,0.00147275,0.0006162425,0.002292213,0.0007947211,0.000170753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001815982,0.0005859765,0.0875581,0.00112735,0.001927546,0.0007391243,0.0008791961,0.07051625,0.2144707,0.01015296,0.05388534,0.5563415],"study_design_scores_gemma":[0.0002616573,0.000458998,0.1281484,0.0002114148,0.0008810156,0.002189211,0.0008805579,0.5268605,0.1784161,0.06238998,0.09895802,0.0003440745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1390371,0.00197853,0.8232604,0.001122204,0.0002817869,0.0004586531,0.01723897,0.01253909,0.004083425],"genre_scores_gemma":[0.4290249,0.001194654,0.4943863,0.0009260848,0.0002942582,0.001636942,0.06243325,0.00425169,0.005851864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007698761,"threshold_uncertainty_score":0.0407154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01151352576953203,"score_gpt":0.2739178708211886,"score_spread":0.2624043450516566,"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."}}