{"id":"W4412867617","doi":"10.1101/2025.08.02.668292","title":"spOT-NMF: Optimal Transport-Based Matrix Factorization for Accurate Deconvolution of 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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Non-negative matrix factorization; Deconvolution; Matrix decomposition; Computer science; Factorization; Matrix (chemical analysis); Artificial intelligence; Pattern recognition (psychology); Algorithm; Physics; Chemistry; Chromatography","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":[0.0003489084,0.0006007061,0.0006473846,0.0002209185,0.0001264955,0.00005255241,0.0005412946,0.001055603,0.00001251224],"category_scores_gemma":[0.00009291555,0.0007036596,0.0004820223,0.0001996604,0.0001304003,0.00001362879,0.00005559227,0.0003376707,0.000001355041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001073615,"about_ca_system_score_gemma":0.001215541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001412433,"about_ca_topic_score_gemma":0.00003111983,"domain_scores_codex":[0.9973557,0.00008637486,0.0008398501,0.0009906986,0.0002431881,0.0004841715],"domain_scores_gemma":[0.9978141,0.00003339197,0.0004681393,0.0008469542,0.0006780722,0.0001593554],"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":[0.0006820664,0.0002384578,0.004893846,0.001078152,0.000202992,0.000002021177,0.00000819801,0.006077512,0.9866163,0.0001351437,0.00005725987,0.000008106293],"study_design_scores_gemma":[0.001861583,0.0002410475,0.008785622,0.0002457107,0.0003209748,6.881454e-9,0.000002055615,0.007548084,0.9758956,0.000001808347,0.004388167,0.0007092885],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.551841,0.0004835463,0.4433033,0.00004673554,0.00122278,0.0008747044,0.002162014,0.00006341495,0.000002594497],"genre_scores_gemma":[0.9869382,0.0002458809,0.01187055,0.00008836478,0.0004951139,0.0001871415,0.00005741581,0.0001023632,0.00001496969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4350972,"threshold_uncertainty_score":0.9995415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01413884929212865,"score_gpt":0.2376819570719974,"score_spread":0.2235431077798687,"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."}}