{"id":"W4409728131","doi":"10.1101/2025.04.12.648541","title":"DTractor enhances cell type deconvolution in spatial transcriptomics by integrating deep neural networks, transfer learning, and matrix factorization","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":"Mila - Quebec Artificial Intelligence Institute; McGill University; McGill University Health Centre","funders":"","keywords":"Deconvolution; Matrix decomposition; Transfer of learning; Computer science; Artificial intelligence; Non-negative matrix factorization; Artificial neural network; Matrix (chemical analysis); Type (biology); Deep neural networks; Factorization; Deep learning; Pattern recognition (psychology); Biological system; Chemistry; Algorithm; Biology; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001213877,0.001180484,0.0005967498,0.0006213084,0.0003431351,0.0006696781,0.001025898,0.0009573641,0.001625145],"category_scores_gemma":[0.002270166,0.0003410729,0.0007783815,0.0006413125,0.0008140912,0.001295497,0.001148349,0.001656518,0.0008686565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008694117,"about_ca_system_score_gemma":0.001252943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006311971,"about_ca_topic_score_gemma":0.009552296,"domain_scores_codex":[0.9996297,0.00007889709,0.00001333532,0.0001240578,0.0001105581,0.0000433744],"domain_scores_gemma":[0.9991974,0.0002793576,0.00009530352,0.0001489086,0.0002126567,0.00006643671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002625393,0.0002805213,0.002959687,0.0001754186,0.0001877823,0.0002453634,0.000155294,0.5652726,0.1618435,0.01276794,0.01081303,0.2450363],"study_design_scores_gemma":[0.000003379635,0.00001858576,0.0002248151,0.000002668768,0.000005497798,0.00002325144,0.000004791864,0.9902869,0.007049245,0.001738342,0.0006350743,0.000007377453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05608839,0.0003433375,0.9373956,0.0003491154,0.00007361126,0.00003502624,0.0003071342,0.003789003,0.00161884],"genre_scores_gemma":[0.41173,0.0003728674,0.5797041,0.0004373931,0.0001062348,0.000129815,0.001657729,0.0006730563,0.005188745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006311971,"threshold_uncertainty_score":0.01255047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006257840894683931,"score_gpt":0.2139862351602072,"score_spread":0.2077283942655233,"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."}}