{"id":"W4411080389","doi":"10.1101/2025.06.04.25328900","title":"PICASA: Decomposing patient heterogeneity of single-cell cancer data by cross-attention neural networks","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Provincial Health Services Authority; University of British Columbia","funders":"","keywords":"Artificial neural network; Cancer; Computer science; Artificial intelligence; Medicine; Internal medicine","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":[0.001784912,0.001142699,0.0008563991,0.001428194,0.0003558295,0.0009078882,0.001420951,0.0008640519,0.002329515],"category_scores_gemma":[0.004248856,0.0004638726,0.001456033,0.001109788,0.0005172143,0.0007614158,0.001426261,0.001608129,0.0006501603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009492963,"about_ca_system_score_gemma":0.000970313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0131648,"about_ca_topic_score_gemma":0.0155904,"domain_scores_codex":[0.9995015,0.000150274,0.00002413689,0.00019885,0.00007022558,0.00005505166],"domain_scores_gemma":[0.9987898,0.0006563162,0.000089881,0.0002094173,0.0001796272,0.0000749347],"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":[0.0007574199,0.0002406356,0.0314502,0.0002714667,0.0009323868,0.0006738753,0.0002941057,0.5865637,0.01492793,0.004242993,0.02189473,0.3377506],"study_design_scores_gemma":[0.00001574287,0.00003102964,0.002393339,0.000009101564,0.00003461521,0.00006358944,0.00002312838,0.9907343,0.001264187,0.004292174,0.001125036,0.00001385082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2065438,0.001873493,0.7718691,0.001495037,0.0002347124,0.0002391397,0.005326597,0.01007595,0.002342181],"genre_scores_gemma":[0.7801989,0.0004583239,0.1976567,0.001037046,0.0002559388,0.000330653,0.01566419,0.0008111232,0.003587068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0131648,"threshold_uncertainty_score":0.02617633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04876631529623932,"score_gpt":0.3191312585860868,"score_spread":0.2703649432898475,"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."}}