{"id":"W4415814107","doi":"10.1038/s41467-025-65783-z","title":"AI-powered spatial cell phenomics enhances risk stratification in non-small cell lung cancer","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Berlin Center for Machine Learning; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; Berlin Institute of Health; Institute for Information and Communications Technology Promotion; Deutschen Konsortium für Translationale Krebsforschung; Korea University; Ministry of Science and ICT, South Korea","keywords":"Lung cancer; Risk stratification; Tumor microenvironment; Cell; Cancer; Immune system; Adenocarcinoma; Multiplex","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001591795,0.0001644615,0.0001501799,0.000084111,0.0001960586,0.00004630939,0.0008187344,0.0004325227,0.000008954129],"category_scores_gemma":[0.00003380092,0.0001762921,0.00007985497,0.0002171919,0.0000837385,0.000006701034,0.0001416194,0.0007379652,0.000002559912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005335733,"about_ca_system_score_gemma":0.0002401126,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009497398,"about_ca_topic_score_gemma":0.02562204,"domain_scores_codex":[0.9990187,0.0001226173,0.0002963412,0.0003054684,0.00006733397,0.0001894889],"domain_scores_gemma":[0.9984294,0.00004699742,0.0001293443,0.001216354,0.0001371774,0.00004078387],"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":[0.0000678459,0.0003892054,0.07429059,0.00006037572,0.00004030135,2.302544e-7,0.0002907959,0.000293164,0.9187414,0.0003986454,0.002229389,0.003198024],"study_design_scores_gemma":[0.002230541,0.0001024062,0.07631375,0.0001111823,0.0001863323,4.939884e-7,0.0003003946,0.01321553,0.8598807,0.0004644395,0.04651474,0.0006795123],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9479587,0.02683259,0.01075325,0.001740404,0.0006938453,0.0007066719,0.0001995331,0.00002939473,0.01108559],"genre_scores_gemma":[0.9872251,0.008477555,0.002747736,0.000570301,0.00007737371,0.0001024884,0.0003834003,0.00001778407,0.0003983092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05886076,"threshold_uncertainty_score":0.9921578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007726703493163719,"score_gpt":0.2736601388289378,"score_spread":0.2659334353357741,"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."}}