{"id":"W7117233846","doi":"10.1136/jitc-2025-012235","title":"AstroID resource: a scalable, relational database structure for longitudinal biomarker discovery","year":2025,"lang":"en","type":"article","venue":"Journal for ImmunoTherapy of Cancer","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Genentech; National Cancer Institute; National Institutes of Health; Bloomberg~Kimmel Institute for Cancer Immunotherapy, Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University; Moderna; Johns Hopkins University; Division of Cancer Prevention, National Cancer Institute; Mark Foundation For Cancer Research; Regeneron Pharmaceuticals; Melanoma Research Alliance; Bristol-Myers Squibb","keywords":"Relational database; Biomarker discovery; Longitudinal data; Biomarker; Relational model; Patient data","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":[0.01531336,0.00129489,0.001479525,0.006597877,0.001729879,0.007541796,0.006106255,0.001215556,0.01442898],"category_scores_gemma":[0.04217257,0.001632311,0.001835788,0.007651671,0.001247103,0.01023596,0.008813336,0.002450712,0.009663949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002513684,"about_ca_system_score_gemma":0.007548759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0109615,"about_ca_topic_score_gemma":0.01073198,"domain_scores_codex":[0.991765,0.001686578,0.001785855,0.001687495,0.002714861,0.0003602631],"domain_scores_gemma":[0.9758475,0.006989921,0.001955576,0.00910366,0.004365386,0.001737841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001440069,0.0003842321,0.01990043,0.00216957,0.0004508858,0.001002687,0.002428139,0.01719878,0.01321025,0.1213617,0.5244293,0.2960239],"study_design_scores_gemma":[0.0006492342,0.0004391524,0.007128107,0.0006460517,0.0002669177,0.00135432,0.00147974,0.1113347,0.02210553,0.09216182,0.7619611,0.0004733292],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.009078981,0.001091065,0.7246112,0.003076148,0.0004167405,0.002090374,0.122957,0.1246864,0.01199205],"genre_scores_gemma":[0.06878328,0.001171528,0.6566834,0.001317874,0.0002051999,0.001869823,0.2564811,0.008177726,0.005309911],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01531336,"threshold_uncertainty_score":0.08098572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01237569453298951,"score_gpt":0.3308527826646038,"score_spread":0.3184770881316143,"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."}}