{"id":"W4413429628","doi":"10.1016/j.compbiomed.2025.110971","title":"Deep learning-based feature discovery for decoding phenotypic plasticity in pediatric high-grade gliomas single-cell transcriptomics","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Feature (linguistics); Phenotype; Transcriptome; Computer science; Decoding methods; Computational biology; Feature selection; Artificial intelligence; Deep learning; Biology; Genetics; Gene; Gene expression; Algorithm","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":[0.0003977174,0.0004711652,0.0005057729,0.0005740427,0.0001900401,0.0005304574,0.000396769,0.0004775069,0.0006319901],"category_scores_gemma":[0.001152628,0.0001601293,0.0005354681,0.0007179904,0.00017704,0.0003221698,0.0004018527,0.0006941762,0.0002700828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000372289,"about_ca_system_score_gemma":0.0004893153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003756691,"about_ca_topic_score_gemma":0.007202904,"domain_scores_codex":[0.9998437,0.0000277044,0.000008916941,0.00005154288,0.00002675826,0.00004135308],"domain_scores_gemma":[0.9997279,0.0001417643,0.00003551643,0.00001917519,0.00005824918,0.0000173084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001042374,0.0003291323,0.06617992,0.0005219892,0.000448108,0.0006825507,0.0002343519,0.13549,0.2221451,0.003225282,0.01280948,0.5568916],"study_design_scores_gemma":[0.00003084458,0.0001534018,0.03593519,0.00004353293,0.0001338846,0.0002813539,0.0001341331,0.9083815,0.04545754,0.005782173,0.0036227,0.00004372867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7383676,0.003720573,0.2436288,0.0009474602,0.0001124452,0.00005745467,0.008866407,0.002318414,0.001980826],"genre_scores_gemma":[0.9550803,0.0006861144,0.03749013,0.0001312851,0.00003726788,0.00008123009,0.005047731,0.00008499205,0.001360998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003756691,"threshold_uncertainty_score":0.007469654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0139689130825631,"score_gpt":0.2748283824705908,"score_spread":0.2608594693880277,"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."}}