{"id":"W4411765463","doi":"10.1093/bib/bbaf303","title":"cfMethylPre: deep transfer learning enhances cancer detection based on circulating cell-free DNA methylation profiling","year":2025,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"Education Department of Shaanxi Province; National Natural Science Foundation of China","keywords":"Interpretability; DNA methylation; Methylation; Breast cancer; Computer science; Artificial intelligence; Cancer; Computational biology; Biomarker; Biomarker discovery; Cell-free fetal DNA; Machine learning; Biology; DNA; Gene; Genetics; Gene expression; Proteomics","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":[0.0008826518,0.001102238,0.0007199123,0.0004744742,0.0002167269,0.000570363,0.001291993,0.001102638,0.001545754],"category_scores_gemma":[0.002065196,0.0003148225,0.0007752436,0.0003505146,0.0004887324,0.0008613585,0.00104915,0.00145861,0.0005664582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005759553,"about_ca_system_score_gemma":0.0008878079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003781119,"about_ca_topic_score_gemma":0.004414546,"domain_scores_codex":[0.9997335,0.00006097369,0.000009857081,0.00009981442,0.00005156026,0.00004421507],"domain_scores_gemma":[0.9995812,0.000209402,0.00004499509,0.0000452302,0.00008674908,0.00003240037],"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":[0.0006347082,0.0004608887,0.01099685,0.0002411055,0.0002861407,0.0003594336,0.0001147052,0.5274409,0.03520578,0.003247997,0.01265216,0.4083594],"study_design_scores_gemma":[0.00001184968,0.00009903033,0.0004701559,0.000006624679,0.0000147959,0.00003175903,0.00000460501,0.9939367,0.003370665,0.001430929,0.0006139798,0.000008906203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1890662,0.002998578,0.7938362,0.001482708,0.0002755744,0.0001286458,0.001113049,0.007855957,0.003243156],"genre_scores_gemma":[0.8764327,0.0008497503,0.109759,0.001365755,0.0002181695,0.0002232223,0.002706102,0.0002348235,0.008210603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003781119,"threshold_uncertainty_score":0.007518232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007581417423562379,"score_gpt":0.2519956500859249,"score_spread":0.2444142326623625,"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."}}