{"id":"W4378620043","doi":"10.1007/s12539-023-00563-1","title":"A Self-attention Graph Convolutional Network for Precision Multi-tumor Early Diagnostics with DNA Methylation Data","year":2023,"lang":"en","type":"article","venue":"Interdisciplinary Sciences Computational Life Sciences","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Methylation; DNA methylation; Computer science; Graph; Support vector machine; Computational biology; Artificial intelligence; Biology; DNA; Gene; Theoretical computer science; Genetics; Gene expression","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":[0.0005601464,0.001003654,0.0007585837,0.0008874573,0.000443086,0.0005258308,0.001691042,0.001235134,0.002439242],"category_scores_gemma":[0.0009948262,0.000552795,0.0008046037,0.000711003,0.0003392563,0.0007885754,0.001080462,0.00109724,0.0008055319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001019272,"about_ca_system_score_gemma":0.001358502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0278636,"about_ca_topic_score_gemma":0.04071879,"domain_scores_codex":[0.9997664,0.00002962696,0.000008538378,0.00009636909,0.00004642636,0.00005249149],"domain_scores_gemma":[0.9996719,0.0001143313,0.00002369831,0.0000574497,0.0001024134,0.00003022269],"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":[0.0004655269,0.0002833125,0.004328585,0.0001514804,0.0003546472,0.0003168149,0.00007935909,0.394845,0.0271939,0.005968803,0.01539725,0.5506153],"study_design_scores_gemma":[0.000006045482,0.00002163705,0.000327239,0.000003717583,0.00002409149,0.00002464117,0.000002998433,0.9951422,0.002474643,0.001439736,0.0005273672,0.000005829873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07418084,0.00140683,0.9097929,0.0008484536,0.0002383704,0.0001095362,0.001392686,0.00877323,0.00325711],"genre_scores_gemma":[0.7415758,0.0006635818,0.238375,0.0007087277,0.0001522297,0.0001306893,0.003727312,0.0003531546,0.01431356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0278636,"threshold_uncertainty_score":0.05540282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05498759351114664,"score_gpt":0.3538988063091896,"score_spread":0.298911212798043,"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."}}