{"id":"W4221051133","doi":"10.1101/2022.02.11.480173","title":"A Self-attention Graph Convolutional Network for Precision Multi-tumour Early Diagnostics with DNA Methylation Data","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Methylation; DNA methylation; Computer science; Computational biology; Graph; Artificial intelligence; Biology; DNA; Gene; Gene expression; Genetics; Theoretical computer science","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":[0.0007071654,0.001078274,0.0006759244,0.0008548574,0.0003256518,0.000467035,0.00147984,0.001145981,0.001716679],"category_scores_gemma":[0.001098939,0.0004925632,0.0007239114,0.0005592225,0.0003731032,0.0007413604,0.0007767873,0.001038166,0.0004749013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001301565,"about_ca_system_score_gemma":0.001140139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01766041,"about_ca_topic_score_gemma":0.01848252,"domain_scores_codex":[0.9997596,0.00003697671,0.00000888131,0.00009093403,0.00004411303,0.00005938446],"domain_scores_gemma":[0.9996157,0.0001474345,0.0000343268,0.00005294765,0.000117426,0.0000321794],"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":[0.0003039929,0.0002764719,0.003738145,0.0001029645,0.0001998208,0.0002063407,0.00006164505,0.6899022,0.02154787,0.002975322,0.005239155,0.275446],"study_design_scores_gemma":[0.000002695113,0.00001246639,0.00014027,0.000001724777,0.000007337704,0.000006608151,0.000001285464,0.9977209,0.001595318,0.000397582,0.0001114053,0.000002414722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1608332,0.0009510276,0.8266302,0.0006727217,0.0001407672,0.0001189199,0.0006755305,0.007387941,0.00258979],"genre_scores_gemma":[0.8423995,0.0002639279,0.1501498,0.0003459768,0.00004902204,0.0001134802,0.001327908,0.0001620169,0.005188345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01766041,"threshold_uncertainty_score":0.03511524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01895065798155142,"score_gpt":0.2440239124695322,"score_spread":0.2250732544879808,"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."}}