方法对比

	机器学习辅助全基因组关联分析	全基因组关联研究 (GWAS)
领域	生物信息学	生物信息学
方法族	Process / pipeline	Process / pipeline
起源年份	2015-2020 (active integration period)	2005–2007
提出者	Multiple groups; popularized through integrations such as Listgarten et al. (2012) and Novembre & Stephens (2008); ML augmentation formalized ~2015-2020	Klein et al. (age-related macular degeneration GWAS, 2005); landmark scale: Wellcome Trust Case Control Consortium (2007)
类型	Hybrid computational genomics pipeline	Observational genomic association study
开创性文献	Beam, A. L., & Kohane, I. S. (2018). Big data and machine learning in health care. JAMA, 319(13), 1317-1318.	Wellcome Trust Case Control Consortium. (2007). Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls. Nature, 447(7145), 661–678.
别名	ML-GWAS, machine learning GWAS, AI-assisted GWAS, deep learning GWAS	GWAS, genome-wide association analysis, whole-genome association study, WGAS
相关	3	6
摘要	Machine learning-assisted GWAS integrates classical genome-wide association testing with machine learning models to improve the detection of genetic variants associated with complex traits. Where traditional GWAS tests each single nucleotide polymorphism (SNP) independently using linear or logistic regression, ML-GWAS captures non-linear interactions and epistasis, ranks candidate loci more accurately, and reduces the false discovery burden in large biobank datasets. The approach has become increasingly prominent as sample sizes and genomic complexity outpace the assumptions of conventional single-SNP tests.	A genome-wide association study (GWAS) systematically tests hundreds of thousands to millions of single-nucleotide polymorphisms (SNPs) across the human genome for statistical association with a trait or disease. By comparing allele frequencies between cases and controls — or by regressing SNP genotypes on a quantitative phenotype — GWAS identifies genomic loci that harbor common genetic variants contributing to complex traits. Since its large-scale debut in 2007, GWAS has catalogued thousands of robust disease–variant associations across virtually every common human condition.