Σύγκριση μεθόδων

	Μελέτη Συσχέτισης Επιγονιδιώματος (ML-EWAS) με Υποβοήθηση Μηχανικής Μάθησης	Παλινδρόμηση Lasso
Πεδίο	Βιοπληροφορική	Μηχανική Μάθηση
Οικογένεια	Process / pipeline	Machine learning
Έτος προέλευσης	2010s (methodological consolidation ~2015–2020)	1996
Δημιουργός	Teschendorff, Relton, and others in the epigenomics field	Tibshirani, R.
Τύπος	Integrative omics analysis pipeline	Regularized linear regression (L1 penalty)
Θεμελιώδης πηγή	Teschendorff, A. E., & Relton, C. L. (2018). Statistical and integrative system-level analysis of DNA methylation data. Nature Reviews Genetics, 19(3), 129–147.	Tibshirani, R. (1996). Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288.
Εναλλακτικές ονομασίες	ML-EWAS, machine learning EWAS, ML-assisted EWAS, epigenome-wide association study with machine learning	LASSO Regresyonu, lasso, L1-regularized regression, L1 regularization
Συναφείς	3	4
Σύνοψη	Machine learning-assisted EWAS integrates conventional epigenome-wide association testing with machine learning models to identify DNA methylation sites associated with a phenotype of interest. By combining the statistical rigour of EWAS with the pattern-recognition power of algorithms such as elastic net, random forest, or gradient boosting, this approach handles the extreme dimensionality of methylation arrays (450,000–850,000 CpG sites) more effectively than univariate testing alone, and can capture non-linear and interaction effects that standard linear models miss.	Lasso regression, introduced by Robert Tibshirani in 1996, is a linear regression method that adds an L1 penalty to the loss so that it shrinks coefficients and performs variable selection at the same time, producing a sparse model. By driving some coefficients exactly to zero it keeps only the predictors that matter.