RAMEN

RAMEN identifies genome-wide Variable Methylated Loci (VML) from microarray DNA methylation data and dissects genome-exposome contributions to these loci using machine learning and statistical techniques.

Key Features:

• VML Identification: Identifies genome-wide Variable Methylated Loci from microarray DNA methylation data.
• Gene-Environment Dissection: Determines whether genetic (G), environmental (E), additive (G+E), or interactive (GxE) models best explain DNA methylation variability at each VML using genomic and exposomic data.
• Machine Learning Integration: Employs machine learning and statistical techniques to dissect genome-exposome contributions to microarray Variably Methylated Loci.

Scientific Applications:

• Cord Blood Methylation Analysis: Analyzes cord blood samples to identify genetic variants as key contributors to DNA methylation variability, typically in additive and interactive combinations with environmental factors.
• Gene-Environment Catalogue Generation: Produces catalogues of Variably Methylated Loci and their gene-environment contributions for specific tissues such as cord blood.

Methodology:

RAMEN uses machine learning and statistical techniques to dissect genome-exposome contributions to microarray Variably Methylated Loci. The method evaluates genetic (G), environmental (E), additive (G+E), and interactive (GxE) models against DNA methylation variability at each identified VML.