Supplementary materials for "Integration of public DNA methylation and expression networks via eQTMs improves prediction of functional gene–gene associations"

This repository contained supplementary materials in the study named: "Integration of public DNA methylation and expression networks via eQTMs improves prediction of functional gene–gene associations."

For extracting all files from the downloaded tar.gz file, the following commanda could be used:

tar -xf supplementary_materials.tar.gz 

The supplementary_materials/data diretcory contains the following sections:

eqtm_predictions: This contains the training and testing datasets for the eQTM prediction procedures

public_methylation_data_and_pca: This contains the harmonized public DNA methylation dataset and its first 100 PCA components

cca_data: This contains the CCA components for the public DNA methylation and gene expression datasets for the negative eQTMs, and the input datasets for the functional gene pair prediction analylsis.

gene_enrichment_results_for_cca: This contains the gene enrichment results for the CCA components for negative and positive eQTMs

The supplementary_materials/model directory contains the following sections:

disease_tissue_predictions: This contains the models trained for tissue prediction and disease prediction based on the PCA components from the public DNA methylation data

eqtm_predictions: This contains models trained for eQTM prediction

cca_transformations: This contains CCA transformation models and models for STRING gene pair predictions