This repository contains implementations and R package to accompany our PO-EN paper. The subdirectory manuscript contains the code and data to reproduce the analysis in our paper.
If you use the code here, please cite our publication:
Zikun Yang et al. A robust semi-supervised model to predict regulatory effects of genetic variants at single nucleotide resolution using massively parallel reporter assays, with applications to fine-mapping of GWAS loci.
Presence-only model with Elastic Net penalty is a regularized generalized linear model training on the presence-absence response. This package provides functions for tuning and fitting the presence-only model. The presence-only model can be used to predict regulatory effects of genetic variants at sequence-level resolution by integrating a large number of epigenetic features and massively parallel reporter assays (MPRAs).
Reference manual can be found at https://github.com/Iuliana-Ionita-Laza/PO.EN/blob/master/PO.EN.pdf.
Vignettes can be found at https://github.com/Iuliana-Ionita-Laza/PO.EN/blob/master/PO.EN_demonstration.pdf.
Install PO.EN in R:
devtools::install_github("Iuliana-Ionita-Laza/PO.EN")
Yang, Z., Wang, C., Erjavec, S., Petukhova, L., Christiano, A., & Ionita-Laza, I. (2021). A semisupervised model to predict regulatory effects of genetic variants at single nucleotide resolution using massively parallel reporter assays. Bioinformatics, 37(14), 1953-1962.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.