.png){kind=icon}
.png){kind=icon}
Return
GECSI: large-scale chromatin state imputation from gene expression
.png){kind=icon}
OA
AI
J
J
DOI：10.1186/s13059-026-04209-5.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Chromatin state annotations based on epigenetic marks are powerful resources, but many additional samples have gene expression data available while lacking epigenetic mark data and chromatin state annotations. Using the EpiATLAS resource of the International Human Epigenome Consortium (IHEC), we develop Gene Expression-based Chromatin State Imputation (GECSI), which uses an ensemble of multi-class logistic regression classifiers to predict chromatin state annotations from gene expression data. We show in cross-validation that GECSI accurately predicts observed chromatin state annotations. We also apply GECSI using gene expression data in 449 IHEC additional samples, providing an expanded chromatin state annotation resource.
Keywords:
Epigenomics
Chromatin states
Chromatin
Gene expression
Genome annotation
Epigenetics
Imputation
Machine learning
Journal
G
IF:
9.4
Papers:
6.3K
Citations:
7.3W
Organization
Cited Papers