Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 45 min ago
Peer-reviewedCC BYGenome biology

GECSI: large-scale chromatin state imputation from gene expression.

  • Jingyuan Fu1,2
  • Jason Ernst3,4,5,6,7,8
8 affiliations
  1. 1Computer Science Department, University of California, Los Angeles, Los Angeles, CA, 90095, USA.
  2. 2Department of Biological Chemistry, University of California, Los Angeles, Los Angeles, CA, 90095, USA.
  3. 3Computer Science Department, University of California, Los Angeles, Los Angeles, CA, 90095, USA. [email protected].
  4. 4Department of Biological Chemistry, University of California, Los Angeles, Los Angeles, CA, 90095, USA. [email protected].
  5. 5Department of Computational Medicine, University of California, Los Angeles, Los Angeles, CA, 90095, USA. [email protected].
  6. 6Eli and Edythe Broad Center of Regenerative Medicine and Stem Cell Research at University of California, Los Angeles, Los Angeles, CA, 90095, USA. [email protected].
  7. 7Jonsson Comprehensive Cancer Center, University of California, Los Angeles, Los Angeles, CA, 90095, USA. [email protected].
  8. 8Molecular Biology Institute, University of California, Los Angeles, Los Angeles, CA, 90095, USA. [email protected].
Read full textPDFDOICite

Abstract

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.

Related

  1. Large-scale chromatin topological remodeling accompanies hepatocellular carcinoma progression
    Fengle Jiang, Zheting Zhang, Zhaoshuo Chen +4
    Scientific ReportsPeer-reviewedCC BYFull textMolecular biology & gene regulationDOAJ
  2. Efficient differential expression analysis of large-scale single-cell transcriptomics data using Dreamlet
    Gabriel E. Hoffman, Donghoon Lee, Jaroslav M. Bendl +12
    Nature CommunicationsPeer-reviewedCC BYFull text75 citedMolecular biology & gene regulationOpenAlex
  3. Recommendation system-inspired learning of crossmodal interaction patterns between chromatin accessibility and gene expression
    Xiaotang Wang, Xuanwei Lin, Qiaoyi Zhang +3
    Nature CommunicationsPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossref
  4. Cis-TERN: a graph-based method to integrate single-cell chromatin accessibility with gene expression data to infer the pseudotime ordering of cells
    Ameya Gokhale, Pawel F Przytycki
    Bioinformatics AdvancesPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
  5. Premeiotic chromatin states orchestrate gene expression during male gametogenesis in rice
    Bo Zhu, Feng Zhao, Qian Liu +6
    Genome BiologyPeer-reviewedCC BY 4.0Full text2 citedProteomics & metabolomicsGenetics & genomicsHAL

Cite

BibTeXRIS
BibTeX
@article{fu2026gecsi,
  title = {{GECSI: large-scale chromatin state imputation from gene expression.}},
  author = {Jingyuan Fu and Jason Ernst},
  journal = {Genome biology},
  year = {2026},
  month = aug,
  doi = {10.1186/s13059-026-04209-5},
  url = {https://europepmc.org/article/MED/42958318},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - GECSI: large-scale chromatin state imputation from gene expression.
AU  - Jingyuan Fu
AU  - Jason Ernst
PY  - 2026
DA  - 2026/08/01
JO  - Genome biology
DO  - 10.1186/s13059-026-04209-5
UR  - https://europepmc.org/article/MED/42958318
AB  - 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.
SN  - 1474-7596
SN  - 1474-760X
ER  -