Histone modification levels are predictive for gene expression

By Rosa Karlic, Ho-Ryun Chung, Julia A. Lasserre, Kristian Vlahovicek, Martin Vingron. Proceedings of the National Academy of Sciences of the United States of America, 2010

789 citations recorded by the source corpus.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/1282cdb2c14fdd2aa6c0d7210fa401effef11e69

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Cistrome Data Browser: expanded datasets and new tools for gene regulatory analysis (2018, background): “Chromatin immunoprecipitation and DNA sequencing (ChIP-seq) experiments (4–7) targeting histones in particular post-translational modification states have revealed that histone marks can be used to identify promoters and enhancers (8,9), discriminate between repressive and activating regulatory stat”
Machine learning in genetics and genomics (2015, methodology): “Some techniques aim to predict the expression of a gene on the basis of the DNA sequence alone 10 , whereas others take into account ChIP–seq profiles of histone modification 11 or transcription factor binding 12 at the gene promoter region.”
Epigenetic modifications and human disease (2010, background): “Actively transcribed genes are characterized by high levels of H3K4me3, H3K27ac, H2BK5ac and H4K20me1 in the promoter and H3K79me1 and H4K20me1 along the gene bod”
Modeling gene expression using chromatin features in various cellular contexts (2012, positive): “[10] recently derived quantitative models to predict gene expression using histone modifications and showed that they are well-correlated.”
ISMARA: automated modeling of genomic signals as a democracy of regulatory motifs (2014, background): “2008), and several recent studies have shown that the levels of these marks can be used to predict gene expression levels (Karlic et al. 2010; Dong et al. 2012; Tippmann et al. 2012).”
Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin (2017, background): “Linear Regression ([14]) × × × × X X × X Support Vector Machine ([7]) × X Bin-specific × X X X × Random Forest ([10]) × X Best-bin × X X × × Rule Learning ([12]) × X × × X × X X DeepChrome-CNN [29] X X Automatic X X X X × AttentiveChrome X X Automatic X X X X X”
Deep learning for computational biology (2016, neutral): “…point, the most accurate prediction of gene expression levels is currently made from a broad set of epigenetic features using sparse linear models (Karlic et al , 2010; Cheng et al , 2011) or random forests (Li et al , 2015); how the selected features determine the transcript levels remains an…”