PT  - JOURNAL ARTICLE
AU  - Suchen Zheng
AU  - Nitya Thakkar
AU  - Hannah L. Harris
AU  - Megan Zhang
AU  - Susanna Liu
AU  - Mark Gerstein
AU  - Erez Lieberman-Aiden
AU  - M. Jordan Rowley
AU  - William Stafford Noble
AU  - Gamze Gürsoy
AU  - Ritambhara Singh
TI  - Predicting A/B compartments from histone modifications using deep learning
AID  - 10.1101/2022.04.19.488754
DP  - 2022 Jan 01
TA  - bioRxiv
PG  - 2022.04.19.488754
4099  - http://biorxiv.org/content/early/2022/04/19/2022.04.19.488754.short
4100  - http://biorxiv.org/content/early/2022/04/19/2022.04.19.488754.full
AB  - Genomes in 3D are folded into organizational units that can influence critical biological functions. In particular, the organization of chromatin into A and B compartments segregates its active regions from the inactive regions. Compartments, evident in Hi-C contact matrices, have been used to describe cell-type specific changes in A/B organization. However, obtaining Hi-C data for all cell and tissue types of interest is prohibitively expensive, which has limited the widespread consideration of compartment status. We present a prediction tool called Compartment prediction using Recurrent Neural Network (CoRNN) that models the relationship between the compartmental organization of the genome and histone modification enrichment. Our model predicts A/B compartments, in a cross-cell type setting, with an average area under the ROC score of 90.9%. Our cell type specific compartment predictions show high overlap with known functional elements. We investigate our predictions by systematically removing combinations of histone marks and find that H3K27ac and H3K36me3 are the most predictive marks. We then perform a detailed investigation of loci where compartment status cannot be accurately predicted from these marks.These regions represent chromatin with ambiguous compartmental status, likely due to variations in status within the population of cells. As such these ambiguous loci also show highly variable compartmental status between biological replicates in the same GM12878 cell type. Our software and trained model are publicly available at https://github.com/rsinghlab/CoRNN.Competing Interest StatementThe authors have declared no competing interest.