Graph embedding and unsupervised learning predict genomic sub-compartments from HiC chromatin interaction data

• Published in: Nature communications 2020-03, Vol.11 (1), p.1173-1173, Article 1173
• Main Authors: Ashoor, Haitham, Chen, Xiaowen, Rosikiewicz, Wojciech, Wang, Jiahui, Cheng, Albert, Wang, Ping, Ruan, Yijun, Li, Sheng
• Format: Article
• Language: English
• Subjects: 38/91; 45/23; 631/114/1305; 631/114/1314; 631/114/794; Algorithms; Artificial neural networks; Chromatin; Chromatin - genetics; Chromatin - metabolism; Cluster Analysis; Clustering; Compartments; Computer applications; Computer Graphics; Data Analysis; Embedding; Epigenome; Gene Expression; Genomes; Genomics - methods; Humanities and Social Sciences; Humans; K562 Cells; Learning; Machine learning; Markov Chains; multidisciplinary; Neural networks; Neural Networks, Computer; Predictions; Reproducibility of Results; Science; Science (multidisciplinary); Unsupervised learning; Unsupervised Machine Learning
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-020-14974-x

Chromatin interaction studies can reveal how the genome is organized into spatially confined sub-compartments in the nucleus. However, accurately identifying sub-compartments from chromatin interaction data remains a challenge in computational biology. Here, we present Sub-Compartment Identifier (SCI), an algorithm that uses graph embedding followed by unsupervised learning to predict sub-compartments using Hi-C chromatin interaction data. We find that the network topological centrality and clustering performance of SCI sub-compartment predictions are superior to those of hidden Markov model (HMM) sub-compartment predictions. Moreover, using orthogonal Chromatin Interaction Analysis by in-situ Paired-End Tag Sequencing (ChIA-PET) data, we confirmed that SCI sub-compartment prediction outperforms HMM. We show that SCI-predicted sub-compartments have distinct epigenetic marks, transcriptional activities, and transcription factor enrichment. Moreover, we present a deep neural network to predict sub-compartments using epigenome, replication timing, and sequence data. Our neural network predicts more accurate sub-compartment predictions when SCI-determined sub-compartments are used as labels for training. Accurate identification of sub-compartments from chromatin interaction data remains a challenge. Here, the authors introduce an algorithm combining graph embedding and unsupervised learning to predict sub-compartments using Hi-C data.