Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/164518
Title: MCI-frcnn: a deep learning method for topological micro-domain boundary detection
Authors: Tian, Simon Zhongyuan
Yin, Pengfei
Jing, Kai
Yang, Yang
Xu, Yewen
Huang, Guangyu
Ning, Duo
Fullwood, Melissa Jane
Zheng, Meizhen
Keywords: Science::Biological sciences
Issue Date: 2022
Source: Tian, S. Z., Yin, P., Jing, K., Yang, Y., Xu, Y., Huang, G., Ning, D., Fullwood, M. J. & Zheng, M. (2022). MCI-frcnn: a deep learning method for topological micro-domain boundary detection. Frontiers in Cell and Developmental Biology, 10, 1050769-. https://dx.doi.org/10.3389/fcell.2022.1050769
Project: T2EP30120- 0020
Journal: Frontiers in Cell and Developmental Biology
Abstract: Chromatin structural domains, or topologically associated domains (TADs), are a general organizing principle in chromatin biology. RNA polymerase II (RNAPII) mediates multiple chromatin interactive loops, tethering together as RNAPII-associated chromatin interaction domains (RAIDs) to offer a framework for gene regulation. RAID and TAD alterations have been found to be associated with diseases. They can be further dissected as micro-domains (micro-TADs and micro-RAIDs) by clustering single-molecule chromatin-interactive complexes from next-generation three-dimensional (3D) genome techniques, such as ChIA-Drop. Currently, there are few tools available for micro-domain boundary identification. In this work, we developed the MCI-frcnn deep learning method to train a Faster Region-based Convolutional Neural Network (Faster R-CNN) for micro-domain boundary detection. At the training phase in MCI-frcnn, 50 images of RAIDs from Drosophila RNAPII ChIA-Drop data, containing 261 micro-RAIDs with ground truth boundaries, were trained for 7 days. Using this well-trained MCI-frcnn, we detected micro-RAID boundaries for the input new images, with a fast speed (5.26 fps), high recognition accuracy (AUROC = 0.85, mAP = 0.69), and high boundary region quantification (genomic IoU = 76%). We further applied MCI-frcnn to detect human micro-TADs boundaries using human GM12878 SPRITE data and obtained a high region quantification score (mean gIoU = 85%). In all, the MCI-frcnn deep learning method which we developed in this work is a general tool for micro-domain boundary detection.
URI: https://hdl.handle.net/10356/164518
ISSN: 2296-634X
DOI: 10.3389/fcell.2022.1050769
Schools: School of Biological Sciences 
Organisations: Cancer Science Institute of Singapore, NUS
Institute of Molecular and Cell Biology, A*STAR
Rights: © 2022 Tian, Yin, Jing, Yang, Xu, Huang, Ning, Fullwood and Zheng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SBS Journal Articles

Files in This Item:
File Description SizeFormat 
fcell-10-1050769.pdf4.82 MBAdobe PDFThumbnail
View/Open

Page view(s)

83
Updated on Feb 24, 2024

Download(s)

21
Updated on Feb 24, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.