TY - JOUR
T1 - Machine learning uncovers cell identity regulator by histone code
AU - Xia, Bo
AU - Zhao, Dongyu
AU - Wang, Guangyu
AU - Zhang, Min
AU - Lv, Jie
AU - Tomoiaga, Alin S.
AU - Li, Yanqiang
AU - Wang, Xin
AU - Meng, Shu
AU - Cooke, John P.
AU - Cao, Qi
AU - Zhang, Lili
AU - Chen, Kaifu
N1 - Funding Information:
This work was supported by grants from NIH/NIGMS (R01GM125632 to K.C.) and NIH/NHLBI (R01HL133254 and R01HL148338 to K.C. and J.C.). Q.C. is supported by US Department of Defense (W81XWH-15-1-0639 and W81XWH-17-1-0357), American Cancer Society (TBE-128382), and NIH/NCI (R01CA208257 and Prostate SPORE P50CA180995 DRP). We thank Scientific Writer Dr Johnique T. Atkins for revising the manuscript.
Publisher Copyright:
© 2020, The Author(s).
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/6/1
Y1 - 2020/6/1
N2 - Conversion between cell types, e.g., by induced expression of master transcription factors, holds great promise for cellular therapy. Our ability to manipulate cell identity is constrained by incomplete information on cell identity genes (CIGs) and their expression regulation. Here, we develop CEFCIG, an artificial intelligent framework to uncover CIGs and further define their master regulators. On the basis of machine learning, CEFCIG reveals unique histone codes for transcriptional regulation of reported CIGs, and utilizes these codes to predict CIGs and their master regulators with high accuracy. Applying CEFCIG to 1,005 epigenetic profiles, our analysis uncovers the landscape of regulation network for identity genes in individual cell or tissue types. Together, this work provides insights into cell identity regulation, and delivers a powerful technique to facilitate regenerative medicine.
AB - Conversion between cell types, e.g., by induced expression of master transcription factors, holds great promise for cellular therapy. Our ability to manipulate cell identity is constrained by incomplete information on cell identity genes (CIGs) and their expression regulation. Here, we develop CEFCIG, an artificial intelligent framework to uncover CIGs and further define their master regulators. On the basis of machine learning, CEFCIG reveals unique histone codes for transcriptional regulation of reported CIGs, and utilizes these codes to predict CIGs and their master regulators with high accuracy. Applying CEFCIG to 1,005 epigenetic profiles, our analysis uncovers the landscape of regulation network for identity genes in individual cell or tissue types. Together, this work provides insights into cell identity regulation, and delivers a powerful technique to facilitate regenerative medicine.
UR - http://www.scopus.com/inward/record.url?scp=85085854191&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085854191&partnerID=8YFLogxK
U2 - 10.1038/s41467-020-16539-4
DO - 10.1038/s41467-020-16539-4
M3 - Article
C2 - 32483223
AN - SCOPUS:85085854191
SN - 2041-1723
VL - 11
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 2696
ER -