Title |
DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning
|
---|---|
Published in |
Genome Biology, April 2017
|
DOI | 10.1186/s13059-017-1189-z |
Pubmed ID | |
Authors |
Christof Angermueller, Heather J. Lee, Wolf Reik, Oliver Stegle |
Abstract |
Recent technological advances have enabled DNA methylation to be assayed at single-cell resolution. However, current protocols are limited by incomplete CpG coverage and hence methods to predict missing methylation states are critical to enable genome-wide analyses. We report DeepCpG, a computational approach based on deep neural networks to predict methylation states in single cells. We evaluate DeepCpG on single-cell methylation data from five cell types generated using alternative sequencing protocols. DeepCpG yields substantially more accurate predictions than previous methods. Additionally, we show that the model parameters can be interpreted, thereby providing insights into how sequence composition affects methylation variability. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 22 | 22% |
United Kingdom | 13 | 13% |
Spain | 5 | 5% |
India | 4 | 4% |
France | 4 | 4% |
Germany | 3 | 3% |
Australia | 3 | 3% |
Austria | 2 | 2% |
Singapore | 1 | <1% |
Other | 10 | 10% |
Unknown | 35 | 34% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Scientists | 60 | 59% |
Members of the public | 40 | 39% |
Science communicators (journalists, bloggers, editors) | 2 | 2% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 3 | <1% |
Denmark | 2 | <1% |
United Kingdom | 1 | <1% |
Canada | 1 | <1% |
Sweden | 1 | <1% |
Germany | 1 | <1% |
Belgium | 1 | <1% |
Japan | 1 | <1% |
Korea, Republic of | 1 | <1% |
Other | 0 | 0% |
Unknown | 742 | 98% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 200 | 27% |
Researcher | 128 | 17% |
Student > Master | 91 | 12% |
Student > Bachelor | 48 | 6% |
Student > Doctoral Student | 27 | 4% |
Other | 111 | 15% |
Unknown | 149 | 20% |
Readers by discipline | Count | As % |
---|---|---|
Biochemistry, Genetics and Molecular Biology | 166 | 22% |
Computer Science | 141 | 19% |
Agricultural and Biological Sciences | 130 | 17% |
Engineering | 40 | 5% |
Mathematics | 19 | 3% |
Other | 84 | 11% |
Unknown | 174 | 23% |