DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning.
Angermueller C, Lee HJ, Reik W, Stegle O, Stegle O. · 2017
Read DeepCpG: accurate prediction of single-cell DNA methylation states using deep learning. by Angermueller C, Lee HJ, Reik W, Stegle O, Stegle O. (2017) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc5387360.txt.
Description
Christof Angermueller, Heather J. Lee, Wolf Reik, and Oliver Stegle present a deep learning tool called DeepCpG in a 2017 Genome Biology paper. DNA methylation is a chemical mark on DNA that helps control genes. New lab methods can read the mark in single cells, but they miss many sites, leaving gaps that block full studies of how cells differ from one another.
DeepCpG uses deep neural networks, a form of machine learning, to guess the missing marks in each cell. Tested on data from five cell types made by different lab methods, it beat older tools by a wide margin. The team also shows how the model can be read to reveal how nearby DNA letters shape mark patterns.
Catalog record
| CREATOR | Angermueller C, Lee HJ, Reik W, Stegle O, Stegle O. |
|---|---|
| YEAR | 2017 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |