Enhanced regulatory sequence prediction using gapped k-mer features.
Ghandi M, Lee D, Mohammad-Noori M, Beer MA. · 2014
Read Enhanced regulatory sequence prediction using gapped k-mer features. by Ghandi M, Lee D, Mohammad-Noori M, Beer MA. (2014) 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-pmc4102394.txt.
Description
Mahmoud Ghandi, Dongwon Lee, Morteza Mohammad-Noori, and Michael A. Beer improved computer prediction of DNA regulatory elements by allowing gaps in short sequence words. Their methods paper appeared in PLoS Computational Biology in 2014. Models often count k-mers, DNA words of fixed length, but longer words become too rare to count reliably.
Gapped k-mers let some positions vary, so longer patterns stay measurable. The team built a classifier, gkm-SVM, plus a robust way to estimate word frequencies and a fast tree structure for large genome-wide jobs. Against their earlier tool and rival approaches, the new method predicted working regulatory elements and tissue-specific enhancers far more accurately, at times doubling precision. It also won consistently on human ENCODE binding data sets.
Catalog record
| CREATOR | Ghandi M, Lee D, Mohammad-Noori M, Beer MA. |
|---|---|
| YEAR | 2014 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 87 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |