Journal
NUCLEIC ACIDS RESEARCH
Volume 36, Issue 12, Pages 4137-4148Publisher
OXFORD UNIV PRESS
DOI: 10.1093/nar/gkn361
Keywords
-
Categories
Funding
- Direct For Mathematical & Physical Scien [0805491] Funding Source: National Science Foundation
- Division Of Mathematical Sciences [0805491] Funding Source: National Science Foundation
- NIGMS NIH HHS [R01-GM080625-01A1, R01-GM07899, R01 GM080625] Funding Source: Medline
Ask authors/readers for more resources
Predicting how and where proteins, especially transcription factors (TFs), interact with DNA is an important problem in biology. We present here a systematic study of predictive modeling approaches to the TFDNA binding problem, which have been frequently shown to be more efficient than those methods only based on position-specific weight matrices (PWMs). In these approaches, a statistical relationship between genomic sequences and gene expression or ChIP-binding intensities is inferred through a regression framework; and influential sequence features are identified by variable selection. We examine a few state-of-the-art learning methods including stepwise linear regression, multivariate adaptive regression splines, neural networks, support vector machines, boosting and Bayesian additive regression trees (BART). These methods are applied to both simulated datasets and two whole-genome ChIP-chip datasets on the TFs Oct4 and Sox2, respectively, in human embryonic stem cells. We find that, with proper learning methods, predictive modeling approaches can significantly improve the predictive power and identify more biologically interesting features, such as TFTF interactions, than the PWM approach. In particular, BART and boosting show the best and the most robust overall performance among all the methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available