.png){kind=icon}
.png){kind=icon}
Return
Extracting sequence features to predict proteinDNA interactions: a comparative study
.png){kind=icon}
OA
AI
DOI：10.1093/nar/gkn361.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
CIS-REGULATORY MODULES
FACTOR-BINDING SITES
TRANSCRIPTIONAL REGULATION
STEM-CELLS
PLURIPOTENCY
DISCOVERY
MODELS
NETWORK
MOTIFS
NANOG
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.1
Papers:
3.6W
Citations:
29.0W
