Identification and analysis of transcription factor family-specific features derived from DNA and protein information

Authors:
Ashish Anand;Ganesan Pugalenthi;Gary B. Fogel;P. N. Suganthan
Affiliations:
School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Singapore, Singapore;School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Singapore, Singapore;Natural Selection Inc., 9330 Scranton Road, Suite 150, San Diego, CA 92121, United States;School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Singapore, Singapore
Venue:
Pattern Recognition Letters
Year:
2010

Citing 6
Cited 0

Pairwise classification and support vector machines

Advances in kernel methods
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
On the algorithmic implementation of multiclass kernel-based vector machines

The Journal of Machine Learning Research
Sequence features of DNA binding sites reveal structural class of associated transcription factor

Bioinformatics
An approach to predict transcription factor DNA binding site specificity based upon gene and transcription factor functional categorization

Bioinformatics
Prediction of Transcription Factor Families Using DNA Sequence Features

PRIB '08 Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics

Quantified Score

Hi-index	0.10

Visualization

Abstract

A common approach for understanding the relationship between transcription factors (TFs) and transcription factor binding sites (TFBSs) is to use features at either the TF level or the DNA level. For a given TF family, features can be derived from the DNA-binding domains at the protein level as well as TF binding sites at the DNA sequence level. Here we investigate the relative importance of features from these different levels for main TF families to better understand: (1) family-specific features and (2) the proportion of features from either the DNA or protein level. We perform class-wise feature selection on TF families to identify important features for each family. Importance of the selected features is assessed in terms of predictive accuracy of assigning TFs and associated TFBSs to correct TF families. Evaluation of the best model on an independent test set resulted in a predictive accuracy of ~90%. Analysis of the selected features used in the best model on a family-by-family basis shows congruence with the fact that interaction between TF proteins and TFBS in the DNA is quite family specific. Our analysis further suggests that: (1) this approach can be used to determine and better understand which features (at both the DNA and protein levels) are important to consider for each TF family, and (2) a similar approach to combine DNA and protein level features may be useful for other datasets where protein-DNA interaction is a key component of biological function.