DNA-binding residues and binding mode prediction with binding-mechanism concerned models

Abstract

BackgroundProtein-DNA interactions are essential for fundamental biological activities including DNA transcription, replication, packaging, repair and rearrangement. Proteins interacting with DNA can be classified into two categories of binding mechanisms - sequence-specific and non-specific binding. Protein-DNA specific binding provides a mechanism to recognize correct nucleotide base pairs for sequence-specific identification. Protein-DNA non-specific binding shows sequence independent interaction for accelerated targeting by interacting with DNA backbone. Both sequence-specific and non-specific binding residues contribute to their roles for interaction.ResultsThe proposed framework has two stage predictors: DNA-binding residues prediction and binding mode prediction. In the first stage - DNA-binding residues prediction, the predictor for DNA specific binding residues achieves 96.45% accuracy with 50.14% sensitivity, 99.31% specificity, 81.70% precision, and 62.15% F-measure. The predictor for DNA non-specific binding residues achieves 89.14% accuracy with 53.06% sensitivity, 95.25% specificity, 65.47% precision, and 58.62% F-measure. While combining prediction results of sequence-specific and non-specific binding residues with OR operation, the predictor achieves 89.26% accuracy with 56.86% sensitivity, 95.63% specificity, 71.92% precision, and 63.51% F-measure. In the second stage, protein-DNA binding mode prediction achieves 75.83% accuracy while using support vector machine with multi-class prediction.ConclusionThis article presents the design of a sequence based predictor aiming to identify sequence-specific and non-specific binding residues in a transcription factor with DNA binding-mechanism concerned. The protein-DNA binding mode prediction was introduced to help improve DNA-binding residues prediction. In addition, the results of this study will help with the design of binding-mechanism concerned predictors for other families of proteins interacting with DNA.

Integrating sequence and gene expression information predicts genome-wide DNA-binding proteins and suggests a cooperative mechanism

“…We have previously developed methods for predicting DNA-binding site residues in proteins from single sequences as well as from evolutionary profiles using neural networks and other machine learning models ( 49 , 50 ). Predictive features in each case share essentially the same local sequence features, even though class labels and hence the trained models differ depending on the carefully prepared datasets ( 24 – 27 , 51 – 54 ). These methods have been recently reviewed comprehensively in the context of their predictive performances ( 28 , 51 ).…”

An Ensemble Docking Approach for Analyzing and Designing Aptamer Heterodimers Targeting VEGF165

“…In the classification, to assess whether a specific aptamer has bound to a particular domain of VEGF 165 , we considered whether the distances between protein side-chain heavy atoms and DNA heavy atoms were within 0.45 nm [50]. More extensive pictorial representations than those in Figure 6 can be found in Figures S2 and S3.…”

Extending Asia Pacific bioinformatics into new realms in the "-omics" era

“…Where experimental structures are not available, structure prediction is still an important area of research, with Liu et al [ 28 ] presenting a new sequence-based hybrid predictor to identify conformationally ambivalent regions in proteins. Huang et al [ 29 ] have used sequence and structural information to predict DNA-binding residues in transcription factors, while Jongkon et al [ 30 ] have predicted the binding preference of various strains of avian influenza A to cognate human receptors. Prasad et al [ 31 ] have employed RNA secondary structure and sequence motifs for the phylogenetic analysis of flukes.…”