Prediction of DNA-binding residues from protein sequence information using random forests

Abstract

Background: Protein-DNA interactions are involved in many biological processes essential for cellular function. To understand the molecular mechanism of protein-DNA recognition, it is necessary to identify the DNA-binding residues in DNA-binding proteins. However, structural data are available for only a few hundreds of protein-DNA complexes. With the rapid accumulation of sequence data, it becomes an important but challenging task to accurately predict DNA-binding residues directly from amino acid sequence data.

Results: A new machine learning approach has been developed in this study for predicting DNA-binding residues from amino acid sequence data. The approach used both the labelled data instances collected from the available structures of protein-DNA complexes and the abundant unlabeled data found in protein sequence databases. The evolutionary information contained in the unlabeled sequence data was represented as position-specific scoring matrices (PSSMs) and several new descriptors. The sequence-derived features were then used to train random forests (RFs), which could handle a large number of input variables and avoid model overfitting. The use of evolutionary information was found to significantly improve classifier performance. The RF classifier was further evaluated using a separate test dataset, and the predicted DNA-binding residues were examined in the context of three-dimensional structures.

Conclusion: The results suggest that the RF-based approach gives rise to more accurate prediction of DNA-binding residues than previous studies. A new web server called BindN-RF http://bioinfo.ggc.org/bindn-rf/ has thus been developed to make the RF classifier accessible to the biological research community.

Figure 1

Schematic diagram for extracting evolutionary information from the PSI-BLAST search result.

Figure 2

ROC curves to show the effect of evolutionary information. HKM represents the random forest classifier trained with the three biochemical features (H, K and M), and HKM+EI indicates the most accurate classifier using evolutionary information (PSSM, H_m, H_d, K_m and K_d).

Figure 3

ROC curves of different classifiers for DNA-binding site prediction. The performance comparison is based on the PDC25t test dataset. The four different classifiers are BindN-RF (this study), BindN [10], DP-Bind [7,8] and DBS-PSSM [6].

Figure 4

Predicted DNA-binding residues shown in the context of three-dimensional structures. Putative DNA-binding residues were predicted for the bacterial transcriptional regulator QacR (PDB ID: 1JT0) using BindN-RF (A) and BindN (B). In each protein-DNA complex, true positives (correctly predicted DNA-binding residues) are in red spacefill; true negatives in green wireframe; false positives in yellow spacefill; false negatives in blue spacefill; and the DNA double helix in purple.