DNABP: Identification of DNA-Binding Proteins Based on Feature Selection Using a Random Forest and Predicting Binding Residues

Abstract

DNA-binding proteins are fundamentally important in cellular processes. Several computational-based methods have been developed to improve the prediction of DNA-binding proteins in previous years. However, insufficient work has been done on the prediction of DNA-binding proteins from protein sequence information. In this paper, a novel predictor, DNABP (DNA-binding proteins), was designed to predict DNA-binding proteins using the random forest (RF) classifier with a hybrid feature. The hybrid feature contains two types of novel sequence features, which reflect information about the conservation of physicochemical properties of the amino acids, and the binding propensity of DNA-binding residues and non-binding propensities of non-binding residues. The comparisons with each feature demonstrated that these two novel features contributed most to the improvement in predictive ability. Furthermore, to improve the prediction performance of the DNABP model, feature selection using the minimum redundancy maximum relevance (mRMR) method combined with incremental feature selection (IFS) was carried out during the model construction. The results showed that the DNABP model could achieve 86.90% accuracy, 83.76% sensitivity, 90.03% specificity and a Matthews correlation coefficient of 0.727. High prediction accuracy and performance comparisons with previous research suggested that DNABP could be a useful approach to identify DNA-binding proteins from sequence information. The DNABP web server system is freely available at http://www.cbi.seu.edu.cn/DNABP/.

C1188D mutation abolishes specific recognition between MLL1‐CXXC domain and CpG site by inducing conformational switch of flexible N‐terminal

“…Recognizing specific DNA sequences by DNA binding proteins (DBPs) is critical for fundamental biological activities like transcription, DNA repair, and DNA replication. Based on a complex model resolved from X‐ray crystallography or NMR experiments, multiple knowledge‐ and physics‐based algorithms have already been developed to analyze protein‐DNA complex, 50‐53 predict protein binding sites 54‐58 or aid DBP design 59‐62 . The specific recognition of DNA by DBP is often regulated by mutations or post‐translational modifications (PTMs) 63,64 .…”

Improved detection of DNA-binding proteins via compression technology on PSSM information

“…In recent years, computational methods based on machine learning (ML) algorithms have become more and more popular because of their promising performance. According to various feature information, the ML-based approachs are mainly composed of structure information-based [ 8 – 18 ] and sequence information-based method [ 1 , 2 , 19 – 35 ].…”

On the prediction of DNA-binding proteins only from primary sequences: A deep learning approach

“…Lou et al proposed a prediction method of DNA-binding proteins by performing the feature rank using random forest and the wrapper-based feature selection using a forward best-first search strategy [ 6 ]. Ma et al used the random forest classifier with a hybrid feature set by incorporating binding propensity of DNA-binding residues [ 7 ]. Professor Liu’s group developed several novel tools for predicting DNA-Binding proteins, such as iDNA-Prot|dis by incorporating amino acid distance-pairs and reducing alphabet profiles into the general pseudo amino acid composition [ 8 ], PseDNA-Pro by combining PseAAC and physiochemical distance transformations [ 9 ], iDNAPro-PseAAC by combining pseudo amino acid composition and profile-based protein representation [ 10 ], iDNA-KACC by combining auto-cross covariance transformation and ensemble learning [ 11 ].…”