newDNA-Prot: Prediction of DNA-binding proteins by employing support vector machine and a comprehensive sequence representation

Zhang, Yanping; Xu, Jun; Zheng, Wei; Zhang, Chen; Qiu, Xingye; Chen, Ke; Ruan, Jishou

doi:10.1016/j.compbiolchem.2014.09.002

Cited by 25 publications

(17 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we adopted a mutual information-based method, i.e., mRMR (Peng et al, 2005), which has been widely used in feature ranking (Niu et al, 2013; Zhao et al, 2013; Zhou et al, 2015; Zhang et al, 2016; Li and Huang, 2017; Liu et al, 2017). It considers both the relevance between features and sample labels and the redundancy among features and has been proven to be an effective feature selection method, especially for gene expression analysis (Qin et al, 2012; Zhang et al, 2014b, 2017, 2018; Zhang Y. et al, 2014; Li et al, 2015; Zhou et al, 2015; Wang et al, 2016; Song et al, 2017; Chen et al, 2018b). The method works like this: let us use Ω to denote all the 25,159 genes, Ω s to denote the selected gene set that includes m genes, and Ω g to denote the n genes that will be evaluated, and one of them will be selected.…”

Section: Methodsmentioning

confidence: 99%

Identification and Analysis of Blood Gene Expression Signature for Osteoarthritis With Advanced Feature Selection Methods

Lan

Kong

et al. 2018

Front. Genet.

View full text Add to dashboard Cite

Osteoarthritis (OA) is a complex disease that affects articular joints and may cause disability. The incidence of OA is extremely high. Most elderly people have the symptoms of osteoarthritis. The physiotherapy of OA is time consuming, and the chances of full recovery from OA are very minimal. The most effective way of fighting OA is early diagnosis and early intervention. Liquid biopsy has become a popular noninvasive test. To find the blood gene expression signature for OA, we reanalyzed the publicly available blood gene expression profiles of 106 patients with OA and 33 control samples using an automatic computational pipeline based on advanced feature selection methods. Finally, a compact 23-gene set was identified. On the basis of these 23 genes, we constructed a Support Vector Machine (SVM) classifier and evaluated it with leave-one-out cross-validation. Its sensitivity (Sn), specificity (Sp), accuracy (ACC), and Mathew's correlation coefficient (MCC) were 0.991, 0.909, 0.971, and 0.920, respectively. Obviously, the performance needed to be validated in an independent large dataset, but the in-depth biological analysis of the 23 biomarkers showed great promise and suggested that mRNA surveillance pathway and multicellular organism growth played important roles in OA. Our results shed light on OA diagnosis through liquid biopsy.

show abstract

Section: Methodsmentioning

confidence: 99%

Identification and Analysis of Blood Gene Expression Signature for Osteoarthritis With Advanced Feature Selection Methods

Lan

Kong

et al. 2018

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…These methods are broadly classified into sequence and structure based predictors. Sequence‐based tools use amino acid composition, evolutionary profile, secondary structure, physicochemical properties, side chain pK a , hydrophobicity index, molecular mass, conservation score (CS), and solvent accessibility as features . Moreover, consensus‐based predictors use multiple programs and Web servers to predict the binding site of DNA in protein sequence .…”

Section: Introductionmentioning

confidence: 99%

“…Sequence-based tools use amino acid composition, score (CS), and solvent accessibility as features. 13,[16][17][18] Moreover, consensus-based predictors use multiple programs and Web servers to predict the binding site of DNA in protein sequence. 2,[19][20][21] These predictors often work well for a specific complex, and hence, Nagarajan et al 22 designed a Web server for selecting the best predictor for predicting DNA binding site based on the structure/function of protein/DNA.…”

Section: Introductionmentioning

confidence: 99%

Dissecting and analyzing key residues in protein‐DNA complexes

Kulandaisamy

Srivastava

Raju

et al. 2017

J of Molecular Recognition

View full text Add to dashboard Cite

Protein-DNA interactions are involved in various fundamental biological processes such as replication, transcription, DNA repair, and gene regulation. To understand the interaction in protein-DNA complexes, the integrative study of binding and stabilizing residues is important. In the present study, we have identified key residues that play a dual role in both binding and stability from a nonredundant dataset of 319 protein-DNA complexes. We observed that key residues are identified in very less number of complexes (29%) and only about 4% of stabilizing/binding residues are identified as key residues. Specifically, stabilizing residues have higher preference to be key residues than binding residues. These key residues include polar, nonpolar, aliphatic, aromatic, and charged amino acids. Moreover, we have analyzed and discussed the key residues in different protein-DNA complexes, which are classified based on protein structural class, function, DNA strand, and their conformations. Especially, Ser, Thr, Tyr, Arg, and Lys residues are commonly found in most of the subclasses of protein-DNA complexes. Further, we analyzed atomic contacts, which show that polar-nonpolar is more enriched than other types of contacts. In addition, the charged contacts are highly preferred in protein-DNA complexes compared with protein-protein and protein-RNA complexes. Finally, we have discussed the sequence and structural features of key residues such as conservation score, surrounding hydrophobicity, solvent accessibility, secondary structure, and long-range order. This study will be helpful to understand the recognition mechanism and structural and functional aspects of protein-DNA complexes.

show abstract

“…More recently, Zou et al developed an entirely sequence-based protocol that transforms and integrates informative features from different scales used by SVM to predict DNA-binding proteins [14]. Zhang et al proposed newDNA-Prot, a DNA-binding protein predictor that employs an SVM classifier and a comprehensive feature that categorized features into six groups: primary sequence-based, evolutionary profile-based, predicted secondary structure-based, predicted relative solvent accessibility-based, physicochemical property-based and biological function-based features [13]. DNA-Pro based on SVM algorithm to distinguish DNA-binding proteins from non-binding proteins [17].…”

Section: Introductionmentioning

confidence: 99%

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

Guo

Sun

2016

PLoS ONE

View full text Add to dashboard Cite

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/.

show abstract

newDNA-Prot: Prediction of DNA-binding proteins by employing support vector machine and a comprehensive sequence representation

Cited by 25 publications

References 63 publications

Identification and Analysis of Blood Gene Expression Signature for Osteoarthritis With Advanced Feature Selection Methods

Identification and Analysis of Blood Gene Expression Signature for Osteoarthritis With Advanced Feature Selection Methods

Dissecting and analyzing key residues in protein‐DNA complexes

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

Contact Info

Product

Resources

About