DomNet: Protein Domain Boundary Prediction Using Enhanced General Regression Network and New Profiles

Yoo, Paul D.; Sikder, Abdur R; Taheri, Javid; Zhou, Bing Bing; Zomaya, Albert Y.

doi:10.1109/tnb.2008.2000747

Cited by 29 publications

(24 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yoo et al [16] introduced DomNet (Protein Domain Boundary Prediction Using Enhanced General Regression Network and New Profiles) which was trained using a compact domain profile, secondary structure, solvent accessibility information, and interdomain linker index to detect possible domain boundaries for a target sequence. The authors proposed a semi-parametric model that uses a nonlinear auto-associative standard regression neural network (EGRN) for filtering noise and less discriminative features.…”

Section: Scooby-domainmentioning

confidence: 99%

Prediction of protein inter-domain linkers using compositional index and simulated annealing

Shatnawi

Zaki

2013

Proceedings of the 15th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Protein chains are typically large and consist of multiple domains which are difficult and computationally expensive to characterize using experimental methods. Therefore, accurate and reliable prediction of protein domain boundaries is often the initial step in both experimental and computational protein research. In this paper, we propose a straightforward yet effective method to predict inter-domain linker segments by using the amino acid compositional index from the amino acid sequence information. Each amino acid in the protein sequence is represented by a compositional index which is deduced from a combination of the difference in amino acid occurrences in domains and linker segments in training protein sequences and the amino acid composition information. Further, we employ simulated annealing to improve the prediction by finding the optimal set of threshold values that separate domains from inter-domain linkers. The performance of the proposed method is compared to the current approaches on two protein sequence datasets. Experimental results show superior performance by the proposed method when compared to the state-of-the-art methods for inter-domain linker prediction.

show abstract

Section: Scooby-domainmentioning

confidence: 99%

Prediction of protein inter-domain linkers using compositional index and simulated annealing

Shatnawi

Zaki

2013

Proceedings of the 15th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Evolutionary information in form of PSSMs is the most widely used input form for protein structure prediction in 1D, 2D and 3D, as well as other computational proteomic prediction/classification tasks [14][15][16][17][18][19][20][21]. The idea of using evolutionary information in the form of PSSMs was first proposed by Jones et al [24], and it improved the accuracy about 3-5% in their prediction tasks.…”

Section: A Evolutionary Dataset Constructionmentioning

confidence: 99%

“…The recent computational proteomic studies report that protein secondary structure information is useful in various protein sequence-based classifications/predictions [14][15][16][17][18][19][20][21]. Although the mutations at sequence level can obscure the similarity between homologs, the secondary-structure patterns of the sequence remain conserved.…”

Section: B Protein Secondary Structure Informationmentioning

confidence: 99%

See 1 more Smart Citation

Tree-Based Consensus Model for Proline Cis-Trans Isomerization Prediction

Yoo

Zomaya

Alromaithi

et al. 2013

2013 IEEE International Symposium on Parallel &Amp; Distributed Processing, Workshops and PHD Forum

Self Cite

View full text Add to dashboard Cite

Proline cis-trans isomerization plays a key role in the rate-determining steps of protein folding. Accurate prediction of proline cis-trans isomerization is of great importance for the understanding of protein folding, splicing, cell signaling, and transmembrane active transport in both the human body and animals. Our goal is to develop a state-of-theart proline cis-trans isomerization predictor with a biophysically-motivated consensus model through the use of evolutionary information only. The current computational predictors of proline cis-trans isomerization achieve about 70-73% accuracies through the use of evolutionary information as well as predicted protein secondary structure information. However, our methods that utilize support vector machine (SVM) and tree-based consensus model have achieved 76.72% and 81.5% accuracies, respectively, on the same proline dataset.

show abstract

“…The statistical and machine-learning-based methods are probably the most frequently used approaches to protein domain predictions, with examples including DGS (Wheelan et al , 2000), DomCut (Suyama and Ohara, 2003), Armadillo (Dumontier et al , 2005), PPRODO (Sim et al , 2005), DOMPro (Cheng et al , 2006), DomNet (Yoo et al , 2008), DROP (Ebina et al , 2011), DOBO (Eickholt et al , 2011), PRODOM (Servant et al , 2002), ADDA (Heger et al , 2005) and EVEREST (Portugaly et al , 2006). In the DGS, DomCut and Armadillo programs, the statistical regularities seen in the Protein Data Bank (PDB) structures, including domain size distribution and residue propensities, are used to deduce the domain linker and boundary predictions.…”

Section: Introductionmentioning

confidence: 99%

ThreaDom: extracting protein domain boundary information from multiple threading alignments

Xue¹,

Xu²,

Wang³

et al. 2013

Bioinformatics

View full text Add to dashboard Cite

Motivation: Protein domains are subunits that can fold and evolve independently. Identification of domain boundary locations is often the first step in protein folding and function annotations. Most of the current methods deduce domain boundaries by sequence-based analysis, which has low accuracy. There is no efficient method for predicting discontinuous domains that consist of segments from separated sequence regions. As template-based methods are most efficient for protein 3D structure modeling, combining multiple threading alignment information should increase the accuracy and reliability of computational domain predictions.Result: We developed a new protein domain predictor, ThreaDom, which deduces domain boundary locations based on multiple threading alignments. The core of the method development is the derivation of a domain conservation score that combines information from template domain structures and terminal and internal alignment gaps. Tested on 630 non-redundant sequences, without using homologous templates, ThreaDom generates correct single- and multi-domain classifications in 81% of cases, where 78% have the domain linker assigned within ±20 residues. In a second test on 486 proteins with discontinuous domains, ThreaDom achieves an average precision 84% and recall 65% in domain boundary prediction. Finally, ThreaDom was examined on 56 targets from CASP8 and had a domain overlap rate 73, 87 and 85% with the target for Free Modeling, Hard multiple-domain and discontinuous domain proteins, respectively, which are significantly higher than most domain predictors in the CASP8. Similar results were achieved on the targets from the most recently CASP9 and CASP10 experiments.Availability: http://zhanglab.ccmb.med.umich.edu/ThreaDom/.Contact: zhng@umich.eduSupplementary information: Supplementary data are available at Bioinformatics online.

show abstract

DomNet: Protein Domain Boundary Prediction Using Enhanced General Regression Network and New Profiles

Cited by 29 publications

References 50 publications

Prediction of protein inter-domain linkers using compositional index and simulated annealing

Prediction of protein inter-domain linkers using compositional index and simulated annealing

Tree-Based Consensus Model for Proline Cis-Trans Isomerization Prediction

ThreaDom: extracting protein domain boundary information from multiple threading alignments

Contact Info

Product

Resources

About