Automatic prediction of protein domains from sequence information using a hybrid learning system

Nagarajan, Niranjan; Yona, Golan

doi:10.1093/bioinformatics/bth086

Cited by 69 publications

(60 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effective entropy measure takes into account the similarity of amino acids. An evolutionary pressure is used to calculate the evolutionary span (Nagaranjan and Yona, 2004) defined as:…”

Section: Features Extractionmentioning

confidence: 99%

See 1 more Smart Citation

BRNN-SVM: Increasing the Strength of Domain Signal to Improve Protein Domain Prediction Accuracy

Hassan¹,

Othman²,

Hassan³

et al. 2012

Recurrent Neural Networks and Soft Computing

View full text Add to dashboard Cite

“…The effective entropy measure takes into account the similarity of amino acids. An evolutionary pressure is used to calculate the evolutionary span (Nagaranjan and Yona, 2004) defined as:…”

Section: Features Extractionmentioning

confidence: 99%

“…KemaDom (Lusheng et al, 2006) and Biozon (Nagaranjan and Yona, 2004); (2) Methods that depend on known protein structure to identify the protein domain, e.g. AutoSCOP (Gewehr et al, 2007) and DOMpro (Cheng et al, 2006); (3) Methods that used dimensional structure to assume protein domain boundaries, e.g.…”

Section: Introductionmentioning

confidence: 99%

BRNN-SVM: Increasing the Strength of Domain Signal to Improve Protein Domain Prediction Accuracy

Hassan¹,

Othman²,

Hassan³

et al. 2012

Recurrent Neural Networks and Soft Computing

View full text Add to dashboard Cite

“…DOMpro [8] uses secondary structure, evolutionary information and solvent accessibility information with a recursive neural network; DomSSEA [9] uses predicted secondary structure; SSEPDomain [10] predicts domains by combining information of secondary structure element alignments. On the other hand, Armidillo [11] uses the amino acids composition to predict domain boundaries; the Nagarajan's method [12] is based on analyzing multiple sequence alignments from database searches, position specific physio-chemical properties of amino acids; and DomainDiscovery [13] uses SVM from sequence information including domain linker index. There are also integrated method, such as Albert Y Z.…”

Section: Protein Domain Predictionmentioning

confidence: 99%

SVM Learning from Imbalanced Data by GA Sampling for Protein Domain Prediction

Zou

Huang

Wang

et al. 2008

2008 the 9th International Conference for Young Computer Scientists

View full text Add to dashboard Cite

show abstract

“…However, these methods produce good results in cases of single-domain proteins. Methods based on similarity and used multiple sequence alignments to represent domain boundaries such as SVM-Fold [1], EVEREST [2] and Biozon [3]. Methods that depend on known protein structure to identify the protein domain such as AutoSCOP [4], Class of Architecture, Topology and Homologous superfamily (CATH) [5] and Structural Classification of Proteins (SCOP) [6].…”

Section: Introductionmentioning

confidence: 99%

Classify a Protein Domain Using SVM Sigmoid Kernel

Hassan

Nawi

Kasim

et al. 2014

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. Protein domains are discrete portion of protein sequence that can fold independently with their own function. Protein domain classification is important for multiple reasons, which including determines the protein function in order to manufacture new protein with new function. However, there are several issues that need to be addressed in protein domain classification which include increasing domain signal and accurate classify to their category. Therefore, to overcome this issue, this paper proposed a new approach to classify protein domain from protein subsequences and protein structure information using SVM sigmoid kernel. The proposed method consists of three phases: Data generating, creating sequence information and classification. The data generating phase selects potential protein and generates clear domain information. The creating sequence information phase used several calculations to generate protein structure information in order to optimize the domain signal. The classification phase involves SVM sigmoid kernel and performance evaluation. The performance of the approach method is evaluated in terms of sensitivity and specificity on single-domain and multiple-domain using dataset SCOP 1.75. The result on SVM sigmoid kernel shown higher accuracy compare with single neural network and double neural network for single and multiple domain prediction. This proposed approach develops in order to solve the problem of coincidently group into both categories either single or multiple domain. This method showed an improvement of classification in term of sensitivity, specificity and accuracy.

show abstract

Automatic prediction of protein domains from sequence information using a hybrid learning system

Abstract: An online domain-prediction server is available at http://biozon.org/tools/domains/

Cited by 69 publications

References 47 publications

BRNN-SVM: Increasing the Strength of Domain Signal to Improve Protein Domain Prediction Accuracy

BRNN-SVM: Increasing the Strength of Domain Signal to Improve Protein Domain Prediction Accuracy

SVM Learning from Imbalanced Data by GA Sampling for Protein Domain Prediction

Classify a Protein Domain Using SVM Sigmoid Kernel

Contact Info

Product

Resources

About