Protein Structural Class Determination Using Support Vector Machines

Işık, Zerrin; Yanıkoğlu, Berrin; Sezerman, Uğur

doi:10.1007/978-3-540-30182-0_9

Cited by 12 publications

(10 citation statements)

References 24 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…effects of the relative frequencies of tetrapeptides on the training results. Similar research has been carried out by some others researchers such as Markowetz [7], [10], [15], [16]). But their dataset are different from the dataset we have used in this research and also they have used dipeptide or tripeptide whereas we have used tetrapeptide.…”

supporting

confidence: 67%

Protein structural class prediction using support vector machine

Shafiullah

Al-Mamun

2010

International Conference on Electrical &Amp; Computer Engineering (ICECE 2010)

View full text Add to dashboard Cite

Abstract-Protein structural class prediction can play a vital role in protein 3-D structure prediction by reducing the search space of 3-D structure prediction algorithms. In this paper we used support vector machine to predict protein structural class solely based of its amino acid sequences, i.e. mainly α, mainly β , α-β and fss from CATH protein structure database; all-α, all-β, α/β, α+β from SCOP protein structure database. Four different datasets were used in this paper among them two were constructed using a unique way called Representative Protein Extraction method. During the training phase for the binary classification 99.91% accuracy was achieved for fss vs. others. Also during the testing phase for SCOP database the overall prediction accuracy was 97.14% whereas for CATH database it was 96%.The results obtained in this study are quite encouraging, indicating that it can be used as a complimentary method for protein class prediction to many other existing methods.

show abstract

supporting

confidence: 67%

Protein structural class prediction using support vector machine

Shafiullah

Al-Mamun

2010

International Conference on Electrical &Amp; Computer Engineering (ICECE 2010)

View full text Add to dashboard Cite

show abstract

“…The tri-gram features capture the neighborhood information of amino acids. Isik et al [47], and Ghanty and Pal [21] also used tri-gram features, however, by reducing the dimensionality of the feature vectors. The performance in terms of recognition accuracy was not very promising for tri-gram features [21].…”

mentioning

confidence: 99%

A Tri-Gram Based Feature Extraction Technique Using Linear Probabilities of Position Specific Scoring Matrix for Protein Fold Recognition

Paliwal

Sharma

Lyons

et al. 2014

IEEE Trans.on Nanobioscience

View full text Add to dashboard Cite

show abstract

“…Segundo Luo et al (2002), essa classificação possui utilidades teóricas e práticas, uma vez que ela provê uma descrição geral e intuitiva da forma das proteínas. Técnicas de AM vêm sendo empregadas com sucesso na solução desse problema de classificação (Cai et al, 2001(Cai et al, , 2002Luo et al, 2002;Isik et al, 2004).…”

Section: Figura 61: Conformações Estruturais Das Proteínasunclassified

“…Em (Cai et al, 2002) e (Isik et al, 2004), SVMs integradas com as estratégias 1ct e tct, respectivamente, foram aplicadas na solução desse problema de classificação. Porém, os conjuntos de dados utilizados em ambos os trabalhos, assim como os atributos extraídos das proteínas, foram diferentes dos empregados nesta Tese.…”

Section: Figura 61: Conformações Estruturais Das Proteínasunclassified

“…Embora os experimentos desses trabalhos não sejam diretamente comparáveis, uma vez que as partições dos dados empregadas não foram as mesmas, essa diferença indica que a representação de proteínas adotada nesta Tese pode ser muito simples comparadaà usada em(Lu et al, 2004).No conjunto de dados structural, as diferentes estratégias multiclasses também tiveram desempenho similar. As taxas de acerto reportadas na literatura para a predição da classe estrutural de proteínas são próximas(Bahar et al, 1997;Luo et al, 2002;Isik et al, 2004) ou superiores(Cai et al, 2001(Cai et al, , 2002às obtidas nesta Tese. Porém, não foram encontrados trabalhos utilizando o mesmo conjunto de dados aqui empregado, não permitindo assim uma comparação direta.…”

unclassified

See 1 more Smart Citation

"Investigação de estratégias para a geração de máquinas de vetores de suporte multiclasses"

Lorena¹

View full text Add to dashboard Cite

Several problems involve the classification of data into categories, also called classes. Given a dataset containing data whose classes are known, Machine Learning (ML) algorithms can be employed for the induction of a classifier able to predict the class of new data from the same domain, thus performing the desired discrimination. Among the several ML techniques applied to classification problems, the Support Vector Machines (SVMs) are known by their high generalization ability. They are originally conceived for the solution of problems with only two classes, also named binary problems. However, several problems require the discrimination of examples into more than two categories or classes. This thesis investigates and proposes strategies for the generalization of SVMs to problems with more than two classes, known as multiclass problems. The focus of this work is on strategies that decompose the original multiclass problem into multiple binary subtasks, whose outputs are then combined to obtain the final classification. The proposed strategies aim to investigate the adaptation of the decompositions for each multiclass application considered, using information of the performance obtained for its solution or extracted from its examples. The implemented algorithms were evaluated on general datasets and on real applications from the Bioinformatics domain. The results obtained open possibilities of many future work. Among the benefits observed is the obtainment of simpler decompositions, which require less binary classifiers in the multiclass solution. vii viii Este documento foi preparado com o formatador de textos L A T E X. O sistema de citações de referências bibliográficas utiliza o padrão Apalike do bibT E X.

show abstract

Protein Structural Class Determination Using Support Vector Machines

Cited by 12 publications

References 24 publications

Protein structural class prediction using support vector machine

Protein structural class prediction using support vector machine

A Tri-Gram Based Feature Extraction Technique Using Linear Probabilities of Position Specific Scoring Matrix for Protein Fold Recognition

"Investigação de estratégias para a geração de máquinas de vetores de suporte multiclasses"

Contact Info

Product

Resources

About