SVM-based detection of distant protein structural relationships using pairwise probabilistic suffix trees

Ogul, Hasan; Mumcuoğlu, Erkan í.

doi:10.1016/j.compbiolchem.2006.05.001

Cited by 20 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For more details of SVMs, please refer Burges (1998), Vapnik (1998), Schölkopf and Smola (2002). Furthermore, SVMs have been used in many fields of bioinformatics such as splice site prediction, protein structural relationship prediction and microarray analysis and so on Phan et al 2005;Baten et al 2006;Ogul and Mumcuoglu 2006;Towsey et al 2006;Wee et al 2006;Huang et al 2007 …”

Section: Encoding the Dre-containing Sequencesmentioning

confidence: 99%

An in silico strategy identified the target gene candidates regulated by dehydration responsive element binding proteins (DREBs) in Arabidopsis genome

et al. 2008

View full text Add to dashboard Cite

Identification of downstream target genes of stress-relating transcription factors (TFs) is desirable in understanding cellular responses to various environmental stimuli. However, this has long been a difficult work for both experimental and computational practices. In this research, we presented a novel computational strategy which combined the analysis of the transcription factor binding site (TFBS) contexts and machine learning approach. Using this strategy, we conducted a genome-wide investigation into novel direct target genes of dehydration responsive element binding proteins (DREBs), the members of AP2-EREBPs transcription factor super family which is reported to be responsive to various abiotic stresses in Arabidopsis. The genome-wide searching yielded in total 474 target gene candidates. With reference to the microarray data for abiotic stresses-inducible gene expression profile, 268 target gene candidates out of the total 474 genes predicted, were induced during the 24-h exposure to abiotic stresses. This takes about 57% of total predicted targets. Furthermore, GO annotations revealed that these target genes are likely involved in protein amino acid phosphorylation, protein binding and Endomembrane sorting system. The results suggested that the predicted target gene candidates were adequate to meet the essential biological principle of stress-resistance in plants.

show abstract

Section: Encoding the Dre-containing Sequencesmentioning

confidence: 99%

An in silico strategy identified the target gene candidates regulated by dehydration responsive element binding proteins (DREBs) in Arabidopsis genome

et al. 2008

View full text Add to dashboard Cite

show abstract

“…Olasılıksal Sonek Ağacının örüntü tahmininde anlamlı sonuçlar ürettiği bilinmektedir [22][23][24][25][26][27]. Transkripsiyon faktörü için bağlanma konumlarında bulunan kısa örüntü olarak tanımlanan motifler, bulunduğu DNA dizilimlerinde geçen diğer tahmin edilecek motifler ile ilgili benzer bilgiler içerebilmektedir.…”

Section: öNerilen Yöntemunclassified

“…Benzer olarak G Protein-Çifti Reseptör (GPCR) sınıflandırması için kullanımı bulunmaktadır [25]. OSA'nın başka bir geliştirilmiş sürümü olan İkili-OSA [26] kullanılarak Destek Vektör Makinesi tabanlı tespit işlemi yapan protein sınıflandırma yöntemi geliştirilmiştir. Protein dizilim analizi yapmak için OSA'nın gelişmiş bir biçimi olan düzleştirilmiş OSA kullanılmıştır [27].…”

Section: Introductionunclassified

Predicting motifs in human and mouse genes by using Probabilistic Suffix Trees

Yıldız

Sert

2010

2010 15th National Biomedical Engineering Meeting

View full text Add to dashboard Cite

ÖzetçeGen ifadelerini düzenleyen mekanizmaların anlaşılması, moleküler biyolojideki önemli araştırma konularından birisidir. Bu konudaki önemli problemlerden birisi, transkripsiyon (yazım) faktörleri için Deoksiribonükleik Asit'te (DNA) bulunan bağlanma konumları gibi düzenleyici elemanları (motifleri) tanıma işlemidir. Bu çalışmada insan ve fare genlerinde bulunan motiflerin tahmini için Olasılıksal Sonek Ağacı (OSA) kullanan bir yöntem önerilmiştir. Deneysel sonuçlar on üç farklı motif bulma araçları ile karşılaştırmalı olarak değerlendirilmiştir. Elde edilen sonuçlar, önerilen yöntemin karşılaştırılan diğer yöntemlerden, nükleotid seviyesinde duyarlılık (nSn) değerine göre daha iyi sonuçlar verdiğini göstermiştir. AbstractThe identification of regulatory elements (motifs) is a challenging task in mollecular biology. An important challenge in this study is to identify regulatory elements (motifs), notably the binding sites in Deocsiribonucleic Acid (DNA) for transcription factors. Based on this motivation we propose a method for motif prediction of mouse and human genes by using Probabilistic Suffix Tree (PST). Experimental results are evaluated comparatively by thirteen distinct motif prediction tools. Our results show that, the proposed method gives a better recognition rate than the compared motif prediction tools, where the recognition rate is nucleotide level sensitivity (nSn).

show abstract

“…The PST method was introduced by Bejerano and Yona to model the protein families [15]. The original PST model was based on identifying significant short segments among the many input sequences, regardless of the relative position of these segments within the different proteins [16]. In this study, to classify a sequence into one of the families, a separate PST is constructed for each family in the data set, and according to the probability distribution over PST, a probability that the sequence belongs to that family is assigned to the query sequence.…”

Section: A Generative Approach: Variable Length Markov Chainmentioning

confidence: 99%

Predicting Metal-Binding Sites of Protein Residues

Küçükbay

Ogul

2015

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Abstract-Metal ions in protein are critical to the function, structure and stability of protein. For this reason accurate prediction of metal binding sites in protein is very important. Here, we present our study which is performed for predicting metal binding sites for histidines (HIS) and cysteines from protein sequence. Three different methods are applied for this task: Support Vector Machine (SVM), Naive Bayes and Variable-length Markov chain. All these methods use only sequence information to classify a residue as metal binding or not. Several feature sets are employed to evaluate impact on prediction results. We predict metal binding sites for mentioned amino acids at 35% precision and 75% recall with Naive Bayes, at 25% precision and 23% recall with Support Vector Machine and at 0.05% precision and 60% recall with Variable-length Markov chain. We observe significant differences in performance depending on the selected feature set. The results show that Naive Bayes is competitive for metal binding site detection. I. INTRODUCTIONProtein plays a crucial role in all biological processes. And they consist of one or more long chains of amino acid residues. In the frame of this perspective, amino acids are important ligands with nitrogen and oxygen as the donor, constituent of many biological important molecules [1].It is estimated that approximately half of all proteins contain a metal [2]. A significant fraction (about one third) of all known proteins is believed to bind metal ions as cofactors in their native conformation [3]. The biological activities of proteins require these cofactors to assist their daily routines. For this reason, a metal ion in a protein and prediction of its binding point is very important to understand the function of proteins in biological activities. Metal ions in proteins are responsible for multiple tasks. They help stabilizing protein structure [4], induce conformational changes [5][6][7], and assist protein functions (e.g. electron transfer, nucleophilic catalysis).There are many related studies about predicting metal binding sites, however, machine learning techniques have been recently applied to predict the metal binding sites of residues. Predicting metal binding sites by using non-computational methods has some drawbacks.X-ray absorption spectroscopy (HT-XAS) has been recently proved to be capable of identifying metalloproteins with high reliability [8,9]. However, the specific ligands involved in binding metal ion(s) cannot be identified by these techniques [9]. Motif-based system has also been developed by using regular expressions but since regular expressions can be quite specific, their results have many false negatives. To overcome these drawbacks, many computational learning techniques have been developed to predict metal binding sites. Early approaches can be found in the work of Nakata et al. (1995). In this study, they focused on predicting zincfinger DNA-binding proteins with a neural network. In this approach, applicable results were generated by a method for c...

show abstract

SVM-based detection of distant protein structural relationships using pairwise probabilistic suffix trees

Cited by 20 publications

References 19 publications

An in silico strategy identified the target gene candidates regulated by dehydration responsive element binding proteins (DREBs) in Arabidopsis genome

An in silico strategy identified the target gene candidates regulated by dehydration responsive element binding proteins (DREBs) in Arabidopsis genome

Predicting motifs in human and mouse genes by using Probabilistic Suffix Trees

Predicting Metal-Binding Sites of Protein Residues

Contact Info

Product

Resources

About