Protein solvent accessibility prediction using support vector machines and sequence conservations

Date

2006-01-01

Author

Ogul, Hasan
Mumcuoğlu, Ünal Erkan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

240
views

0
downloads

A two-stage method is developed for the single sequence prediction of protein solvent accessibility from solely its amino acid sequence. The first stage classifies each residue in a protein sequence as exposed or buried using support vector machine (SVM). The features used in the SVM are physicochemical properties of the amino acid to be predicted as well as the information coming from its neighboring residues. The SVM-based predictions are refined using pairwise conservative patterns, called maximal unique matches (MUMs). The MUMs are identified by an efficient data structure called suffix tree. The baseline predictions, SVM-based predictions and MUM-based refinements are tested on a nonredundant protein data set and similar to 73% prediction accuracy is achieved for a solvent accessibility threshold that provides an evenly distribution between buried and exposed classes. The results demonstrate that the new method achieves slightly better accuracy than recent methods using single sequence prediction.

Subject Keywords

Secondary structure

URI

https://hdl.handle.net/11511/55538

Journal

ARTIFICIAL INTELLIGENCE AND NEURAL NETWORKS

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Synthesis and Stimuli-Responsive Properties of Metallo-Supramolecular Phosphazene Polymers Based on Terpyridine Metal Complexes Sezer, Selda; KÖYTEPE, SÜLEYMAN; GÜLTEK, AHMET; SEÇKİN, TURGAY (2021-08-01) In this study, terpyridine functionalized phosphazene based metallo-supramolecular polymers were synthesized by three step reaction method. In the first step, 4 '-(4-aminophenyl)-2,2 ':6 ',2 ''-terpyridine was synthesized with p-nitro benzaldehyde and 2-acetylpyridine. Then, the monomer containing six terpyridine (TPY) units attached to the phosphazene was prepared from 4 '-(4-aminophenyl)-2,2 ':6 ',2 ''-terpyridine and hexachlorocyclotriphosphazene by a condensation reaction. Finally, metallo-supramolecula...
Protein adsorption and transport in dextran-modified ion-exchange media. I: Adsorption Bowes, Brian D.; Koku, Harun; Czymmek, Kirk J.; Lenhoff, Abraham M. (Elsevier BV, 2009-11-06) Adsorption behavior is compared on a traditional agarose-based ion-exchange resin and on two dextran-modified resins, using three proteins to examine the effect of protein size. The latter resins typically exhibit higher static capacities at low ionic strengths and electron microscopy provides direct visual evidence supporting the view that the higher static capacities are due to the larger available binding volume afforded by the dextran. However, isocratic retention experiments reveal that the larger prot...
Amino acid substitution matrices based on 4-body Delaunay contact profiles Sacan, Ahmet; Toroslu, İsmail Hakkı (2007-10-17) Sequence similarity search of proteins is one of the basic and most common steps followed in bioninformatics research and is used in making evolutionary, structural, and functional inferences. The quality of the search and the alignment of the protein sequences depend crucially on the underlying amino-acid substitution matrix. We present a method for deriving amino acid substitution matrices from 4-body contact propensities of amino-acids in 3D protein structures. Unlike current popular methods, our method ...
Enzyme prediction with word embedding approach Akın, Erkan; Atalay, M. Volkan.; Department of Computer Engineering (2019) Information such as molecular function, biological process, and cellular localization can be inferred from the protein sequence. However, protein sequences vary in length. Therefore, the sequence itself cannot be used directly as a feature vector for pattern recognition and machine learning algorithms since these algorithms require fixed length feature vectors. We describe an approach based on the use of the Word2vec model, more specifically continuous skip-gram model to generate the vector representation o...
Protein-based complex medium design for recombinant serine alkaline protease production Çalık, Pınar; Telli, IE; Oktar, C; Ozdemir, E (Elsevier BV, 2003-12-02) This work reports on the design of a complex medium based on simple and complex carbon sources, i.e. glucose, sucrose, molasses, and defatted-soybean, and simple and complex nitrogen sources, i.e. (NH4)(2)HPO4, casein, and defatted-soybean, for serine alkaline protease (SAP) production by recombinant Bacillus subtilis carrying pHV1431::subC gene. SAP activity was obtained as 3050 U cm(-3) with the initial defatted-soybean concentration C-soybean(o) = 20 kg m(-3) and initial glucose concentration C-G(o) = 8 ...

Citation Formats

H. Ogul and Ü. E. Mumcuoğlu, “Protein solvent accessibility prediction using support vector machines and sequence conservations,” ARTIFICIAL INTELLIGENCE AND NEURAL NETWORKS, pp. 141–148, 2006, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/55538.