Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Abdullah Gül Univers...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

DIMENSIONALITY REDUCTION FOR PROTEIN SECONDARY STRUCTURE PREDICTION

Authors: Görmez, Yasin;

DIMENSIONALITY REDUCTION FOR PROTEIN SECONDARY STRUCTURE PREDICTION

Abstract

Gerekli metabolik süreçleri yürüten proteinler insan hayatı için büyük önemtaşımaktadır. Proteinlerin fonksiyonları ile üç boyutlu yapıları arasında yakın bir ilişkibulunmaktadır. Dört yapı düzeyi olan proteinlerin bir çoğunun, birincil yapı olarak daadlandırılan amino asit dizilimi bilinmekte ancak üçüncül yapıları bilinmemektedir.Üçüncül yapıların laboratuvar ortamında tespit edilmesinin çok maliyetli ve zor olması,amino asit dizilimini kullanarak yapı tahmini yapan sistemlerin geliştirilmesine nedenolmuştur. Protein yapı tahmini yapan sistemlerin en önemli aşamalarından biri iseikincil yapı etiketlerinin tanımlanması işlemidir. Yeni öznitelik çıkarma yaklaşımlarıgeliştirildikçe yapısal özelliklerin tahmini için kullanılan veri setleri yüksek boyutlarasahip olabilmekte ve kullanılan özniteliklerden bazıları gürültülü veri içerebilmektedir.Bu nedenle uygun sayıda ve doğru öznitelikleri seçmek, iyi bir başarı oranı elde etmekiçin önemli aşamalardan biridir. Bu çalışmada iki farklı veri seti üzerinde derin otokodlayıcı kullanılarak boyut düşürme işlemi uygulanmış, temel bileşen analizi, ki-kare,bilgi kazancı, kazanım oranı, korelasyon tabanlı öznitelik seçim teknikleri ve minimumfazlalık maksimum ilgi algoritması gibi çeşitli öznitelik seçim ve boyut düşürmeteknikleri ayrıca genetik algoritma, aç gözlü algoritma ve en iyi ilk önce algoritması gibiçeşitli arama stratejileri ile birlikte kullanılarak elde edilen veri setleri ilekarşılaştırılmıştır. İkincil yapı tahmin başarısının karşılaştırılması için destek vektörmakinası kullanılmıştır.

Proteins are important for our lives and they execute essential metabolic processes. Thefunctions of the proteins can be understood by looking at the three-dimensionalstructures of the proteins. Because the experimental detection of tertiary structure iscostly computational systems that estimate the structure provides a convenientalternative. One of the important steps of protein structure estimation is theidentification of secondary structure tags. As new feature extraction methods aredeveloped, the data sets used for this estimation can have high dimensions and some ofthe attributes can contain noisy data. For this reason, choosing the right number offeatures and the right attributes is one of the important steps to achieve a good successrate. In this study, size reduction process is applied on two different datasets using adeep autoencoder and various dimension reduction and feature selection techniquessuch as basic component analysis, chi-square, information gain, gain ratio, correlationbasedfeature selection (CFS) and the minimum redundancy maximum relevancealgorithm as well as search strategies such as best first, genetic search, greedyalgorithm. To evaluate the prediction accuracy, a support vector machine classifier isemployed.

68

Country
Turkey
Related Organizations
Keywords

Biyomühendislik, Deep Learning, Bioengineering, Autoencoder, Dimension Reduction, Feature Selection, Protein Secondary Structure Prediction, Computer Engineering and Computer Science and Control, Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 203
    download downloads 80
  • 203
    views
    80
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
203
80
Green