Browsing by Author "Gungor, Burcu Bakir"

Now showing 1 - 4 of 4

Comparison of Disease Specific Sub-Network Identification Programs
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2018) Adanur, Beyhun; Gungor, Burcu Bakir; AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü
Active sub-network search aims to identify a group of interconnected genes in a protein-protein interaction network that contains most of the disease-associated genes. In recent years, to address active sub-network search problem, various algorithms and programs are developed. In this study, performances of disease specific sub-network identification programs are compared. The same input dataset is run in jActiveModules, ActiveSubnetworkGA, CytoHubba, ClusterViz, MCODE, CytoMOBAS, PathFindR, PIN BPA and PEWCC programs. Then, functional enrichment analysis is applied on obtained sub-networks. Finally, they are compared according to the results of GO Enrichment Analysis. In addition to these, work performances, features and requirements of programs are compared.
An Ensemble Feature Selection Methodology That Incorporates Domain Knowledge for Cardiovascular Disease Diagnosis
(IEEE, 2020) Kolukisa, Burak; Güngör, Vehbi Çağrı; Gungor, Burcu Bakir; 0000-0003-0423-4595; 0000-0002-2272-6270; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Kolukisa, Burak; Güngör, Vehbi Çağrı; Gungor, Burcu Bakir
Koroner Arter Hastalığı (KAH), arterlerin duvarlarında aterom denilen yağlı madde birikiminin bir sonucu olarak kalbin yeterince beslenememesi durumudur. KAH, 2016 yılında dünyadaki toplam ölümlerin %31'ine (17,9 milyon) neden olmuştur ve teşhis edilmesi zordur. 2030 yılında, yaklaşık olarak 23,6 milyon insanın bu hastalıktan öleceği tahmin edilmektedir. Makine öğrenmesi ve veri madenciliği yöntemlerinin gelişmesiyle birlikte, bazı fiziksel ve biyokimyasal değerleri inceleyerek, KAH’nı ucuz ve zahmetsiz bir şekilde teşhis etmek mümkün olabilir. Bu çalışmada, KAH sınıflandırma problemi için, uzman bilgisini içine alan yeni bir topluluk öznitelik seçim yöntemi önerilmiştir. Önerilen çözüm, UCI Cleveland KAH veri kümesi üzerinde uygulanmış, farklı sınıflandırma algoritmaları kullanılarak, farklı performans ölçütleri karşılaştırılmıştır. Gerçekleştirdiğimiz deneylerde, önerdiğimiz çözümün, MLP sınıflandırıcısı ve seçilen 9 öznitelik kullanıldığında, %85.47 doğruluk, %82.96 hassasiyet ve 0.839 F-ölçüsüne ulaştığı gösterilmiştir. Bu çalışmanın devamında, hastanelerde gerçek zamanlı veriler üzerinde, hızlı bir şekilde KAH tahminlemesi yapabilecek bir makine öğrenmesi modeli oluşturabilmeyi amaçlıyoruz.
Identification of Shared Pathways Among Immune Related Diseases Utilizing Active Subnetworks
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2020) Eryilmaz, Mahmut Kaan; Kuzudisli, Cihan; Gungor, Burcu Bakir; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
Different, but related diseases often contain shared symptoms indicating the presence of possible overlaps in underlying pathogenic mechanisms. The identification of the shared pathways and related factors across these diseases helps to better understand the causes of these diseases, to prevent and treat these diseases. In this study, using immune-related diseases, we proposed a new method on how to compare the development mechanisms of related diseases based on biological pathways. Following the developments in genomic technologies, the genotyping gets cheaper and easier, and hence genome-wide association studies (GWAS) emerged. By this means, via studying big-sized case-control groups for a specific disease, potential genetic variations, single nucleotide polymorphisms (SNPs) could he identified. With the help of these studies, in which around a million of SNPs are scanned, the variations and genes that could have a role in specific disease development could be detected. In this study, via using available GWAS datasets and human protein-protein interaction network, and via detecting active subnetworks and affected pathways, seven immune related diseases are analyzed. Via investigating the similarities among the identified pathways for related diseases, we aim to define the underlying pathogenic mechanisms, and hence to contribute to the elucidation of disease development mechanisms and to the drug repositioning studies.
Investigation of Hepatocellular Carcinoma Molecular Mechanisms via in Silico Analyses
(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2020) Dogan, Refika Sultan; Saka, Samed; Gungor, Burcu Bakir; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
Hepatocellular carcinoma (HCC) is the most common cause of cancer-related death in the world. The molecular changes in the organism during the development of HCC are not fully understood. The aim of the present study is to contribute to the identification of critical genes and pathways associated with HCC via integrating various bioinformatics methods. In this study, experiments were conducted on gene expression data of 14 HCC tissues and non-cancerous control tissues. A total of 1229 genes, which show a statistically significant change between the groups, were identified. Among these, 681 genes were upregulated and 548 genes were downregulated. Via mapping the detected genes into protein protein interaction networks, active subnetwork search, subnetwork topological analysis and functional enrichment analyses were carried out. The interactions between the molecular pathways affected by HCC were also presented.