Profile URL: https://hdl.handle.net/20.500.12573/2677
Job Title:Doç. Dr.
Email Address:burcu.gungor@agu.edu.tr
Main Affiliation:02. 04. Bilgisayar Mühendisliği
Status: Current Staff
ORCID:
0000-0002-2272-6270
0000-0002-2272-6270Scopus ID:
25932029800
25932029800YÖK Akademik: E1BACF325F9A2BCB
Google Scholar:
4R2wbm8AAAAJ&hl
4R2wbm8AAAAJ&hlWeb of Science ID:
HCS-3124-2022
HCS-3124-2022Name Variants:
Bakir Gungor, Burcu Bakir-Gungor, Burcu
132 results
Scholarly Output Search Results
Now showing 1 - 10 of 132
Conference Object Citation - WoS: 1Citation - Scopus: 1Prediction of Type 2 Diabetes Using Metagenomic Data and Identification of Taxonomic Biomarkers(IEEE, 2024-05-15) Temiz, Mustafa; Kuzudisli, Cihan; Yousef, Malik; Bakir-Gungor, BurcuNowadays, different molecular levels of -omics data on diseases are generated and analyzing these data with machine learning methods is one of the popular research topics. Among these data, the use of metagenomic data to facilitate the diagnosis, detection and treatment of diseases is increasing day by day. Type 2 diabetes (T2D) is a chronic disease characterized by insulin resistance and progressive dysfunction of pancreatic beta cells. While the number of people with diabetes is increasing by around 8% annually, the cost of treating the disease is rising by 18% per year. Therefore, the number of studies on the diagnosis, development and progression of T2D is increasing over time. The aim of this study is to achieve higher machine learning performance by using fewer metagenomic features and to achieve better classification performance by reducing computational costs. In this study, we compare the performance of three different methods using T2D-related metagenomic data. First, the MetaPhlAn tool is used to calculate the taxonomic species and their relative abundances in each sample. The SVM-RCE, RCE-IFE and microBiomeGSM tools used in this study are methods that perform classification by grouping and scoring features and are known to work well on complex datasets. In this study, the best results were obtained with the RCE-IFE tool with an AUC of 0.72 with an average of 125 features information. In addition, key taxonomic species identified by these tools as associated with T2D are presented in comparison to the literature.Article Citation - WoS: 11Citation - Scopus: 9Ensemble Feature Selection for Clustering Damage Modes in Carbon Fiber-Reinforced Polymer Sandwich Composites Using Acoustic Emission(Wiley-VCH Verlag GmbH, 2024-07-15) Gulsen, Abdulkadir; Kolukisa, Burak; Caliskan, Umut; Bakir-Gungor, Burcu; Gungor, Vehbi CagriAcoustic emission (AE) serves as a noninvasive technique for real-time structural health monitoring, capturing the stress waves produced by the formation and growth of cracks within a material. This study presents a novel ensemble feature selection methodology to rank features highly relevant with damage modes in AE signals gathered from edgewise compression tests on honeycomb-core carbon fiber-reinforced polymer. Two distinct features, amplitude and peak frequency, are selected for labeling the AE signals. An ensemble-supervised feature selection method ranks feature importance according to these labels. Using the ranking list, unsupervised clustering models are then applied to identify damage modes. The comparative results reveal a robust correlation between the damage modes and the features of counts and energy when amplitude is selected. Similarly, when peak frequency is chosen, a significant association is observed between the damage modes and the features of partial powers 1 and 2. These findings demonstrate that, in addition to the commonly used features, other features, such as partial powers, exhibit a correlation with damage modes. This article presents a novel ensemble feature selection methodology to rank features relevant to damage modes on acoustic emission signals in carbon fiber-reinforced polymer sandwich composites. Subsequently, ranked features are utilized in unsupervised clustering models to identify damage modes. The comparative results demonstrate that, along with common features, other features, like partial powers, have a robust correlation with damage modes.image (c) 2024 WILEY-VCH GmbHArticle Citation - WoS: 17Citation - Scopus: 23GeNetOntology: Identifying Affected Gene Ontology Terms via Grouping, Scoring, and Modeling of Gene Expression Data Utilizing Biological Knowledge-Based Machine Learning(Frontiers Media S.A., 2023-08-21) Ersoz, Nur Sebnem; Bakir-Gungor, Burcu; Yousef, MalikIntroduction: Identifying significant sets of genes that are up/downregulated under specific conditions is vital to understand disease development mechanisms at the molecular level. Along this line, in order to analyze transcriptomic data, several computational feature selection (i.e., gene selection) methods have been proposed. On the other hand, uncovering the core functions of the selected genes provides a deep understanding of diseases. In order to address this problem, biological domain knowledge-based feature selection methods have been proposed. Unlike computational gene selection approaches, these domain knowledge-based methods take the underlying biology into account and integrate knowledge from external biological resources. Gene Ontology (GO) is one such biological resource that provides ontology terms for defining the molecular function, cellular component, and biological process of the gene product.Methods: In this study, we developed a tool named GeNetOntology which performs GO-based feature selection for gene expression data analysis. In the proposed approach, the process of Grouping, Scoring, and Modeling (G-S-M) is used to identify significant GO terms. GO information has been used as the grouping information, which has been embedded into a machine learning (ML) algorithm to select informative ontology terms. The genes annotated with the selected ontology terms have been used in the training part to carry out the classification task of the ML model. The output is an important set of ontologies for the two-class classification task applied to gene expression data for a given phenotype.Results: Our approach has been tested on 11 different gene expression datasets, and the results showed that GeNetOntology successfully identified important disease-related ontology terms to be used in the classification model.Discussion: GeNetOntology will assist geneticists and scientists to identify a range of disease-related genes and ontologies in transcriptomic data analysis, and it will also help doctors design diagnosis platforms and improve patient treatment plans.Conference Object Protein-Protein Etkilesim Ağlarinda Aktif Alt Ağ Arama Yöntemlerinin Performans Degerlendirmeleri(Institute of Electrical and Electronics Engineers Inc., 2019-09) Güner, Pinar; Bakir-Güngör, BurcuProtein-protein interaction networks are mathematical representations of the physical contacts between proteins in the cell. A group of interconnected proteins in a protein-protein interaction network that contains most of the disease associated proteins and some interacting other proteins is called an active subnetwork. Active subnetwork search is important to understand mechanisms underlying diseases. Active subnetworks are used to discover disease related regulatory pathways, functional modules and to classify diseases. In the literature there are many methods to search for active subnetworks. The purpose of this study is to compare the performance of different subnetwork identification methods. By using the Rheumatoid Arthritis dataset, the performances of greedy approach, genetic algorithm, simulated annealing algorithm, prize collecting steiner forest and game theory based subnetwork search methods are compared. © 2020 Elsevier B.V., All rights reserved.Article ETNT: Enhanced Textnettopics With Filtered LDA Topics and Sequential Forward / Backward Topic Scoring Approaches(Science & information Sai Organization Ltd, 2024) Voskergian, Daniel; Jayousi, Rashid; Bakir-Gungor, BurcuTextNetTopics is a novel text classification-based topic modelling approach that focuses on topic selection rather than individual word selection to train a machine learning algorithm. However, one key limitation of TextNetTopics is its scoring component, which evaluates each topic in isolation and ranks them accordingly, ignoring the potential relationships between topics. In addition, the chosen topics may contain redundant or irrelevant features, potentially increasing the feature set size and introducing noise that can degrade the overall model performance. To address these limitations and improve the classification performance, this study introduces an enhancement to TextNetTopics. eTNT integrates two novel scoring approaches: Sequential Forward Topic Scoring (SFTS) and Sequential Backward Topic Scoring (SBTS), which consider topic interactions by assessing sets of topics simultaneously. Moreover, it incorporates a filtering component that aims to enhance topics' quality and discriminative power by removing non-informative features from each topic using Random Forest feature importance values. These integrations aim to streamline the topic selection process and enhance classifier efficiency for text classification. The results obtained from the WOS-5736, LitCovid, and MultiLabel datasets provide valuable insights into the superior effectiveness of eTNT compared to its counterpart, TextNetTopics.Conference Object Performance Evaluations of Active Subnetwork Search Methods in Protein-Protein Interaction Networks(IEEE, 2019) Gunter, Pinar; Bakir-Gungor, BurcuProtein-protein interaction networks are mathematical representations of the physical contacts between proteins in the cell. A group of interconnected proteins in a protein-protein interaction network that contains most of the disease associated proteins and some interacting other proteins is called an active subnetwork. Active subnetwork search is important to understand mechanisms underlying diseases. Active subnetworks are used to discover disease related regulatory pathways, functional modules and to classify diseases. In the literature there arc many methods to search for active subnetworks. The purpose of this study is to compare the performance of different subnetwork identification methods. By using the Rheumatoid Arthritis dataset, the performances of greedy approach, genetic algorithm, simulated annealing algorithm, prize collecting steiner forest and game theory based subnetwork search methods are compared.Article Citation - WoS: 28Citation - Scopus: 34miRcorrNet: Machine Learning-Based Integration of miRNA and mRNA Expression Profiles, Combined with Feature Grouping and Ranking(PeerJ Inc., 2021-05-19) Yousef, M.; Göy, G.; Mitra, R.; Eischen, C.M.; Jabeer, A.; Bakir-Güngör, B.A better understanding of disease development and progression mechanisms at the molecular level is critical both for the diagnosis of a disease and for the development of therapeutic approaches. The advancements in high throughput technologies allowed to generate mRNA and microRNA (miRNA) expression profiles; and the integrative analysis of these profiles allowed to uncover the functional effects of RNA expression in complex diseases, such as cancer. Several researches attempt to integrate miRNA and mRNA expression profiles using statistical methods such as Pearson correlation, and then combine it with enrichment analysis. In this study, we developed a novel tool called miRcorrNet, which performs machine learning-based integration to analyze miRNA and mRNA gene expression profiles. miRcorrNet groups mRNAs based on their correlation to miRNA expression levels and hence it generates groups of target genes associated with each miRNA. Then, these groups are subject to a rank function for classification. We have evaluated our tool using miRNA and mRNA expression profiling data downloaded from The Cancer Genome Atlas (TCGA), and performed comparative evaluation with existing tools. In our experiments we show that miRcorrNet performs as good as other tools in terms of accuracy (reaching more than 95% AUC value). Additionally, miRcorrNet includes ranking steps to separate two classes, namely case and control, which is not available in other tools. We have also evaluated the performance of miRcorrNet using a completely independent dataset. Moreover, we conducted a comprehensive literature search to explore the biological functions of the identified miRNAs. We have validated our significantly identified miRNA groups against known databases, which yielded about 90% accuracy. Our results suggest that miRcorrNet is able to accurately prioritize pan-cancer regulating high-confidence miRNAs. miRcorrNet tool and all other supplementary files are available at https://github.com/ malikyousef/miRcorrNet. © 2021 Elsevier B.V., All rights reserved.Article Citation - Scopus: 8Network Anomaly Detection Using Deep Autoencoder and Parallel Artificial Bee Colony Algorithm-Trained Neural Network(PeerJ Inc., 2024-10-08) Dedeturk, Bilge Kagan; Bakir-Gungor, Burcu; Hacılar, Hilal; Gungor, Vehbi CagriConference Object Tip 2 Diyabet'te Etkilenen Yolak Alt Ağlarını Bulmak İçin Yukarıdan Aşağıya İşleyen Bir Yaklaşım(IEEE, 2020-10-05) Unlu Yazici, Miray; Bakir-Gungor, BurcuDiabetes Mellitus (DM) is a metabolic disorder caused by dysfunction of insulin-producing pancreatic beta cells, insulin resistance, or impairment of insulin functionality. Type 2 Diabetes Mellitus (T2D) is a complex multifactorial disease that accounts for 90% of diabetes cases. In recent years, genome-wide association studies (GWAS) have successfully identified genetic variants associated with T2D risk. However, while conventional GWAS analyses focus on 'the tip of the iceberg' single nucleotide polymorphisms (SNPs), new analysis methods are needed to uncover hidden variations in these studies. In our previous study, we developed a post-GWAS analysis methodology to find disease-associated marker pathways by integrating human protein-protein interaction network, known biological pathways and potential SNPs. In this study, via adding different in-silico approaches to our methodology, we aim to identify affected pathway subnetworks and affected pathway clusters in addition to the affected protein subnetworks in T2D, and consequently to enlighten molecular mechanisms of T2D. Using this proposed method, we analyzed T2D GWAS meta-analysis data including 12.931 cases ye 57.196 controls. The approach we presented here is based on both the significance value of affected pathway and its topological relationship with other neighbor pathways. In the functional enrichment stage of our method, important pathways were obtained using hypergeometric test and gene-pathway matrix was formed. Then pathway-pathway similarity values were calculated using Jaccard index. Using the scores obtained in the similarity matrix, pathway-pathway network was constructed, and disease-related pathway modules were obtained using subnetwork search algorithms. As a result, genes, pathways and pathway subnetworks that might have a potential role in T2D development were identified, and the categories and classes that are related with these affected pathways were determined.Conference Object In-silico Identification of Papillary Thyroid Carcinoma Molecular Mechanisms(IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2019-04) Ersoz, Nur Sebnem; Guzel, Yasin; Bakir-Gungor, BurcuRepresenting approximately 70% to 80% of thyroid cancers, papillary thyroid cancer (PTC) is the most common type of thyroid cancers. PTC is seen in all age groups, but it is seen more frequently in women than in men. Detection of biomarker proteins of papillary thyroid cancinoma plays an important role in the diagnosis of the disease. In this study, we aim to find target genes and pathways that are associated with papillar thyroid carcinoma, by integrating different bioinformatics methods. For this purpose, usingin-silico methodologies, candidate genes and pathways that could explain disease development mechanisms are identified. Throughout this study, firstly we identified differentially expressed genes as the amount of their protein product differ between patient and healthy groups. Secondly, by using active subnetworks search algorithms, topologic analyses and functional enrichment tests, candidate proteins,which could be thought as PTC biomarkers, and affected pathways are identified.