Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
11 results
Search Results
Article Developing a Label Propagation Approach for Cancer Subtype Classification Problem(TUBITAK, 2021) Güner, P.; Bakir-Güngör, B.; Coşkun, M.; Şahan, Pınar GünerCancer is a disease in which abnormal cells grow uncontrollably and invade other tissues. Several types of cancer have various subtypes with different clinical and biological implications. Based on these differences, treatment methods need to be customized. The identification of distinct cancer subtypes is an important problem in bioinformatics, since it can guide future precision medicine applications. In order to design targeted treatments, bioinformatics methods attempt to discover common molecular pathology of different cancer subtypes. Along this line, several computational methods have been proposed to discover cancer subtypes or to stratify cancer into informative subtypes. However, existing works do not consider the sparseness of data (genes having low degrees) and result in an ill-conditioned solution. To address this shortcoming, in this paper, we propose an alternative unsupervised method to stratify cancer patients into subtypes using applied numerical algebra techniques. More specifically, we applied a label propagation-based approach to stratify somatic mutation profiles of colon, head and neck, uterine, bladder, and breast tumors. We evaluated the performance of our method by comparing it to the baseline methods. Extensive experiments demonstrate that our approach highly renders tumor classification tasks by largely outperforming the state-of-the-art unsupervised and supervised approaches. © 2022 Elsevier B.V., All rights reserved.Article Forecasting the Consumer Price Index in Türkiye Using Machine Learning Models: A Comparative Analysis(Gazi Univ, 2025-09-01) Söylemez, İsmet; Ünlü, Ramazan; Nalici, Mehmet ErenThis study utilizes machine learning models to forecast Türkiye's Consumer Price Index (CPI), thereby addressing a critical gap in inflation prediction methodologies. The central research problem involves the forecasting of CPI in a volatile economic environment, which is essential for informed policymaking. The primary objective of this study is to evaluate the performance of three machine learning models, such as Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM), in forecasting CPI over periods ranging from one to six months, utilizing data from 2012 to 2024. The study's unique contribution lies in the application of the \"SelectKBest\" method, which identifies the most relevant indices, thereby enhancing the efficiency of the models. An ensemble method, Averaging Voting, is also employed to combine the strengths of these models, producing more accurate and robust predictions. The findings indicate that while the RF model consistently generates the most accurate forecasts across all shifts, the SVM model demonstrates a particular strength in the domain of short-term predictions. The ensemble model demonstrates a substantial performance improvement, with a R2 value of 0.962 for one-month ahead of estimates and 0.956 for five-month forecasts. This combined approach has been shown to outperform individual models, offering a more reliable framework for CPI forecasting. The findings offer valuable insights for economic policymakers, enabling more precise and stable inflation predictions in Türkiye.Article Citation - Scopus: 1eTNT: Enhanced Textnettopics With Filtered LDA Topics and Sequential Forward / Backward Topic Scoring Approaches(Science and Information Organization, 2024) Voskergian, Daniel; Jayousi, Rashid; Bakir-Güngör, 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. © 2024 Elsevier B.V., All rights reserved.Article Citation - WoS: 3Citation - Scopus: 4Prediction of Biomechanical Properties of Ex Vivo Human Femoral Cortical Bone Using Raman Spectroscopy and Machine Learning Algorithms(Elsevier, 2025-09) Unal, Mustafa; Unlu, Ramazan; Uppuganti, Sasidhar; Nyman, Jeffry S.This study applied Raman spectroscopy (RS) to ex vivo human cadaveric femoral mid-diaphysis cortical bone specimens (n = 118 donors; age range 21-101 years) to predict fracture toughness properties via machine learning (ML) models. Spectral features, together with demographic variables (age, sex) and structural parameters (cortical porosity, volumetric bone mineral density), were fed into support vector regression (SVR), extreme tree regression (ETR), extreme gradient boosting (XGB), and ensemble models to predict fracture-toughness metrics such as crack-initiation toughness (Kinit) and energy-to-fracture (J-integral). Feature selection was based on Raman-derived mineral and organic matrix parameters, such as nu 1Phosphate (PO4)/CH2-wag, nu 1PO4/ Amide I, and others, to capture the complex composition of bone. Our results indicate that ensemble models consistently outperformed individual models, with the best performance for crack initiation toughness (Kinit) prediction being achieved using the ensemble approach. This yielded a coefficient of determination (R2) of 0.623, root-mean squared error (RMSE) of 1.320, mean absolute error (MAE) of 1.015, and mean percentage absolute error (MAPE) of 0.134. For prediction of the overall energy to propagate a crack (J-integral), the XGB model achieved an R2 of 0.737, RMSE of 2.634, MAE of 2.283, and MAPE of 0.240. This study highlights the importance of incorporating mineral quality properties (MP) and organic matrix properties (OMP) for enhanced prediction accuracy. This work represents the first-ever study combining Raman spectroscopy with other clinical and structural features to predict fracture toughness of human cortical bone, demonstrating the potential of artificial intelligence (AI) and ML in advancing bone research. Future studies could focus on larger datasets and more advanced modeling techniques to further improve predictive capabilities.Article Citation - WoS: 1Citation - Scopus: 1PSO Supported Ensemble Algorithm for Bad Data Detection Against Intelligent Hacking Algorithm(Frontiers Media S.A., 2021-07-23) Yavuz, Levent; Soran, Ahmet; Onen, Ahmet; Muyeen, S. M.Power system cybersecurity has recently become important due to cyber-attacks. Due to advanced computer science and machine learning (ML) applications being used by malicious attackers, cybersecurity is becoming crucial to creating sustainable, reliable, efficient, and well-protected cyber-systems. Power system operators are needed to develop sophisticated detection mechanisms. In this study, a novel machine-learning-based detection algorithm that combines the five most popular ML algorithms with Particle Swarm Optimizer (PSO) is developed and tested by using an intelligent hacking algorithm that is specially developed to measure the effectiveness of this study. The hacking algorithm provides three different types of injections: random, continuous random, and slow injections by adaptive manner. This would make detection harder. Results shows that recall values with the proposed algorithm for each different type of attack have been increased.Article Citation - WoS: 2Citation - Scopus: 3Multi Fragment Melting Analysis System (MFMAS) for One-Step Identification of Lactobacilli(Elsevier, 2020-10) Kesmen, Zulal; Kilic, Ozge; Gormez, Yasin; Celik, Mete; Bakir-Gungor, BurcuThe accurate identification of lactobacilli is essential for the effective management of industrial practices associated with lactobacilli strains, such as the production of fermented foods or probiotic supplements. For this reason, in this study, we proposed the Multi Fragment Melting Analysis System (MFMAS)-lactobacilli based on high resolution melting (HRM) analysis of multiple DNA regions that have high interspecies heterogeneity for fast and reliable identification and characterization of lactobacilli. The MFMAS-lactobacilli is a new and customized version of the MFMAS, which was developed by our research group. MFMAS-lactobacilli is a combined system that consists of i) a ready-to-use plate, which is designed for multiple HRM analysis, and ii) a data analysis software, which is used to characterize lactobacilli species via incorporating machine learning techniques. Simultaneous HRM analysis of multiple DNA fragments yields a fingerprint for each tested strain and the identification is performed by comparing the fingerprints of unknown strains with those of known lactobacilli species registered in the MFMAS. In this study, a total of 254 isolates, which were recovered from fermented foods and probiotic supplements, were subjected to MFMAS analysis, and the results were confirmed by a combination of different molecular techniques. All of the analyzed isolates were exactly differentiated and accurately identified by applying the single-step procedure of MFMAS, and it was determined that all of the tested isolates belonged to 18 different lactobacilli species. The individual analysis of each target DNA region provided identification with an accuracy range from 59% to 90% for all tested isolates. However, when each target DNA region was analyzed simultaneously, perfect discrimination and 100% accurate identification were obtained even in closely related species. As a result, it was concluded that MFMAS-lactobacilli is a multi-purpose method that can be used to differentiate, classify, and identify lactobacilli species. Hence, our proposed system could be a potential alternative to overcome the inconsistencies and difficulties of the current methods.Article Citation - WoS: 3Citation - Scopus: 3MicroRNA Prediction Based on 3D Graphical Representation of RNA Secondary Structures(Tubitak Scientific & Technological Research Council Turkey, 2019-08-05) Sacar Demirci, Muserref Duygu; Demirci, Müşerref Duygu SaçarMicroRNAs (miRNAs) are posttranscriptional regulators of gene expression. While a miRNA can target hundreds of messenger RNA (mRNAs), an mRNA can be targeted by different miRNAs, not to mention that a single miRNA might have various binding sites in an mRNA sequence. Therefore, it is quite involved to investigate miRNAs experimentally. Thus, machine learning (ML) is frequently used to overcome such challenges. The key parts of a ML analysis largely depend on the quality of input data and the capacity of the features describing the data. Previously, more than 1000 features were suggested for miRNAs. Here, it is shown that using 36 features representing the RNA secondary structure and its dynamic 3D graphical representation provides up to 98% accuracy values. In this study, a new approach for ML-based miRNA prediction is proposed. Thousands of models are generated through classification of known human miRNAs and pseudohairpins with 3 classifiers: decision tree, naive Bayes, and random forest. Although the method is based on human data, the best model was able to correctly assign 96% of nonhuman hairpins from MirGeneDB, suggesting that this approach might be useful for the analysis of miRNAs from other species.Article Citation - WoS: 8Citation - Scopus: 10Lung Cancer Subtype Differentiation From Positron Emission Tomography Images(Tubitak Scientific & Technological Research Council Turkey, 2020-01-27) Ayyildiz, Oguzhan; Aydin, Zafer; Yilmaz, Bulent; Karacavus, Seyhan; Senkaya, Kubra; Icer, Semra; Kaya, Eser; Taşdemir, ArzuLung cancer is one of the deadly cancer types, and almost 85% of lung cancers are nonsmall cell lung cancer (NSCLC). In the present study we investigated classification and feature selection methods for the differentiation of two subtypes of NSCLC, namely adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). The major advances in understanding the effects of therapy agents suggest that future targeted therapies will be increasingly subtype specific. We obtained positron emission tomography (PET) images of 93 patients with NSCLC, 39 of which had ADC while the rest had SqCC. Random walk segmentation was applied to delineate three-dimensional tumor volume, and 39 texture features were extracted to grade the tumor subtypes. We examined 11 classifiers with two different feature selection methods and the effect of normalization on accuracy. The classifiers we used were the k-nearest-neighbor, logistic regression, support vector machine, Bayesian network, decision tree, radial basis function network, random forest, AdaBoostM1, and three stacking methods. To evaluate the prediction accuracy we performed a leave-one-out cross-validation experiment on the dataset. We also considered optimizing certain hyperparameters of these models by performing 10-fold cross-validation separately on each training set. We found that the stacking ensemble classifier, which combines a decision tree, AdaBoostM1, and logistic regression methods by a metalearner, was the most accurate method for detecting subtypes of NSCLC, and normalization of feature sets improved the accuracy of the classification method.Article Citation - WoS: 24Citation - Scopus: 24Circular RNA-MicroRNA Interaction Predictions in SARS-CoV Infection(Walter de Gruyter Gmbh, 2021-03-01) Demirci, Yilmaz Mehmet; Demirci, Muserref Duygu Sacar; Saçar Demirci, Müşerref DuyguDifferent types of noncoding RNAs like MicroRNAs (miRNAs) and circular RNAs (circRNAs) have been shown to take part in various cellular processes including post-transcriptional gene regulation during infection. MiRNAs are expressed by more than 200 organisms ranging from viruses to higher eukaryotes. Since miRNAs seem to be involved in host-pathogen interactions, many studies attempted to identify whether human miRNAs could target severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) mRNAs as an antiviral defence mechanism. In this work, a machine learning based miRNA analysis work flow was developed to predict differential expression patterns of human miRNAs during SARS-CoV-2 infection. In order to obtain the graphical representation of miRNA hairpins, 36 features were defined based on the secondary structures. Moreover, potential targeting interactions between human circRNAs and miRNAs as well as human miRNAs and viral mRNAs were investigated.Article Citation - WoS: 14Citation - Scopus: 20A Deep Learning Approach With Bayesian Optimization and Ensemble Classifiers for Detecting Denial of Service Attacks(Wiley, 2020-05-06) Gormez, Yasin; Aydin, Zafer; Karademir, Ramazan; Gungor, Vehbi C.Detecting malicious behavior is important for preventing security threats in a computer network. Denial of Service (DoS) is among the popular cyber attacks targeted at web sites of high-profile organizations and can potentially have high economic and time costs. In this paper, several machine learning methods including ensemble models and autoencoder-based deep learning classifiers are compared and tuned using Bayesian optimization. The autoencoder framework enables to extract new features by mapping the original input to a new space. The methods are trained and tested both for binary and multi-class classification on Digiturk and Labris datasets, which were introduced recently for detecting various types of DDoS attacks. The best performing methods are found to be ensembles though deep learning classifiers achieved comparable level of accuracy.