Yazar "Aydin, Zafer" seçeneğine göre listele

Listeleniyor 1 - 9 / 9
  • Küçük Resim Yok
    Öğe
    Comparative analysis of machine learning approaches for predicting respiratory virus infection and symptom severity
    (Peerj Inc, 2023) Isik, Yunus Emre; Aydin, Zafer
    Respiratory diseases are among the major health problems causing a burden on hospitals. Diagnosis of infection and rapid prediction of severity without time-consuming clinical tests could be beneficial in preventing the spread and progression of the disease, especially in countries where health systems remain incapable. Personalized medicine studies involving statistics and computer technologies could help to address this need. In addition to individual studies, competitions are also held such as Dialogue for Reverse Engineering Assessment and Methods (DREAM) challenge which is a community-driven organization with a mission to research biology, bioinformatics, and biomedicine. One of these competitions was the Respiratory Viral DREAM Challenge, which aimed to develop early predictive biomarkers for respiratory virus infections. These efforts are promising, however, the prediction performance of the computational methods developed for detecting respiratory diseases still has room for improvement. In this study, we focused on improving the performance of predicting the infection and symptom severity of individuals infected with various respiratory viruses using gene expression data collected before and after exposure. The publicly available gene expression dataset in the Gene Expression Omnibus, named GSE73072, containing samples exposed to four respiratory viruses (H1N1, H3N2, human rhinovirus (HRV), and respiratory syncytial virus (RSV)) was used as input data. Various preprocessing methods and machine learning algorithms were implemented and compared to achieve the best prediction performance. The experimental results showed that the proposed approaches obtained a prediction performance of 0.9746 area under the precision-recall curve (AUPRC) for infection (i.e., shedding) prediction (SC-1), 0.9182 AUPRC for symptom class prediction (SC-2), and 0.6733 Pearson correlation for symptom score prediction (SC-3) by outperforming the best leaderboard scores of Respiratory Viral DREAM Challenge (a 4.48% improvement for SC-1, a 13.68% improvement for SC-2, and a 13.98% improvement for SC-3). Additionally, over-representation analysis (ORA), which is a statistical method for objectively determining whether certain genes are more prevalent in pre-defined sets such as pathways, was applied using the most significant genes selected by feature selection methods. The results show that pathways associated with the 'adaptive immune system' and 'immune disease' are strongly linked to pre-infection and symptom development. These findings contribute to our knowledge about predicting respiratory infections and are expected to facilitate the development of future studies that concentrate on predicting not only infections but also the associated symptoms.
  • Küçük Resim Yok
    Öğe
    Comparison of Machine Learning Classifiers for Protein Secondary Structure Prediction
    (IEEE, 2018) Aydin, Zafer; Kaynar, Oguz; Gormez, Yasin; Isik, Yunus Emre
    Three-dimensional structure prediction is one of the important problems in bioinformatics and theoretical chemistry. One of the most important steps in the three-dimensional structure prediction is the estimation of secondary structure. Due to rapidly growing databases and recent feature extraction methods datasets used for predicting secondary structure can potentially contain a large number of samples and dimensions. For this reason, it is important to use algorithms that are fast and accurate. In this study, various classification algorithms have been optimized for the second phase of a two-stage classifier on EVAset benchmark both in the original input space and in the space reduced using the information gain metric. The most accurate classifier is obtained as the support vector machine while the extreme learning machine is significantly faster in model training.
  • Küçük Resim Yok
    Öğe
    Comparison of NR and UniClust Databases for Protein Secondary Structure Prediction
    (IEEE, 2018) Aydin, Zafer; Kaynar, Oguz; Gormez, Yasin
    Three-dimensional structure prediction is one of the important problems in bioinformatics and theoretical chemistry. One of the most important steps in the three-dimensional structure prediction is the estimation of secondary structure. Improving the accuracy rate in protein secondary structure prediction depends on computed attributes as well as the classification algorithms. In multiple alignment methods, which are often used to extract an attribute, the calculated values differ according to the database used for the alignment. For this reason, it is important to use a suitable database against which the target proteins are aligned to compute profile feature vectors. In this study, 5 different datasets are generated for the CB513 benchmark with the aid of two different alignment methods and three different databases. The profile features are fed as input to a two-stage hybrid classifier. According to the experimental results, the highest accuracy rate is obtained when UniClust database is used at the first stage of HHBlits alignment to calculate PSSM values and NR database is used at the first stage of HHBlits alignment to calculate structural profile matrices.
  • Küçük Resim Yok
    Öğe
    Dimensionality reduction for protein secondary structure and solvent accesibility prediction
    (IMPERIAL COLLEGE PRESS, 2018) Aydin, Zafer; Kaynar, Oguz; Gormez, Yasin
    Secondary structure and solvent accessibility prediction provide valuable information for estimating the three dimensional structure of a protein. As new feature extraction methods are developed the dimensionality of the input feature space increases steadily. Reducing the number of dimensions provides several advantages such as faster model training, faster prediction and noise elimination. In this work, several dimensionality reduction techniques have been employed including various feature selection methods, autoencoders and PCA for protein secondary structure and solvent accessibility prediction. The reduced feature set is used to train a support vector machine at the second stage of a hybrid classifier. Cross-validation experiments on two difficult benchmarks demonstrate that the dimension of the input space can be reduced substantially while maintaining the prediction accuracy. This will enable the incorporation of additional informative features derived for predicting the structural properties of proteins without reducing the accuracy due to overfitting.
  • Küçük Resim Yok
    Öğe
    Feature Selection for Protein Dihedral Angle Prediction
    (IEEE, 2017) Aydin, Zafer; Kaynar, Oguz; Gormez, Yasin; Koyuncu, B; Tomar, GS
    Three-dimensional structure prediction has crucial importance for bioinformatics and theoretical chemistry. One of the main steps of three-dimensional structure prediction is dihedral (torsion) angle prediction. As new feature extraction methods are developed the dimension of the input space increases considerably yielding longer model training and less accurate models due to noisy or redundant features. In this study, feature selection is employed for dimensionality reduction on one of the established benchmarks of protein 1D structure prediction. Experimental results show that the feature selection improves the accuracy of protein dihedral angle class prediction by 2% and can eliminate up to %82 of the features when random forest classifier is used. Accurate prediction of dihedral angles will eventually contribute to protein structure prediction.
  • Küçük Resim Yok
    Öğe
    IGPRED-MultiTask: A Deep Learning Model to Predict Protein Secondary Structure, Torsion Angles and Solvent Accessibility
    (IEEE Computer Soc, 2023) Gormez, Yasin; Aydin, Zafer
    Protein secondary structure, solvent accessibility and torsion angle predictions are preliminary steps to predict 3D structure of a protein. Deep learning approaches have achieved significant improvements in predicting various features of protein structure. In this study, IGPRED-Multitask, a deep learning model with multi task learning architecture based on deep inception network, graph convolutional network and a bidirectional long short-term memory is proposed. Moreover, hyper-parameters of the model are fine-tuned using Bayesian optimization, which is faster and more effective than grid search. The same benchmark test data sets as in the OPUS-TASS paper including TEST2016, TEST2018, CASP12, CASP13, CASPFM, HARD68, CAMEO93, CAMEO93_HARD, as well as the train and validation sets, are used for fair comparison with the literature. Statistically significant improvements are observed in secondary structure prediction on 4 datasets, in phi angle prediction on 2 datasets and in psi angel prediction on 3 datasets compared to the state-of-the-art methods. For solvent accessibility prediction, TEST2016 and TEST2018 datasets are used only to assess the performance of the proposed model.
  • Küçük Resim Yok
    Öğe
    IGPRED: Combination of convolutional neural and graph convolutional networks for protein secondary structure prediction
    (Wiley, 2021) Gormez, Yasin; Sabzekar, Mostafa; Aydin, Zafer
    There is a close relationship between the tertiary structure and the function of a protein. One of the important steps to determine the tertiary structure is protein secondary structure prediction (PSSP). For this reason, predicting secondary structure with higher accuracy will give valuable information about the tertiary structure. Recently, deep learning techniques have obtained promising improvements in several machine learning applications including PSSP. In this article, a novel deep learning model, based on convolutional neural network and graph convolutional network is proposed. PSIBLAST PSSM, HHMAKE PSSM, physico-chemical properties of amino acids are combined with structural profiles to generate a rich feature set. Furthermore, the hyper-parameters of the proposed network are optimized using Bayesian optimization. The proposed model IGPRED obtained 89.19%, 86.34%, 87.87%, 85.76%, and 86.54% Q3 accuracies for CullPDB, EVAset, CASP10, CASP11, and CASP12 datasets, respectively.
  • Küçük Resim Yok
    Öğe
    NSEM: Novel Stacked Ensemble Method for Sentiment Analysis
    (IEEE, 2018) Emre Isik, Yunus; Gormez, Yasin; Kaynar, Oguz; Aydin, Zafer
    Today, people often share their ideas, opinions and feelings through forums, social media sites, blogs and similar platforms. For this reason, access to these data has become very easy. Increase in the number of shares makes it possible to analyze and use these data in terms of marketing and politics. However, due to the large number of data, it is impossible that this analysis will be done by humans. Determination of what type of emotion is included automatically is done by sentiment analysis methods. In these methods, the text is defined as a mathematical vector and classified by machine learning methods. Ensemble methods are one of the most important methods used as classifiers in sentiment analysis. In these methods, a classifier error is tried to be solved by another classifier. In sentiment analysis, the feature vector that describes the text is as important as the classifier. Feature vectors obtained using different methods can make mistakes in different places. For this reason, in this study, NSEM is proposed for sentiment analysis, which is a new ensemble method that uses 2 different classifiers and 2 different feature extraction methods. As a result of the analysis, the proposed method is the most successful method with an accuracy rate of 79.1%.
  • Küçük Resim Yok
    Öğe
    The Determination of Distinctive Single Nucleotide Polymorphism Sets for the Diagnosis of Behcet's Disease
    (IEEE Computer Soc, 2022) Isik, Yunus Emre; Gormez, Yasin; Aydin, Zafer; Bakir-Gungor, Burcu
    Behcet's Disease (BD) is a multi-system inflammatory disorder in which the etiology remains unclear. The most probable hypothesis is that genetic tendency and environmental factors play roles in the development of BD. In order to find the essential reasons, genetic changes on thousands of genes should be analyzed. Besides, there is a need for extra analysis to find out which genetic factor affects the disease. Machine learning approaches have high potential for extracting the knowledge from genomics and selecting the representative Single Nucleotide Polymorphisms (SNPs) as the most effective features for the clinical diagnosis process. In this study, we have attempted to identify representative SNPs using feature selection methods, incorporating biological information and aimed to develop a machine-learning model for diagnosing Behcet's disease. By combining biological information and machine learning classifiers, up to 99.64 percent accuracy of disease prediction is achieved using only 13,611 out of 311,459 SNPs. In addition, we revealed the SNPs that are most distinctive by performing repeated feature selection in cross-validation experiments.