Browsing by Author "Ogul, Hasan"

Now showing 1 - 20 of 43

Author Recognition from Lyrics
(2015) Kirmaci, Basar; Ogul, Hasan
Music information retrieval has been an important task due to the wide use of internet and related technologies for entertainment. In previous studies, the problem has been considered using the meta-data or melodic content. The use of lyrics in this context is not that common. There is not study either for Turkish songs in this respect. In this study, we discuss the predictability of the author using the text data in a Turkish lyric. To this end, we propose a system that can predict the author using the features extracted from text content. The performance of the system is evaluated on a large data set collected from writers with different music styles.
Classification of Patients with Heart Failure
(2014) Bayrak, Tuncay; Ogul, Hasan; https://orcid.org/0000-0001-6826-4350; U-4603-2019
Echocardiography is imaging of anatomy and physiology of heart with high frequency sound waves by using ultrasonic transducers. The signals obtained by using this method are defined as echocardiogram. In this way, the function of heart can be investigated and any abnormal case is determined according to many parameters. In this study, the classification was realized, according to 7 of features obtained from echocardiogram signals belong to 74 of patient in Machine Learning Repository (UCI) database. Naive Bayes was determined as the best classification method for this dataset and 63% sensitivity, 84% specificity, and an accuracy value of 77% has been reached. In conclusion, this study presents an investigation of determination of which features are significant in death based on heart failure.
Comparison of Similarity Metrics in Microarray Experiment Retrieval
(2015) Acici, Koray; Ogul, Hasan; 0000-0002-3821-6419; HDM-9910-2022
Content-based retrieval of biological experiments is a recent challenge in bioinformatics. The task is to search in a database using a query-by-example without any meta-data annotation. In this study, for retrieving relevant microRNA experiments from microarray repositories, performance evaluation of known similarity metrics was conducted to compare experiment fingerprints. It was shown that Spearman correlation coefficient outperformed others by comparison on real datasets. This result shows that ranks of fingerprint values are more important than the exact values in experiment fingerprint.
Computational Prediction of MicroRNA Function and Activity
(2014) Ogul, Hasan; 24272442
Inferring microRNA (miRNA) functions and activities has been extremely important to understand their system-level roles and the mechanisms behind the cellular behaviors of their target genes. This chapter first details methodologies necessary for prediction of function and activity. It then introduces the computational methods available for investigation of sequence and experimental data and for analysis of the information flow mediated through miRNAs.
Computer-Aided Breast Cancer Diagnosis from Thermal Images Using Transfer Learning
(2020) Cabioglu, Cagri; Ogul, Hasan
Breast cancer is one of the prevalent types of cancer. Early diagnosis and treatment of breast cancer have vital importance for patients. Various imaging techniques are used in the detection of cancer. Thermal images are obtained by using the temperature difference of regions without giving radiation by the thermal camera. In this study, we present methods for computer aided diagnosis of breast cancer using thermal images. To this end, various Convolutional Neural Networks (CNNs) have been designed by using transfer learning methodology. The performance of the designed nets was evaluated on a benchmarking dataset considering accuracy, precision, recall, F1 measure, and Matthews Correlation coefficient. The results show that an architecture holding pre-trained convolutional layers and training newly added fully connected layers achieves a better performance compared with others. We have obtained an accuracy of 94.3%, a precision of 94.7% and a recall of 93.3% using transfer learning methodology with CNN.
A Content-Based Retrieval Framework for Whole Metagenome Sequencing Samples
(2018) Sener, Duygu Dede; Santoni, Daniele; Felici, Giovanni; Ogul, Hasan; 30367805
Finding similarities and differences between metagenomic samples within large repositories has been rather a significant issue for researchers. Over the recent years, content-based retrieval has been suggested by various studies from different perspectives. In this study, a content-based retrieval framework for identifying relevant metagenomic samples is developed. The framework consists of feature extraction, selection methods and similarity measures for whole metagenome sequencing samples. Performance of the developed framework was evaluated on given samples. A ground truth was used to evaluate the system performance such that if the system retrieves patients with the same disease, -called positive samples-, they are labeled as relevant samples otherwise irrelevant. The experimental results show that relevant experiments can be detected by using different fingerprinting approaches. We observed that Latent Semantic Analysis (LSA) Method is a promising fingerprinting approach for representing metagenomic samples and finding relevance among them. Source codes and executable files are available at www.baskent.edu.tr/similar to hogul/WMS_retrieval.rar
Content-Based Retrieval of Microarray Experiments
(2016) Ogul, Hasan
Content-Based Search on Time-Series Microarray Databases Using Cluster-Based Fingerprints
(2017) Ozkoc, Esma Erguner; Ogul, Hasan; AAG-1506-2021
Background: The rapid growth of gene expression databases has created a need for content-based searches as an alternative to unstructured database queries using keyword- or metadata-based searches. Content-based searching is the ability to retrieve all experiments with similar gene expression patterns in a database regardless of the biological annotations provided for these experiments. Objective: While this concept is still in its infancy in a general context, in this study we focus on applying it to a specific subset of gene expression datasets, by only querying experiments involving time-series expression profiles. Method: To this end, we propose a novel experiment fingerprinting scheme obtained by clustering expression profiles, for content-based searching of time-series microarray experiments. To determine the retrieval ability of the proposed scheme, we performed a simulated information retrieval task on a large set of microarray experiments gathered from a public repository. The relevance between any two experiments was then defined using their commonalities based on annotated disease associations. Results and Conclusion: The results showed that relevant experiments can be more successfully retrieved using this new method compared with traditional differential expression-based methods.
Context-Sensitive Model Learning for Lung Nodule Detection
(2016) Ogul, B. Buket; Ogul, Hasan; Sumer, Emre; AGA-5711-2022
Nodule detection in chest radiographs is a main component of current Computer Aided Diagnosis (CAD) systems. The problem is usually approached as a supervised classification task of candidate nodule segments. To this end, a discriminative model is learnt from predefined set of features. A key concern with this approach is the fact that some normal tissues are also imaged and these regions can overlap with the lung tissue as to hide the nodules. These overlaps may reduce the discriminative ability of extracted features and increase the number of false positives accordingly. In this study, we offer to learn distinct models for bone and normal tissue regions following to the segmentation of ribs, which are often the major reason for false positives. Thus, the nodule candidates in bone and normal tissue regions can be assessed in context-sensitive way. The experiments on a common benchmark set determine that the proposed approach can significantly recue the false positives while preserving the sensitivity of detections.
Data Integration for Gene Expression Prediction
(2018) Bayrak, Tuncay; Ogul, Hasan; 0000-0001-6826-4350; U-4603-2019
In computational system biology, one challenging topic is predicting the exact value of gene expression for further meta-analysis. For this, a data integration approach and regression based task are proposed. To improve prediction performance, gene expression data consisted of continuous value is integrated with binary data from miRNA-mRNA regulation pairs by a simple approach. For regression task, a recently introduced method, Relevance Vector Machine (RVM) and linear regression are used. For evaluation, Spearman and Pearson Correlation Coefficients, and Root Mean Squared Error are used. The results we obtain show that the proposed approach can significantly improve the prediction performance. Data integration approach and RVM are promising in many machine learning problems.
A deep learning approach for sepsis monitoring via severity score estimation
(2021) Asuroglu, Tunc; Ogul, Hasan; 33157471
Background and objective: Sepsis occurs in response to an infection in the body and can progress to a fatal stage. Detection and monitoring of sepsis require multi-step analysis, which is time-consuming, costly and requires medically trained personnel. A metric called Sequential Organ Failure Assessment (SOFA) score is used to determine the severity of sepsis. This score depends heavily on laboratory measurements. In this study, we offer a computational solution for quantitatively monitoring sepsis symptoms and organ systems state without laboratory test. To this end, we propose to employ a regression-based analysis by using only seven vital signs that can be acquired from bedside in Intensive Care Unit (ICU) to predict the exact value of SOFA score of patients before sepsis occurrence. Methods: A model called Deep SOFA-Sepsis Prediction Algorithm (DSPA) is introduced. In this model, we combined Convolutional Neural Networks (CNN) features with Random Forest (RF) algorithm to predict SOFA scores of sepsis patients. A subset of Medical Information Mart in Intensive Care (MIMIC) III dataset is used in experiments. 5154 samples are extracted as input. Ten-fold cross validation test are carried out for experiments. Results: We demonstrated that our model has achieved a Correlation Coefficient (CC) of 0.863, a Mean Absolute Error (MAE) of 0.659, a Root Mean Square Error (RMSE) of 1.23 for predictions at sepsis onset. The accuracies of SOFA score predictions for 6 hours before sepsis onset were 0.842, 0.697, and 1.308, in terms of CC, MAE and RMSE, respectively. Our model outperformed traditional machine learning and deep learning models in regression analysis. We also evaluated our model's prediction performance for identifying sepsis patients in a binary classification setup. Our model achieved up to 0.982 AUC (Area Under Curve) for sepsis onset and 0.972 AUC for 6 hours before sepsis, which are higher than those reported by previous studies. Conclusions: By utilizing SOFA scores, our framework facilitates the prognose of sepsis and infected organ systems state. While previous studies focused only on predicting presence of sepsis, our model aims at providing a prognosis solution for sepsis. SOFA score estimation process in ICU depends on laboratory environment. This dependence causes delays in treating patients, which in turn may increase the risk of complications. By using easily accessible non-invasive vital signs that are routinely collected in ICU, our framework can eliminate this delay. We believe that the estimation of the SOFA score will also help health professionals to monitor organ states. (C) 2020 Elsevier B.V. All rights reserved.
DeepMBS: Prediction of Protein Metal Binding-Site Using Deep Learning Networks
(2017) Haberal, Ismail; Ogul, Hasan; 0000-0002-8647-4295; AAJ-8956-2021
The tertiary structure of a protein indicates what vital function that protein fulfills in the cell. Prediction of the metal binding comformation of a protein from its sequence is a crucial step in predicting its tertiary structure. In this study, a computational method was developed for predicting the binding of Histidine and Cysteine to metals. We propose a deep convolutional neural network architecture, DeepMBS, to predict protein metal binding sites. To our knowledge, this study is the first realization of deep learning idea for the problem of predicting metal binding site. The method allows automatic extraction of complex interactions between important features using only sequence information by utilizing PAM120 scoring matrix. Features were extracted from protein sequences obtained from the Protein Data Bank and deep convolutional neural network was applied to these features. According to experimental results on a benchmark dataset, metal binding states can be predicted with 82% recall and 79% precision. These results show that a better performance can be achived with deep learning approach compared with previous studies on the same dataset.
Detection of Microrna Clusters Associated with Prostate Cancer
(2014) Haberal, Ismail; Ogul, Hasan; https://orcid.org/0000-0002-8647-4295; AAJ-8956-2021
MicroRNAs (miRNAs) are a class of small non-coding RNAs of 22 nucleotides which normally function as negative regulators of target mRNA expression at the posttranscriptional level. miRNAs play a role for one or more target genes by suppressing in processes as growth, differentiation, proliferation and cell death. Recent evidence has shown that miRNA mutations or mis-expression correlate with various human cancers and indicates that miRNAs can function as tumour suppressors and oncogenes. MicroRNAs have been shown to repress the expression of important cancer-related genes and might prove useful in the diagnosis and treatment of cancer. In this study, hierarchical microRNA clusters are obtained through microarray expression data in order to analyze the microRNA prostate cancer relationships. Clustering results are evaluated by their biological relevance. It is seen that such approach can be useful in detectitn relationships between microRNAs and diseases.
Eliminating Rib Shadows in Chest Radiographic Images Providing Diagnostic Assistance
(2016) Ogul, Hasan; Ogul, B. Buket; Agildere, A. Muhtesem; Bayrak, Tuncay; Sumer, Emre; https://orcid.org/0000-0003-4223-7017; https://orcid.org/0000-0001-6826-4350; 26775736; AAB-5802-2020; U-4603-2019
A major difficulty with chest radiographic analysis is the invisibility of abnormalities caused by the superimposition of normal anatomical structures, such as ribs, over the main tissue to be examined. Suppressing the ribs with no information loss about the original tissue would therefore be helpful during manual identification or computer-aided detection of nodules on a chest radiographic image. In this study, we introduce a two-step algorithm for eliminating rib shadows in chest radiographic images. The algorithm first delineates the ribs using a novel hybrid self-template approach and then suppresses these delineated ribs using an unsupervised regression model that takes into account the change in proximal thickness (depth) of bone in the vertical axis. The performance of the system is evaluated using a benchmark set of real chest radiographic images. The experimental results determine that proposed method for rib delineation can provide higher accuracy than existing methods. The knowledge of rib delineation can remarkably improve the nodule detection performance of a current computer-aided diagnosis (CAD) system. It is also shown that the rib suppression algorithm can increase the nodule visibility by eliminating rib shadows while mostly preserving the nodule intensity. (C) 2015 Elsevier Ireland Ltd. All rights reserved.
Evaluating Text Features for Lyrics-Based Songwriter Prediction
(2015) Kirmaci, Basar; Ogul, Hasan; 978-1-4673-7939-7
We offer an automated way of estimating the author of a song using only its lyrics content. To this end, we introduce a complete text classification framework which takes raw lyrics data as input and report estimated songwriter. The performance of the system is evaluated based on its classification and retrieval ability on a large dataset of Turkish songs, which was collected in this study. The results promote the use of such technique as a complementary tool in music information retrieval applications.
Exploiting Active Microrna Interactions for Diagnosis from Expression Profiling Experiments
(2017) Corapcioglu, Erdem; Ogul, Hasan
In silico diagnosis through microRNA expression profiling experiments is a promising direction in the clinical practices of bioinformatics science. The task is computationally defined as a classification problem where a query experiment is required to be assigned into one of the predefined diseases using a model learned from previously labeled samples. While several powerful machine learning models exist to perform this task, the challenging issue is how to feed these models by effectively encoded samples. This encoding requires a sensible representation of experiment content. In contrast to previous data-driven representations based on observed differential expressions of individual miRNAs, we offer here a interaction-driven representation scheme that considers the active interactions of miRNAs with other entities in either direction of gene regulation, i.e. regulating or being regulated. We use the enrichment scores of the miRNA sets annotated by corresponding interaction elements to encode the input experiments. We have empirically shown that the new encoding can lead to a higher disease classification accuracy compared with the traditional data-driven approach.
Exploiting Active MicroRNA Interactions for Diagnosis from Expression Profiling Experiments
(2017) Corapcioglu, Erdem; Ogul, Hasan
In silico diagnosis through microRNA expression profiling experiments is a promising direction in the clinical practices of bioinformatics science. The task is computationally defined as a classification problem where a query experiment is required to be assigned into one of the predefined diseases using a model learned from previously labeled samples. While several powerful machine learning models exist to perform this task, the challenging issue is how to feed these models by effectively encoded samples. This encoding requires a sensible representation of experiment content. In contrast to previous data-driven representations based on observed differential expressions of individual miRNAs, we offer here a interaction-driven representation scheme that considers the active interactions of miRNAs with other entities in either direction of gene regulation, i.e. regulating or being regulated. We use the enrichment scores of the miRNA sets annotated by corresponding interaction elements to encode the input experiments. We have empirically shown that the new encoding can lead to a higher disease classification accuracy compared with the traditional data-driven approach.
Inferring Microarray Relevance By Enrichment Of Chemotherapy Resistance-Based MicroRNA Sets
(2015) Acici, Koray; Ogul, Hasan; 0000-0002-3821-6419; HDM-9910-2022
Inferring relevance between microarray experiments stored in a gene expression repository is a helpful practice for biological data mining and information retrieval studies. In this study, we propose a knowledge-based approach for representing microarray experiment content to be used in such studies. The representation scheme is specifically designed for inferring a disease-associated relevance of microRNA experiments. A group of annotated microRNA sets based on their chemotherapy resistance are used for a statistical enrichment analysis over observed expression data. A query experiment is then represented by a single dimensional vector of these enrichment statistics, instead of raw expression data. According to the results, new representation scheme can provide a better retrieval performance than traditional differential expression-based representation.
Inferring Similarity between Time-Series Microarrays: A Content-based Approach
(2015) Sener, Duygu Dede; Ogul, Hasan; 0000-0001-6766-4977
Public repositories for gene expression studies have been growing rapidly in the last decade. Retrieval of gene expression experiments based on textual descriptions does not provide sufficient data for biologists and clinicians. Content-based search has recently become more desirable in retrieving similar experiments. Current methods for content-based retrieval cannot address the problem of profiling the gene behaviors in multiple measurement points, i.e. in time course. This study, to the best of our knowledge, is the first attempt to build a fingerprint for each gene by considering all time points to infer its time-course profile to represent the experiment content in an information retrieval framework. An empirical study is performed on a large dataset of Arabidopsis microarrays from Gene Expression Omnibus (GEO). Experimental results show that relevant experiments are retrieved based on content similarity.
Information Retrieval in Metal Music Sub Genres
(2017) Acici, Koray; Asuroglu, Tunc; Ogul, Hasan; 0000-0003-4153-0764; HDM-9910-2022; AAC-7834-2020
Digital music platforms use meta-data based information retrieval systems for offering songs to users for their own taste of music. According to this system, songs that are labeled by other users are compared to songs that user listened and similar labeled songs are retrived in the process. In this situtation, information retrieval is independent from song content and subjective. To achieve objectivity, content based information retrieval systems are needed. In this study, a content-based music retrieval system based on one dimensional local binary pattern features which are extracted from audio data is proposed. Instead of retrieving different music genres, retrieval is applied on metal music sub-genres which have not been studied before and results are reported.