Now showing items 1-19 of 19

    • Anti-cancer Drug Activity Prediction by Ensemble Learning 

      Tolan, Ertan; Tan, Mehmet (SCITEPRESS, 2016)
      Personalized cancer treatment is an ever-evolving approach due to complexity of cancer. As a part of personalized therapy, effectiveness of a drug on a cell line is measured. However, these experiments are backbreaking and ...
    • Biological Network Derivation by Positive Unlabeled Learning Algorithms 

      Pancaroglu, Doruk; Tan, Mehmet (Bentham Bcience Publ. Ltd., 2016)
      Background: In cases where only a single group (or class) of samples is available for a given problem, positive unlabeled learning algorithms can be applied. One such case is the interactions between various biological/chemical ...
    • Disease outbreak prediction by data integration and multi-task learning 

      Bardak, Batuhan; Tan, Mehmet (IEEE, 2017)
      The requirements for treatments vary for different diseases. These have to be considered in order to plan ahead the expenditures for the health care system. In this sense, disease surveillance has a significant impact on ...
    • Drug response prediction by ensemble learning and drug-induced gene expression signatures 

      Tan, Mehmet; Özgül, Ozan Fırat; Bardak, Batuhan; Ekşioğlu, Işıksu; Sabuncuoğlu, S. ( Academic Press Inc., 2019-09)
      Chemotherapeutic response of cancer cells to a given compound is one of the most fundamental information one requires to design anti-cancer drugs. Recently, considerable amount of drug-induced gene expression data has ...
    • Drug sensitivity prediction for cancer cell lines based on pairwise kernels and miRNA profiles 

      Tan, Mehmet (IEEE, 2014)
      Cancer cell lines comprise an important tool to design and evaluate new drug candidates. Prediction of in vivo drug response for cancer cell lines has become attractive due to recently issued large scale drug screen ...
    • Edge distance graph kernel and its application to small molecule classification 

      Tan, Mehmet (TUBITAK Scientific & Technical Research Council Turkey, 2017)
      Graph classification is an important problem in graph mining with various applications in different fields. Kernel methods have been successfully applied to this problem, recently producing promising results. A graph kernel ...
    • Effective gene expression data generation framework based on multi-model approach 

      Sirin, Utku; Erdogdu, Utku; Polat, Faruk; Tan, Mehmet; Alhajj, Reda (Elsevier, 2016-06)
      Objective: Overcome the lack of enough samples in gene expression data sets having thousands of genes but a small number of samples challenging the computational methods using them. Methods and material: This paper introduces ...
    • A Fully Unsupervised Framework for Scoring Driving Style 

      Ozgul, Ozan Firat; Cakir, Mehmet Ulas; Tan, Mehmet; Amasyali, Mehmet Fatih; Hayvacı, Harun Taha (IEEE, 2018)
      Rating driving performance is a challenging topic. It attracts professionals from a variety of domains such as automotive industry and insurance companies. In this work, we propose a fully unsupervised driver scoring ...
    • Hastalık salgınlarının internet erişim ve arama verisi kullanılarak tahmini 

      Bardak, Batuhan (TOBB ETÜ Fen Bilimleri EnstitüsüTOBB University of Economics and Technology,Graduate School of Engineering and Science, 2016)
      Hastalıkların hangi nedenden dolayı ortaya çıktığı ve önceden tahmin edilmesi insan sağlığı için çok önemli bir konudur. Son yıllarda teknolojinın hızla gelişmesi ve internetin yoğun biçimde kullanılmasıyla ortaya büyük ...
    • Improving Positive Unlabeled Learning Algorithms for Protein Interaction Prediction 

      Pancaroglu, Doruk; Tan, Mehmet (SPRINGER-Verlag Berlin, 2014)
      In binary classification, it is sometimes difficult to label two training samples as negative. The aforementioned difficulty in obtaining true negative samples created a need for learning algorithms which does not use ...
    • Kimyasal moleküllerin eşlenmesi için çizge temelli örüntü tanıma kullanımı 

      Gökçer, Yunus (TOBB ETÜ Fen Bilimleri EnstitüsüTOBB University of Economics and Technology,Graduate School of Engineering and Science, 2015)
      Veri gösterimlerinin sınıflandırılmasında kullanılan örüntü tanıma teknikleri biyoenformatik ve kemoenformatik alanlarının önemli bileşenleri olarak görülürler. Kimyasal moleküllerin aktivitelerinin sonuçlarını tahmin ...
    • Multi-Scale Modularity and Motif Distributional Effect in Metabolic Networks 

      Gao, Shang; Chen, Alan; Rahmani, Ali; Zeng, Jia; Tan, Mehmet; Alhajj, Reda; Rokne, Jon; Demetrick, Douglas; Wei, Xiaohui (BENTHAM Science Publ. Ltd., 2016)
      Metabolism is a set of fundamental processes that play important roles in a plethora of biological and medical contexts. It is understood that the topological information of reconstructed metabolic networks, such as modular ...
    • Predicting drug activity by image encoded gene expression profiles 

      Ozgul, O.F.; Bardak, Batuhan; Tan, Mehmet (Institute of Electrical and Electronics Engineers Inc., 2018-07-05)
      Developing personalized cancer treatment procedures requires a prior knowledge on the effects of different drugs on cancer cell lines. While obtaining this information in vitro is a tedious task, the emergence of numerous ...
    • Prediction of anti-cancer drug response by kernelized multi-task learning 

      Tan, Mehmet (Elsevier, 2016-10)
      Motivation: Chemotherapy or targeted therapy are two of the main treatment options for many types of cancer. Due to the heterogeneous nature of cancer, the success of the therapeutic agents differs among patients. In this ...
    • Prediction of influenza outbreaks by integrating Wikipedia article access logs and Google flu trend data 

      Bardak, Batuhan; Tan, Mehmet (Institute of Electrical and Electronics Engineers Inc., 2015-12-28)
      Prediction of influenza outbreaks is of utmost importance for health practitioners, officers and people. After the increasing usage of internet, it became easier and more valuable to fetch and process internet search query ...
    • Protein etkileşim tahmini için pozitif etiketsiz öğrenme algoritmalarının geliştirilmesi 

      Pancaroğlu, Doruk (TOBB Ekonomi ve Teknoloji Üniversitesi Fen Bilimleri Enstitüsü, 2014)
      Protein etkileşim tahmini için ikili sınıflandırmada, mevcut iki adet proteinin negatif (etkileşime girmeyen) olduğunu tespit edebilmek zor bir işlemdir. Bu zorluğun sebeplerinden biri bu sınıflandırmayı yapmaya yardımcı ...
    • Protein etkileşimlerinin tahmininde pozitif etiketlenmemiş öğrenme 

      Kılıç, Cumhur (2012)
      Bir veri kümesindeki örneklerin belli bir özelliğe sahip olup olmayışlarına göre etiketlendirilmeleri işlemine ikili sınıflandırma adı verilir. Bir ikili sınıflandırıcı eğitebilmek için, genel yaklaşımda, hem pozitif hem ...
    • Toplu öğrenme ile ilaç kombinasyonlarının sinerji skor tahmini 

      Ekşioğlu, Işıksu (TOBB ETÜ Fen Bilimleri Enstitüsü, 2020)
      Kanser gibi ortaya çıkış sebebi birden fazla genetik ve çevresel nedene bağlı olan kompleks hastalıkların tedavisinde son zamanlarda en çok tercih edilen yöntem; birden fazla ilacın birarada kullanıldığı politerapi ...
    • Topluluk yöntemi ve ilaç imzaları kullanılarak anti kanser ilaçların aktivite tahmini 

      Tolan, Ertan (TOBB ETÜ Fen Bilimleri EnstitüsüTOBB University of Economics and Technology,Graduate School of Engineering and Science, 2016)
      Kişiselleştirilmiş kanser tedavisi, kanserin karmaşıklığı da göz önünde bulundurulduğunda, gelişmekte olan bir yaklaşımdır. Kişiselleştirilmiş tedavinin bir parçası olarak, bir ilacın bir hücre hattındaki etkinliği labarotuvar ...