A5045764563- Bioinformatics and Genomic Networks
- RNA Research and Splicing
- Machine Learning in Bioinformatics
- RNA and protein synthesis mechanisms
- Gene expression and cancer classification
- Genomics and Phylogenetic Studies
- RNA modifications and cancer
- Protein Structure and Dynamics
- Genomics and Chromatin Dynamics
- Microbial Metabolic Engineering and Bioproduction
- Cancer-related gene regulation
- Gene Regulatory Network Analysis
- Cancer-related molecular mechanisms research
- Computational Drug Discovery Methods
- Advanced Image and Video Retrieval Techniques
- Algorithms and Data Compression
- Enzyme Structure and Function
- 14-3-3 protein interactions
- Advanced Proteomics Techniques and Applications
- Molecular Biology Techniques and Applications
- Power Quality and Harmonics
- Scientific Computing and Data Management
- Image Retrieval and Classification Techniques
- Biomedical Text Mining and Ontologies
- CRISPR and Genetic Engineering
Middle East Technical University
2013-2023
Turkish Aerospace Industries (Turkey)
2015
TUBITAK BILGEM
2011
Scientific and Technological Research Council of Turkey
2008
Bilkent University
2007
University of California, Santa Barbara
2003-2005
The automatic extraction of chemical information from text requires the recognition entity mentions as one its key steps. When developing supervised named (NER) systems, availability a large, manually annotated corpus is desirable. Furthermore, large corpora permit robust evaluation and comparison different approaches that detect chemicals in documents. We present CHEMDNER corpus, collection 10,000 PubMed abstracts contain total 84,355 labeled by expert chemistry literature curators,...
We propose an efficient and biologically sensitive algorithm based on repeated random walks (RRW) for discovering functional modules, e.g., complexes pathways, within large-scale protein networks. Compared to existing cluster identification techniques, RRW implicitly makes use of network topology, edge weights, long range interactions between proteins.We apply the proposed technique a yeast genes accurately identify statistically significant clusters proteins. validate biological...
3'-Untranslated region (UTR) shortening of mRNAs via alternative polyadenylation (APA) has important ramifications for gene expression. By using proximal APA sites and switching to shorter 3'-UTRs, proliferating cells avoid miRNA-mediated repression. Such 3'-UTR events may explain the basis some proto-oncogene activation cases observed in cancer cells. In this study, we investigated whether 17 β-estradiol (E2), a potent proliferation signal, induces activate proto-oncogenes estrogen receptor...
Alternative polyadenylation (APA) plays a role in gene expression regulation generally by shortening of 3'UTRs (untranslated regions) upon proliferative signals and relieving microRNA-mediated repression. Owing to high indices triple negative breast cancers (TNBCs), we hypothesized APA cause 3'UTR length changes this aggressive subgroup cancers. Our probe-based meta-analysis approach identified alterations where the significant majority was events (∼70%, 113 165) mostly proliferation-related...
Genome wide protein networks have become reality in recent years due to high throughput methods for detecting interactions. Recent studies show that a networked representation of proteins provides more accurate model biological systems and processes compared conventional pair-wise analyses. Complementary the availability networks, various graph analysis techniques been proposed mine these pathway discovery, function assignment, prediction complex membership. In this paper, we propose using...
We present a new method for conducting protein structure similarity searches, which improves on the accuracy, robustness, and efficiency of some existing techniques. Our is grounded in theory differential geometry 3D space curve matching. generate shape signatures proteins that are invariant, localized, robust, compact, biologically meaningful. To improve matching we smooth noisy raw atomic coordinate data with spline fitting. efficiency, adopt hierarchical coarse-to-fine strategy. use an...
Salmonella enterica is a bacterial pathogen that usually infects its host through food sources. Translocation of the proteins into cells leads to changes in signaling mechanism either by activating or inhibiting proteins. Given infection modifies response network host, more coherent view underlying biological processes and networks can be obtained using modeling approach based on reverse engineering principles. In this work, we have used published temporal phosphoproteomic dataset...
Sea-surface targets are automatically detected and tracked using the bag-of-features (BOF) technique with scale-invariant feature transform (SIFT) in infrared (IR) visual (VIS) band videos. Features corresponding to sea-surface background first clustered a training set offline, these features then used for online target detection BOF technique. The matched those subsequent frame tracking purposes of heuristic rules. Tracking performance is compared an optical-flow-based method respect ground...
Certain aspects of diagnosis, prognosis, and treatment cancer patients are still important challenges to be addressed. Therefore, we propose a pipeline uncover patterns alternative polyadenylation (APA), hidden complexity in transcriptomes, further accelerate efforts discover novel genes pathways. Here, analyzed expression data for 1045 found significant shift usage poly(A) signals common tumor types (breast, colon, lung, prostate, gastric, ovarian) compared normal tissues. Using...
Many tools have been developed to visualize protein structures. Tools that based on Java 3D((TM)) are compatible among different systems and they can be run remotely through web browsers. However, using 3D for visualization has some performance issues with it. The primary concerns about molecular in their being slow terms of interaction speed inability load large molecules. This behavior is especially apparent when the number atoms displayed huge, or several proteins simultaneously...
We propose a novel technique for automatically generating the SCOP classification of protein structure with high accuracy. achieve accurate by combining decisions multiple methods using consensus committee (or an ensemble) classifier. Our technique, based on decision trees, is rooted in machine learning which shows that judicially employing component classifiers, ensemble classifier can be constructed to outperform its components. use two sequence- and three structure-comparison tools as...
Reconstructing the topology of a signaling network by means RNA interference (RNAi) technology is an underdetermined problem especially when single gene in knocked down or observed. In addition, exponential search space limits existing methods to small networks size 10-15 genes. this paper, we propose integrating RNAi data with reference physical interaction network. We formulate reconstruction as finding minimum number edit operations on given The transform that satisfies observations. show...
Transcriptome experiments are performed to assess protein abundance through mRNA expression analysis. Expression levels of genes vary depending on the experimental conditions and cell response. data must be diverse yet comparable in reference stably expressed genes, even if they generated from different same biological context various laboratories. In this study, patterns 9090 microarray samples grouped into 381 NCBI-GEO datasets were investigated identify novel candidate using...
In recent years, a considerable amount of research effort has been directed to the analysis biological networks with availability genome-scale genes and/or proteins an increasing number organisms. A protein-protein interaction (PPI) network is particular which represents physical interactions between pairs organism. Major on PPI focused understanding topological organization networks, evolution and identification conserved subnetworks across different species, discovery modules interaction,...
A global view of the protein space is essential for functional and evolutionary analysis proteins. In order to achieve this, a similarity network can be built using pairwise relationships among However, existing networks employ single measure therefore their utility depends highly on quality selected measure. more robust representation realized if multiple sources information are used.We propose novel approach analyzing multi-attribute by combining random walks graphs with Bayesian theory....
In this paper, we propose a new method to search different instances of video sequence inside long and/or collection. The proposed is robust view point and illumination changes which may occur since the sequences are captured in times with cameras, differences order number frames due editing. algorithm does not require any query be given for searching, finds all repeating fully automatic way. First, ranked according their similarity on distribution salient points colour values. Then, tree...
Analysis of integrated genome-scale networks is a challenging problem due to heterogeneity high-throughput data. There are several topological measures, such as graphlet counts, for characterization biological networks. In this paper, we present methods counting small sub-graph patterns in which modeled labeled multidigraphs. We have obtained physical, regulatory, and metabolic interactions between H. sapiens proteins from the Pathway Commons database. The network filtered tissue/disease...
Nowadays, increasing number of game engines are being developed for mobile platforms. As platforms small scale compared to console and desktop alternatives, engine development in uses basic software methods. However, as enhance more complex games become possible, methods will not well advanced requirements. This paper examines design a that provides maturity by using goals patterns. Our results show developing goal pattern based approach regular clear path building each aspect the with...