Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12469/45

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by browse.metadata.publisher "Association for Computing Machinery"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Thumbnail Image
    Article
    Citation - WoS: 14
    Force-Directed Approaches To Sensor Localization
    (Association for Computing Machinery, 2010) Efrat, Alon; Forrester, David; Iyer, Anand; Kobourov, Stephen G.; Erten, Cesim; Kılış, Ozan
    As the number of applications of sensor networks increases so does the interest in sensor network localization that is in recovering the correct position of each node in a network of sensors from partial connectivity information such as adjacency range or angle between neighboring nodes. In this article we consider the anchor-free localization problem in sensor networks that report possibly noisy range information and angular information about the relative order of each sensor's neighbors. Previously proposed techniques seem to successfully reconstruct the original positions of the nodes for relatively small networks with nodes distributed in simple regions. However these techniques do not scale well with network size and yield poor results with nonconvex or nonsimple underlying topology. Moreover the distributed nature of the problem makes some of the centralized techniques inapplicable in distributed settings. To address these problems we describe a multiscale dead-reckoning (MSDR) algorithm that scales well for large networks can reconstruct complex underlying topologies and is resilient to noise. The MSDR algorithm takes its roots from classic force-directed graph layout computation techniques. These techniques are augmented with a multiscale extension to handle the scalability issue and with a dead-reckoning extension to overcome the problems arising with nonsimple topologies. Furthermore we show that the distributed version of the MSDR algorithm performs as well as if not better than its centralized counterpart as shown by the quality of the layout measured in terms of the accuracy of the computed pairwise distances between sensors in the network.
  • Thumbnail Image
    Conference Object
    Importance of Regional Differences in Brain Throughout Aging for Down Syndrome
    (Association for Computing Machinery, 2018) Kulan, Handan; Dağ, Tamer
    Down syndrome (DS) which affects approximately one in 700 live births is caused by an extra copy of the long arm of human chromosome 21 (HSA21). Statistical analysis has been done for understanding the protein expression profiles based on age and sex differences in DS. In addition there are ongoing research efforts for comprehending expression patterns based on different brain regions. However little is known about the mechanisms of expression differences in brain regions throughout aging. Insights into these mechanisms are required to understand the susceptibility of distinct brain regions to neuronal insults with aging. Dissection of this selective vulnerability will be critical to our understanding of DS. By extracting information from the critical proteins which take part in the mechanism of the molecular pathways the diagnosis of DS can become easier. Also understanding the molecular pathways can contribute to develop effective drugs for the treatment of DS. In this work forward feature selection technique is applied for determining the protein subsets for old and young mice datasets which consist of the expression profiles across different brain regions. When these subsets are analyzed it is observed that selected proteins play important roles in the processes such as mTOR signaling pathway AD MAPK signaling pathway and apoptosis. We believe that the subsets of protein selected in our work can be utilized to understand the process of DS and can be used to develop age-related effective drugs.
  • Thumbnail Image
    Conference Object
    Ranking Protein-Protein Binding Using Evolutionary Information and Machine Learning
    (Association for Computing Machinery, 2017) Farhoodi, Roshanak; Akbal-Delibas, Bahar; Haspel, Nurit
    Discriminating native-like complexes from false-positives with high accuracy is one of the biggest challenges in protein-protein docking. The relationship between various favorable intermolecular interactions (e.g. Van derWaals electrostatic desolvation forces etc.) and the similarity of a conformation to its native structure is commonly agreed though the precise nature of this relationship is not known very well. Existing protein-protein docking methods typically formulate this relationship as a weighted sum of selected terms and tune their weights by introducing a training set with which they evaluate and rank candidate complexes. Despite improvements in recent docking methods they are still producing a large number of false positives which often leads to incorrect prediction of complex binding. Using machine learning we implemented an approach that not only ranks candidate complexes relative to each other but also predicts how similar each candidate is to the native conformation. We built a Support Vector Regressor (SVR) using physico-chemical features and evolutionary conservation. We trained and tested the model on extensive datasets of complexes generated by three state-of-the-art docking methods. The set of docked complexes was generated from 79 different protein-protein complexes in both the rigid and medium categories of the Protein-Protein Docking Benchmark v.5. We were able to generally outperform the built-in scoring functions of the docking programs we used to generate the complexes attesting to the potential of our approach in predicting the correct binding of protein-protein complexes.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 6
    Using Machine Learning Classifiers To Identify the Critical Proteins in Down Syndrome
    (Association for Computing Machinery, 2018) Kulan, Handan; Dağ, Tamer
    Pharmacotherapies of intellectual disability (ID) are largely unknown as the abnormalities at the complex molecular level which causes ID are difficult to understand. Down syndrome (DS) which is the prevalent cause of ID and caused by an extra copy of the human chromosome21 (Hsa21) has been investigated on protein levels by using the Ts65Dn mouse model of DS which are orthologs of %50 of Hsa21 classical protein coding genes. Recent works have applied the classification methods to understand critical factors in DS as it is believed that the problem was naturally related to classification problem since the determination of proteins discriminatory between classes of mice was required. In this study we apply forward feature selection method to identify correlated proteins and their interactions in DS. After identification we report supervised learning model of expression levels of selected proteins in order to understand the critical proteins for diagnosing and explaining DS. The proposed technique depicts optimum classification results achieved by optimizing parameters with grid search. When compared with the former work our classification results give higher accuracy. © 2018 Association for Computing Machinery.