Yazar "Otu, H.H." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    A dynamic Bayesian framwork to learn temporal gene interactions using external knowledge
    (IEEE Computer Society, 2013) Ağyüz, U.; Işçi, S.; Öztürk, C.; Ademoğlu, A.; Otu, H.H.
    One of the main problems in systems biology is learning gene interaction networks from experimental data. This turns out to be a challenging task as the experimental data is sparse and noisy, and network learning algorithms are computationally intense. Bayesian Networks (BN) have become a popular choice for learning such networks as BNs avoid overfitting and are robust to noise. In this paper we build up on our established framework, Bayesian Network Prior, where we incorporate existing biological knowledge in learning gene interaction networks. However, biological phenomena are time-dependent and there is need to extend the static structure of learning approaches to a temporal level. Here, we present a Dynamic BN framework, which learns interaction networks between different time points in time-series data. Both intra and inter networks are learnt and compared to standard DBN learning algorithms. Our results based on synthetic and simulated gene expression data suggest that the proposed method outperforms existing approaches in identifying the underlying network structure. The proposed framework is robust to errors in the incorporated knowledge and can combine various experimental data types together with existing knowledge when learning networks. © 2013 IEEE.
  • Küçük Resim Yok
    Öğe
    Detecting gene interactions within a Bayesian Network framework using external knowledge
    (2012) Isci, S.; Agyuz, U.; Ozturk, C.; Otu, H.H.
    Biological and clinical databases are increasing at a very high rate making a large volume of experimental data publicly available. In this paper, we propose a framework that makes use of external biological knowledge to predict if two given genes interact with each other. To this end, we utilize prior knowledge about interaction of two genes by generating a Bayesian Network using existing external biological knowledge. External knowledge types to be utilized are obtained from interaction databases such as BioGrid and Reac-tome and consist of protein-protein, protein-DNA/RNA, and gene interactions. We first built a naïve Bayesian Network to predict if two genes interact by employing parameter learning using known gene interactions. We propose that the resulting model will be incorporated into methods learning networks from high throughput biological data and interacting genes will be represented in the form of a network. In this process of network generation, the Bayesian Network model deducing gene interactions from external knowledge will be used to calculate the probability of candidate networks to enhance the structure learning task. Our simulations on both synthetic and real data sets show that proposed framework can successfully enhance identification of the true network and be used in predicting gene interactions. © 2012 IEEE.