Ali Golzadeh; Ali Kamandi; Hossein Rahami
Abstract
Predicting missing links in noisy protein-protein interaction networks is an essential~computational method. Recently, attributed network embedding methods have been shown to be significantly effective in generating low-dimensional representations of nodes to predict links; in these representations, ...
Read More
Predicting missing links in noisy protein-protein interaction networks is an essential~computational method. Recently, attributed network embedding methods have been shown to be significantly effective in generating low-dimensional representations of nodes to predict links; in these representations, both the nodes'features and the network's topological information are preserved. Recent research suggests that models based on paths of length 3 between two nodes are more accurate than models based on paths of length 2 for predicting missing links in a protein-protein interaction network. In the present study, an attributed network embedding method termed ANE-SITI is recommended to combine protein sequence information and network topological information. In addition, to improve accuracy, network topological information also considers paths of length 3 between two proteins. The results of this experiment demonstrate that ANE-SITI outperforms the compared methods on various~protein-protein interaction (PPI) networks.
Maliheh Ghomsheh; Ali Kamandi
Abstract
Artificial neural networks that have been so popular in recent years, are inspired from biological neural networks in the nature. The aim of this work is to study the properties of biological neural networks to find out what is actually happening in these networks. To do so, we study on Caenrohibditis ...
Read More
Artificial neural networks that have been so popular in recent years, are inspired from biological neural networks in the nature. The aim of this work is to study the properties of biological neural networks to find out what is actually happening in these networks. To do so, we study on Caenrohibditis elegans neural network, which is the simplest and the only biological neural network that is fully mapped. We implemented the sub-circuit of C.elegans neural network that is associated with the sensation of aversive stimuli which results in forward and backward locomotion, and we found out that some of its neurons are ineffective in developing considered outputs. However, removing these neurons together has considerable effect on these outputs.
