Accepted Papers

  • MuLiSA: A new strategy for discovery of protein functional motifs and residues
    Chien-Heng Lin and Jinn-Moon Yang,National Chiao Tung University,Taiwan.
    To predict and identify details regarding function from protein sequences is an emergency task since the growing number and diversity of protein sequence. Here, we develop a novel approach for identifying conservation residues and motifs of ligand-binding proteins. In this method, called MuLiSA (Multiple Ligand-bound Structure Alignment), we first superimpose the ligands of ligand-binding proteins and then the residues of ligand-binding sites are naturally aligned. We identify important residues and patterns based on the z-scores of the residue entropy and residue-segment entropy. After identifying new pattern candidates, the profiles of patterns are generated to predict the protein function from only protein sequences. We tested our approach on ATP-binding proteins and HEM-binding proteins. The experiments show that MuLiSA can identify the conservation residues and novel patterns which are really correlated with protein functions of certain ligand-binding proteins. We found that our MuLiSA can identify conservation patterns and is better than traditional alignments such as CE and CLUSTALW in some ligand-binding proteins. We believe that our MuLiSA is useful to discover ligand-binding specificity-determining residues and functional important patterns of proteins.
  • Detection of Twelve Leads of Electrocardiogram Signal to Identify Cardiac Abnormalities Using Artificial Neural Network with Backpropagation Method
    Talitha Asmaria,Imam Sapuan,EndahPurwanti,Airlannga University,Indonesia.
    A research has been conducted to detect the twelve leads of electrocardiogram signal to identify cardiac abnormalities using artificial neural network with backpropagation method. This study aims to obtain the image features that can be used as the input of the software and then obtain the optimal parameter values of backpropagation as well as get an optimal value of accuracy of the software. In this research, the software is designed using an interface which aims to allow the users to use the software conveniently. The software is also built using two artificial neural networks, which the first one is for detecting abnormalities of wave on leads and the last one is for identifying cardiac abnormalities. From backpropagation algorithm, this project has some parameters, those are the number of hidden layers are fifteen, the value of learning rate is 0.1, the maximum epoch is 1000, and the error target is 0.001. The software has been conducted to detect cardiac normality, left atrial hypertrophy, right ventricular hypertrophy, and, cardiac abnormalities. The software has been tested to detect cardiac abnormalities on ECG images with an accuracy rate is 93.33%.