Browsing by Author "Wannige, C.T."

Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    An Accurate Multiple Sequence Alignment Algorithm for Biological Sequence Sets with High Length Variations
    (Uva Wellassa University of Sri Lanka, 2018) Jayasingha, J.A.D.T.B.; Wannige, C.T.
    Multiple sequence alignment (MSA) is used for many studies in modern biology. There are many algorithms available for the alignment of multiple sequences. Among them, progressive alignment algorithm is the most commonly used heuristic alignment strategy for MSA. It solves MSA with an economic complexity but does not provide accurate solutions, because there is a conflict between accuracy and complexity. The existing similarity score method in progressive alignment algorithm does not consider the lengths of the sequences in the considered sequence set. So, if the protein or DNA sequences are with high length variations, the initial alignment scores may not produce a correct measure of similarity between the sequences. This leads to less accurate initial alignment scores, and as a consequence, final multiple sequence alignment may produce inaccurate results. In this research, we present a modified progressive alignment algorithm especially for sequences with high length variations. We modify the latest version of ClustalW 2.1 by replacing the similarity distance measure in ClustalW algorithm with a novel distance measure. The new distance score method captures the distance between each sequence pairs in sequence set and the obtained distance measure is utilized to generate a better guide tree for progressive alignment. In order to determine the pairwise similarity distance measure, we used lengths of the shortest common super-sequence (SCS) and the Longest Common Sub-sequence (LCS). We assessed our algorithm with BALIBASE 3.0 protein benchmark and compared the obtained results to those obtained with ClustalW alignment algorithm using the Quality score (Q Score) and the Sum of Pairs Score (SPS). We obtained better Q scores and SP scores for the alignments from modified ClustalW algorithm over original ClustalW algorithm. Furthermore, the alignment speed of modified ClustalW algorithm is multiple times faster than the original ClustalW algorithm. Keywords
  • No Thumbnail Available
    Item
    A Deep Learning Based Method for Predicting DNA N6- Methyladenine (6mA) Sites in Eukaryotes
    (Uva Wellassa University of Sri Lanka, 2020) Roland, L.H.; Wannige, C.T.
    DNA N6-methyladenine (6mA) is an epigenetic modification, which is involved in many biological regulation processes like DNA replication, DNA repair, transcription, and gene expression regulation. The widespread presence of this 6mA modification in eukaryotes has been unclear until recently. Therefore, for eukaryotes, the study of DNA 6mA is insufficient. Accurate identification of 6mA sites genome-wide provides a deeper understanding of the epigenetic modification process and the biological processes it involves. Existing experimental techniques are time-consuming and computational machine learning methods have room for performance improvement. DNA N6- methyladenine prediction in cross-species shows low performance. Hence, there is a need for a highly accurate, time-efficient method to predict the distribution of 6mA sites in eukaryotes. Deep learning models have shown higher accuracy in many experiments in bioinformatics. In this regard, we develop a customized VGG16 based model using convolution neural networks. We introduce a novel 3-dimensional encoding mechanism extending the one-hot encoding method for the given DNA sequences of length 41bp to support the VGG16 model input. Specifically, the 10-fold cross-validation on the benchmark datasets for the proposed model achieves higher accuracies for crossspecies, Rice, and M. musculus genomes. The cross-species data set was prepared by integrating the benchmark datasets of Rice, and M. musculus. This model outperforms the existing computational tools SNNRice6mA, ilM-CNN with a current validation accuracy of 97% for the prediction of 6mA sites. The model trained with cross-species data predicts 6mA sites of other species Arabidopsis Thaliana, Rosa Chinensis, Drosophila, and Yeast with a prediction accuracy over 70%. Thus, this model can be used for the genome-wide prediction of 6mA sites in eukaryotes. Keywords: DNA Sequence encoding method, Deep learning, Epigenetics, Bioinformatics, DNA N6-Methyladenine
  • No Thumbnail Available
    Item
    An Improved Deep Learning Based Method for Protein Family Classification
    (Uva Wellassa University of Sri Lanka, 2020) Sandaruwan, P.D.; Wannige, C.T.
    Proteins are large and complex molecules that play a critical role in various aspects of life. Only 20 amino acids provide millions of proteins by combining into chains called polypeptide chains with different types of amino acids, lengths, and folds. Therefore, they are considered the building blocks of life. In proteomics, proteins are classified into families to achieve many goals such as predicting functional properties of novel proteins, discovering new drugs for new diseases, etc. As biological experiments are more expensive to deal with a large number of new proteins, one of the main computational approaches of protein classification is deep learning. Nowadays, with the progress of computational techniques, deep learning plays a key role in many areas. In this paper, our goal is to offer an improved alignment-free deep learning-based method for pattern recognition in proteins for classification. In this research work, we were based on one of the recent deep Learning approaches called DeepFam. We designed an improved method using the concepts which have been used in image classification and natural language processing. We extensively experimented with using the Clusters of orthologous Groups (COG) and G-Protein-coupled receptor (GPCR) datasets. our method showed higher validation accuracy than DeepFam and other methods that had been experimented using the same data sets. Keywords: Bioinformatics, Protein family prediction, Deep learning, Deep convolutional neural networks
  • No Thumbnail Available
    Item
    Increased Reactive Oxygen Species Induced by Toxic Heavy Metals as an Initiator of CKDu
    (Uva Wellassa University of Sri Lanka, 2018) Upamalika, S.W.A.M.; Wannige, C.T.
    For more than two decades, many people in the North Central Province of Sri Lanka are affected by chronic kidney disease of uncertain etiology (CKDu) . The main risk factors of this disease are identified as heavy metals (arsenic, cadmium and lead), pesticide exposure, heat stress and dehydration, fluoride content and hardness of water. To identify molecular mechanisms of renal injury by these factors, we carried out a comprehensive literature survey. According to literature, heavy metals like arsenic initiate toxicity through generation of excessive Reactive oxygen species via two mechanisms. The first mechanism is inducing enzyme complexes to increase reactive oxygen species formation. The second mechanism is via inhibiting antioxidant enzymes. To take an insight into which mechanism has the highest impact, we regenerated an existing mathematical model of redox system in the body. Since experimental data show an increase of superoxide level with heavy metal exposure, we increased superoxide concentration ten times in the simulation. Further, to simulate the inhibition of enzymes, enzyme levels were decreased ten times. Both changes increased reactive oxygen species levels such as hydroxyl ion and lipid peroxidation. In addition, increasing the superoxide level showed high impact rather than decreasing the antioxidant enzymes levels. The reason for increase of superoxide could be the ability of heavy metals to interact in activation of enzyme complexes such as NADPH oxidase, mitochondrial transport chain enzyme complexes I and III. The reason for depletion of antioxidants like Glutathione and antioxidant enzymes such as Superoxide dismutase and Catalase would be the ability of heavy metals to complex with thiol groups in these molecules. The outcome of both mechanisms was an accumulation of higher amount of reactive oxygen species inside the cell. These reactive oxygen species induced oxidative stress activates cellular pathways which lead to cellular toxicity.
  • No Thumbnail Available
    Item
    Low Cost Railway Tracking and Mobile Application Based Train Monitoring System
    (Uva Wellassa University of Sri Lanka, 2020) Wijesundara, W.M.D.D.B.; Wannige, C.T.
    The railway is one of the common and low-cost transportation systems which is used by many passengers in Sri Lanka. However, delays in trains are frequent and passengers cannot find the actual location of the train since these facilities are not supported by the current system. The main intention of this work is to provide railway tracking and monitoring to the railway passengers at a low cost. This system would help passengers to know the train delays earlier, the actual arrival time of the train, to know the nearby railway station and the shortest path. The assumed system consists of a system administrator, a set of passengers, and a tracking device. Each passenger should have a smart device with an Android operating system. The tracking device needs to be positioned in the engine controlling room of the train. The prototype software was mainly developed for the users to find the actual location of the train. The proposed system works on Arduino, GPS/GSM module. While waiting for the train, the passenger should enable the data connection and GPS if they wish to know the nearest train location and the shortest path to reach the nearest location. When the tracking device is powered on and connected to the network coverage, it will be automatically connected to the server and the location data would be uploaded. Users can run the application and select the train to view the real-time map, estimated arrival time, and other data. Moreover, if the passenger doesn't know the nearest station, the system would automatically select the nearest station, show the shortest path, and predicted travel time to the user. The cost for the construction of the system is less than 25$ and this system can be applied to the buses in public transport or school busses. Other systems in the market cost around 80$. The pilot system provides the actual location of train and arrival time with high accuracy and the average error is 46 seconds. Using this method, the railway transportation system can be carried out as a diligent service. Keywords: Real time tracking, GPS, GSM, Android, Arduino, Train
  • No Thumbnail Available
    Item
    Sensitivity Analysis of a Redox System Model to Understand the Initiation of Chronic Kidney Disease of Unknown Etiology Progression
    (Uva Wellassa University of Sri Lanka, 2020) Upamalika, S.W.A.M.; Wannige, C.T.; Vidanagamachchi, S.M.
    Identification of the most significant parameter set in a mathematical model is very important to understand the model behavior. Sensitivity analysis is carried out to accomplish this purpose. Chronic Kidney Disease of unknown etiology has been identified as a disease with very high death rates in many tropical countries around the world including Sri Lanka, India, Egypt, and some Mesoamerican countries. Heavy metal exposure is one of the identified evidential factors of this disease progression. Oxidative stress is the main pathological mechanism that leads the kidney tubular cells to cell death pathways with heavy metal exposure. Oxidative stress is raised due to the unbalanced production of reactive oxygen species inside the cells. In this study, a sensitivity analysis was carried out on an existing mathematical model of the Redox system of the body to identify the parameters which are significant in controlling the process of reactive oxygen generation. After simulating the existing mathematical model, a sensitivity analysis was carried out including a local sensitivity analysis which gives the individual effect followed by a global sensitivity analysis which gives the group effect of parameter perturbations. According to the study, five parameters out of sixteen parameters in the mathematical model were identified from the local sensitivity analysis as the most sensitive parameters. Global sensitivity analysis was used to rank them according to the P values of the KS test. A constant was identified which is related to superoxide variation in the system has the highest sensitivity. Also, most of the identified sensitive parameters are correlated with enzyme driven reactions. According to the researchers' perspective, heavy metal exposure also affects the enzymes in the redox system of the body. Therefore, when modeling heavy metal toxicity we can conclude that much consideration should be given to those reactions correlated with enzymes. Keywords: CKDu, Oxidative stress, Mathematical modeling, Sensitivity analysis, Parameters