Figure 1 - uploaded by Indika Perera
Content may be subject to copyright.
Source publication
With the advancement of biology and computer science, the amount of DNA sequences has grown at a rapid rate giving rise to the analysis of phylogenetic trees with many taxa. The maximum likelihood analysis is commonly considered as the best approach in phylogenetic analyses, which is extremely intensive for computation. Availability of computer res...
Contexts in source publication
Context 1
... calculates the transition probability matrices QXY for all the nodes, except the root node of a tree. QXY contains the instantaneous transition probabilities for a certain DNA nucleotide X to mutate into another nucleotide Y which is given by Equation 2 for the given tree in Figure 1. As shown in the tree in Figure 1, the site pattern Ds = (xA, xB, xC, xD, xE) are observed at the terminal nodes labeled by the sequences A, B, C, D, E. The ancestral states (xF, xG, xH) at the internal nodes labeled F, G, H are unknown. ...
Context 2
... contains the instantaneous transition probabilities for a certain DNA nucleotide X to mutate into another nucleotide Y which is given by Equation 2 for the given tree in Figure 1. As shown in the tree in Figure 1, the site pattern Ds = (xA, xB, xC, xD, xE) are observed at the terminal nodes labeled by the sequences A, B, C, D, E. The ancestral states (xF, xG, xH) at the internal nodes labeled F, G, H are unknown. In Equation 2, kXY denotes the expected number of substitutions (branch lengths) that occur between nodes X and Y, rs denotes relative rate for site S, and í µí¼ denotes frequency, and Pij represents transition probability matrix to get from state i to state j after a substitution at a site. ...
Citations
... A considerable amount of time was spent on the model training process and this can be reduced by using proper techniques to utilize hardware utilization. Besides, the parallel implementation of these classification algorithms can be accelerated using Graphics Processing Unit (GPU) (Welivita et al. 2017;Welivita et al. 2018;Rajapaksa et al. 2019). Hence, computer-intensive tasks can reduce a considerable amount of processing time. ...
Alzheimer's Disease (AD) is a progressive neurological disease commonly found in adults over 65 years. Significant growth is estimated for this neurological disorder where diagnosis should be handled effectively and efficiently. Therefore, early detection and medication are crucial in the progression of AD. This study focuses on developing a deep-learning-based computational model by considering Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) as the neurological modalities. These two types of modalities provide rich information on the neurological and anatomical aspects of the human brain to assist AD identification. We consider three main architectures namely, Capsule network, Dense Net and Inception V3 as the learning models. The optimized Inception V3 model has shown high accuracy results of 96.05% and 95.49% for MRI and PET data, respectively.
... Addition to that it is expected to increase the performance of genetic distance calculation tree construction methods by integrating GPU capabilities [28]. Once the entire phylogenetic tree construction and updating workflow is built, it is expected to integrated with our existing bioinformatics learning workflow [29]. ...
Phylogenetics is one of the dominant data engineering research disciplines based on biological information. More particularly here, we consider raw DNA sequences and do comparative analysis in order to come up with meaningful conclusions. When representing evolutionary relationships among different organisms in a concise manner, the phylogenetic tree helps significantly. When constructing phylogenetic trees, the elementary step is to calculate the genetic distance among species. Alignment-based sequencing and alignment-free sequencing are the two leading distance computation methods that are used to find genetic relatedness of different species. In this paper, we propose a novel alignment-free, pairwise, distance calculation method based on k-mers and a state of art machine learning-based phylogenetic tree construction mechanism. With the proposed approach, we can convert longer DNA sequences into compendious k-mer forests which gear up the efficiency of comparison. Later we construct the phylogenetic tree based on calculated distances with the help of an algorithm build upon k-medoid clustering, which guaranteed significant efficiency and accuracy compared to traditional phylogenetic tree construction methods.
Survival analysis is a critical task in glioma patient management due to the inter and intra tumor heterogeneity. In clinical practice, clinicians estimate the survival with their experience, which can be biased and optimistic. Over the past decades, diverse survival analysis approaches were proposed incorporating distinct data such as imaging and genetic information. The remarkable advancements in imaging and high throughput omics and sequencing technologies have enabled the acquisition of this information of glioma patients eficiently, providing novel insights for survival estimation in the present day. Besides, in the past years, machine learning techniques and deep learning have emerged into the field of survival analysis of glioma patients trading off the traditional statistical analysis-based survival analysis approaches. In this survey paper, we explore the prognostic parameters acquired, utilizing diagnostic imaging techniques and genomic platforms for survival or risk estimation of glioma patients. Further, we review the techniques, learning and statistical analysis algorithms, along with their benefits and limitations used for prognosis prediction. Consequently, we highlight the challenges of the existing state-of-the-art survival prediction studies and propose future directions in the field of research.
