Application of support vector machines in viral biology
23 Nov 2019-pp 361-403
TL;DR: This chapter provides lucid and easy to understand details of SVM algorithms along with applications in virology, one such robust tool based rigorously on statistical learning theory.
Abstract: Novel experimental and sequencing techniques have led to an exponential explosion and spiraling of data in viral genomics. To analyse such data, rapidly gain information, and transform this information to knowledge, interdisciplinary approaches involving several different types of expertise are necessary. Machine learning has been in the forefront of providing models with increasing accuracy due to development of newer paradigms with strong fundamental bases. Support Vector Machines (SVM) is one such robust tool, based rigorously on statistical learning theory. SVM provides very high quality and robust solutions to classification and regression problems. Several studies in virology employ high performance tools including SVM for identification of potentially important gene and protein functions. This is mainly due to the highly beneficial aspects of SVM. In this chapter we briefly provide lucid and easy to understand details of SVM algorithms along with applications in virology.
Citations
More filters
TL;DR: In this paper, the authors used machine learning techniques to characterize and predict the developing spontaneous activity in mouse cortical neurons on microelectrode arrays (MEAs) during the first three weeks in vitro.
Abstract: Synchronization and bursting activity are intrinsic electrophysiological properties of in vivo and in vitro neural networks. During early development, cortical cultures exhibit a wide repertoire of synchronous bursting dynamics whose characterization may help to understand the parameters governing the transition from immature to mature networks. Here we used machine learning techniques to characterize and predict the developing spontaneous activity in mouse cortical neurons on microelectrode arrays (MEAs) during the first three weeks in vitro. Network activity at three stages of early development was defined by 18 electrophysiological features of spikes, bursts, synchrony, and connectivity. The variability of neuronal network activity during early development was investigated by applying k-means and self-organizing map (SOM) clustering analysis to features of bursts and synchrony. These electrophysiological features were predicted at the third week in vitro with high accuracy from those at earlier times using three machine learning models: Multivariate Adaptive Regression Splines, Support Vector Machines, and Random Forest. Our results indicate that initial patterns of electrical activity during the first week in vitro may already predetermine the final development of the neuronal network activity. The methodological approach used here may be applied to explore the biological mechanisms underlying the complex dynamics of spontaneous activity in developing neuronal cultures.
7 citations
TL;DR: In this article , the authors demonstrate the possibility of applying surface-enhanced Raman spectroscopy (SERS) combined with machine learning technology to detect and differentiate influenza type A and B viruses in a buffer environment.
2 citations
TL;DR: In this paper, the authors use olfactory behaviour data from the nematode C. elegans, which has isogenic populations in a laboratory setting, and employ machine learning approaches for a binary classification task predicting whether or not the worm will be attracted to a given monomolecular odorant.
Abstract: The chemical basis of smell remains an unsolved problem, with ongoing studies mapping perceptual descriptor data from human participants to the chemical structures using computational methods. These approaches are, however, limited by linguistic capabilities and inter-individual differences in participants. We use olfactory behaviour data from the nematode C. elegans, which has isogenic populations in a laboratory setting, and employ machine learning approaches for a binary classification task predicting whether or not the worm will be attracted to a given monomolecular odorant. Among others, we use architectures based on Natural Language Processing methods on the SMILES representation of chemicals for molecular descriptor generation and show that machine learning algorithms trained on the descriptors give robust prediction results. We further show, by data augmentation, that increasing the number of samples increases the accuracy of the models. From this detailed analysis, we are able to achieve accuracies comparable to that in human studies and infer that there exists a non trivial relationship between the features of chemical structures and the nematode9s behaviour.
1 citations
References
More filters
TL;DR: This study provides the first preliminary understanding of the virome of some bat populations in China, which may guide the discovery and isolation of novel viruses in the future.
Abstract: Increasing data indicate that bats harbor diverse viruses, some of which cause severe human diseases. In this study, sequence-independent amplification and high-throughput sequencing (Solexa) were applied to the metagenomic analysis of viruses in bat fecal samples collected from 6 locations in China. A total of 8,746,417 reads with a length of 306,124,595 bp were obtained. Among these reads, 13,541 (0.15%) had similarity to phage sequences and 9,170 (0.1%) had similarity to eukaryotic virus sequences. A total of 129 assembled contigs (>100 nucleotides) were constructed and compared with GenBank: 32 contigs were related to phages, and 97 were related to eukaryotic viruses. The most frequent reads and contigs related to eukaryotic viruses were homologous to densoviruses, dicistroviruses, coronaviruses, parvoviruses, and tobamoviruses, a range that includes viruses from invertebrates, vertebrates, and plants. Most of the contigs had low identities to known viral genomic or protein sequences, suggesting that a large number of novel and genetically diverse insect viruses as well as putative mammalian viruses are transmitted by bats in China. This study provides the first preliminary understanding of the virome of some bat populations in China, which may guide the discovery and isolation of novel viruses in the future.
207 citations
TL;DR: The drug's pharmacology, including pharmacokinetics and drug interactions, is discussed, as are the clinical efficacy studies that led to licensure and clinical use of maraviroc.
Abstract: Maraviroc is the first US Food and Drug Administration-approved drug from a new class of antiretroviral agents that targets a host protein, the chemokine receptor CCR5, rather than a viral target. Binding of maraviroc to this cell-surface protein results in blocking human immunodeficiency virus type 1 (HIV-1) attachment to the coreceptor and prevents the virus from entering CD4+ cells. In this review, we include the details of the discoveries that led to the development of this drug. The drug's pharmacology, including pharmacokinetics and drug interactions, is discussed, as are the clinical efficacy studies that led to licensure. HIV-1 mechanisms of resistance to maraviroc, assays to determine viral coreceptor use (tropism), drug safety, and clinical use of maraviroc are discussed at length.
205 citations
TL;DR: The application of protein interaction networks as a translational approach to the study of human disease and the challenges faced by these approaches are described.
Abstract: Proteins do not function in isolation; it is their interactions with one another and also with other molecules (e.g. DNA, RNA) that mediate metabolic and signaling pathways, cellular processes, and organismal systems. Due to their central role in biological function, protein interactions also control the mechanisms leading to healthy and diseased states in organisms. Diseases are often caused by mutations affecting the binding interface or leading to biochemically dysfunctional allosteric changes in proteins. Therefore, protein interaction networks can elucidate the molecular basis of disease, which in turn can inform methods for prevention, diagnosis, and treatment. In this chapter, we will describe the computational approaches to predict and map networks of protein interactions and briefly review the experimental methods to detect protein interactions. We will describe the application of protein interaction networks as a translational approach to the study of human disease and evaluate the challenges faced by these approaches.
194 citations
TL;DR: A wide range of immunoinformatics tools are reviewed, with a focus on B- and T-cell epitope prediction, to highlight fundamental differences in the underlying algorithms and discuss the various metrics employed to assess prediction quality, comparing their strengths and weaknesses.
Abstract: Immunoinformatics involves the application of computational methods to immunological problems. Prediction of B- and T-cell epitopes has long been the focus of immunoinformatics, given the potential translational implications, and many tools have been developed. With the advent of next-generation sequencing (NGS) methods, an unprecedented wealth of information has become available that requires more-advanced immunoinformatics tools. Based on information from whole-genome sequencing, exome sequencing and RNA sequencing, it is possible to characterize with high accuracy an individual’s human leukocyte antigen (HLA) allotype (i.e., the individual set of HLA alleles of the patient), as well as changes arising in the HLA ligandome (the collection of peptides presented by the HLA) owing to genomic variation. This has allowed new opportunities for translational applications of epitope prediction, such as epitope-based design of prophylactic and therapeutic vaccines, and personalized cancer immunotherapies. Here, we review a wide range of immunoinformatics tools, with a focus on B- and T-cell epitope prediction. We also highlight fundamental differences in the underlying algorithms and discuss the various metrics employed to assess prediction quality, comparing their strengths and weaknesses. Finally, we discuss the new challenges and opportunities presented by high-throughput data-sets for the field of epitope prediction.
170 citations
TL;DR: A novel paradigm is suggested in order to confirm that the protein interaction networks can be the target of therapy for treatment of complex multi-genic diseases rather than individual molecules with disrespect the network.
Abstract: The physical interaction of proteins which lead to compiling them into large densely connected networks is a noticeable subject to investigation. Protein interaction networks are useful because of making basic scientific abstraction and improving biological and biomedical applications. Based on principle roles of proteins in biological function, their interactions determine molecular and cellular mechanisms, which control healthy and diseased states in organisms. Therefore, such networks facilitate the understanding of pathogenic (and physiologic) mechanisms that trigger the onset and progression of diseases. Consequently, this knowledge can be translated into effective diagnostic and therapeutic strategies. Furthermore, the results of several studies have proved that the structure and dynamics of protein networks are disturbed in complex diseases such as cancer and autoimmune disorders. Based on such relationship, a novel paradigm is suggested in order to confirm that the protein interaction networks can be the target of therapy for treatment of complex multi-genic diseases rather than individual molecules with disrespect the network.
165 citations
"Application of support vector machi..." refers background in this paper
...The knowledge that is encapsulated in the PPI can help improve the biological and biomedical applications [77]....
[...]
...Eighty percent of proteins are not functional in isolated forms but they operate in complexes by interacting with other molecules [77, 78]....
[...]
...These networks are known as PPI networks (PIN) [77, 79]....
[...]