China
Africa
Explore chapters and articles related to this topic
Bioinformatics
Published in Hajiya Mairo Inuwa, Ifeoma Maureen Ezeonu, Charles Oluwaseun Adetunji, Emmanuel Olufemi Ekundayo, Abubakar Gidado, Abdulrazak B. Ibrahim, Benjamin Ewa Ubi, Medical Biotechnology, Biopharmaceutics, Forensic Science and Bioinformatics, 2022
O. M. Oyawoye, H. A. Olorunsola, A. O. Oluduro, O. O. Bamigboye, E. K. Oladipo, T. M. Olotu, I. J. Adeosun, M. O. Kaka, O. O. Obembe
The term “bioinformatics” is an abbreviation for “Biological Informatics.” It is a combination of biological sciences and computer science, and many scientists now refer to it as computational biology. It became more recognized following the establishment of the human genome project (Kumar et al., 2017). Bioinformatics is a field that brings together computer science, information technology, and biology into one. Genomics, proteomics, genetics, transcriptomics, and evolution are only a few of the biological sciences covered. The goal of the field is to allow for the discovery of new biological ideas as well as the creation of a global context from which to comprehend unifying biological principles.
Computational Biology for Clinical Research
Published in Rishabha Malviya, Pramod Kumar Sharma, Sonali Sundram, Rajesh Kumar Dhanaraj, Balamurugan Balusamy, Bioinformatics Tools and Big Data Analytics for Patient Care, 2023
Rakhi Mishra, Rupa Mazumder, Prem Shankar Mishra
A level of understanding of the components and the organizational structure of the system is necessary to formulate initial hypotheses about how the system operates. Computational biology consists of a series of theories and applications used to translate biology into mechanisms for advancement in the discovery of medicines. This helps in the understanding of biological testing more practically and rigorously and aids in forming a bridge to hold different insights on a single platform. While technical developments provide opportunities, conceptual advances are the proper drivers of progress. This chapter has reviewed the principles of systems biology, which further can be applied to translational research. The molecular and cellular level of data studies can be performed with the use of different computer tools, among which is one of the latest and most advanced resources for research. The ultimate object of computational biology is to develop predictive computational models of a disease, which will provoke a revolution in the diagnosis process and provide the mechanistic understanding necessary for personalized therapeutic approaches. To obtain the factor of causes and their effect on the severity of the disease, it is necessary to understand and analyze the patient and the disease data which can be done by the computational approach. Additionally, biologically meaningful information can be derived from diagnostic tests if interpreted in functional relationships rather than as independent measurements. Such systems-biology-based diagnostics will transform disease taxonomies from the phenotypical to the molecular and allow physicians to select optimal therapeutic regimens for individual patients. Combining computational methods and computational modeling with systems thinking can lead to the development of a “virtual sandbox” in which researchers can utilize their creativity and intuition to try out and explore multiple different hypotheses and lines of investigation.
Quantum technology a tool for sequencing of the ratio DSS/DNA modifications for the development of new DNA-binding proteins
Published in Egyptian Journal of Basic and Applied Sciences, 2022
Adamu Yunusa Ugya, Kamel Meguellati
Quantum computers are a new generation of devices that perform computational tasks by utilizing quantum phenomena such as superposition and entanglement [12]. Quantum computers are thought to have a high potential to outperform present technologies in a variety of tasks [13], including modeling complicated systems [14], machine learning [15], and optimization [16]. The subject of how quantum computers could be employed for computational biology and bioinformatics is still being intensively in search [17]. Grover’s search, which may be used as a subroutine for sub-sequence alignment with a quadratic speedup [18], is one of the techniques that can be achieved utilizing quantum computers. In the computational biology domain, there has been an upsurge in activity at the intersection of machine learning and quantum computing [19]. The proposed quantum algorithms [20], which are of great interest in terms of obtaining polynomial and exponential computational speedups, necessitate a large number of qubits and extremely low error rates, which are both beyond the capabilities of current noisy intermediate-scale quantum (NISQ) devices. Many different quantum computing implementations and models have been developed. But no literature report has shown how this sequencing method can aid in the discovery of new domain for DNA-binding proteins despite the promising of quantum microscopy and nanopore sequencing. The current study is aimed at reviewing the available literature on the quantum sequencing method and predicting the role of the quantum sequencing method in the discovery of new domain for DNA-binding proteins.
DeepCOVID-19: A model for identification of COVID-19 virus sequences with genomic signal processing and deep learning
Published in Cogent Engineering, 2022
Emmanuel Adetiba, Joshua A. Abolarinwa, Anthony A. Adegoke, Tunmike B. Taiwo, Oluwaseun T. Ajayi, Abdultaofeek Abayomi, Joy N. Adetiba, Joke A. Badejo
Deep learning architectures have been applied in diverse bioinformatics, computer vision, and computational biology studies including classification and prediction of DNA and RNA-binding specificity (Trabelsi et al., 2019). According to (Alipanahi et al., 2015), the DeepBind for instance, utilized a single layer of convolution in a Convolutional Neural Network (CNN) architecture to learn a signal detector that recapitulate known motifs while (Zeng et al., 2016) investigated other parameters in architectures including the number of layers and operations such as pooling. Other studies such as iDeepS (Pan et al., 2018) and DanQ (Quang & Xie, 2016) have used more complex architectures integrating both the CNN and Recurrent Neural Network (RNN) layer models. In a separate study, the KERGU method (Shen et al., 2018), which is a purely RNN-based architecture utilized a layer of bidirectional Gated Recurrent Units (bi-GRUs). This was combined with a k-mer, embedding representation of input sequence to create an internal state of the network that allows it to capture long-range dependencies.
Deep learning for predicting toxicity of chemicals: a mini review
Published in Journal of Environmental Science and Health, Part C, 2018
Weihao Tang, Jingwen Chen, Zhongyu Wang, Hongbin Xie, Huixiao Hong
Deep learning is a subfield of machine learning, the core technique in artificial intelligence.45,46 In March 2016, AlphaGo, a “go” (one of the ancient board games originated from East Asia also known as Weichi)-playing robot developed by Google with core deep learning algorithms, defeated Sedol Lee, one of the top human players in the world. This surprising event spurred extensive interest in artificial intelligence revival.47 Deep learning has been employed extensively in image analysis, speech recognition and natural language processing.48–51 Recently, deep learning has been extended to use in bioinformatics, computational biology and QSARs.43,52,53 In 2012, the winning Merck activity prediction challenge team (https://www.kaggle.com) developed a deep learning QSAR model that significantly improved prediction performance compared with those generated by random forest models.54 More recently, a deep learning QSAR model won the Tox21 toxicity prediction challenge (https://tripod.nih.gov/tox21/challenge), which aimed to compare the capabilities of different machine learning algorithms for toxicity prediction.55 Clearly, deep learning algorithms can achieve stellar performance in chemical toxicity prediction, especially in the “big data” era.