China
Africa
Explore chapters and articles related to this topic
Artificial Intelligence for Precision Medicine
Published in Kamal Kumar Sharma, Akhil Gupta, Bandana Sharma, Suman Lata Tripathi, Intelligent Communication and Automation Systems, 2021
Genomics is big data. The genome of a human involves 3 billion base pairs of nucleotides. The Human Genome Project (HGP), a 13-year worldwide project, costs billions of dollars to map and sequence the entire human genome by the year 2003. The achievements of the HGP generated a good deal of genome-wide association studies (GWASs) and led to several advances in human genomics. Results from such research are assembled in the GWAS Catalogue database that is maintained by the European Bioinformatics Institute (EMBL-EBI) and the National Human Genome Research Institute (NHGRI). These GWASs have dramatically enhanced insights into the genetics of human disorders and contributed to developing novel drug targets. Over the past 15 years, the cost of WGS has decreased significantly. Such declines in expenses promote several kinds of research to adopt sequencing techniques. Lately, the UK Biobank (UKB), a longitudinal study of 500 000 UK resident, has published the data on whole-exome sequencing (WES) for the initial sample of 50 000 participants [6].
Radiation Therapy and Radiation Safety in Medicine
Published in Suzanne Amador Kane, Boris A. Gelman, Introduction to Physics in Modern Medicine, 2020
Suzanne Amador Kane, Boris A. Gelman
The complete collection of information stored in an organism's DNA is called its genome; in humans, this comprises roughly six billion base pairs. The sequence of base pairs in DNA specifies the construction of the body's proteins. Proteins are another variety of polymer, which form the basis of the body's functional and structural organization; proteins are chains of chemical groups called amino acids. In the DNA molecule, triplets of bases (sets of three nucleic acids in a row) code for each one of the twenty amino acids that are the building blocks of proteins; for example, the three nucleic acids, AAA, code for the amino acid lysine, while TAC codes for the amino acid tyrosine. Thus, the sequence of base pairs along a strand of DNA is a blueprint for constructing proteins (Figure 7.4a). To first approximation, the segment of DNA required to describe the construction of a protein is called a gene.
Semi-supervised Learning
Published in Peter Wlodarczak, Machine Learning and its Applications, 2019
Supervised methods use labeled data for training, unsupervised methods are applied on unlabeled data and have to determine feature importance by themselves. Semi-supervised methods follow a hybrid approach. Sometimes, we have a small number of labeled instances and a large number of unlabeled instances. For instance, a fraud detection application in a financial institution might be able to detect known types of fraud, but there are many new, unknown types of fraud that the system might miss. In this case, semi-supervised methods can be applied. This has several advantages. Labeling data, which is a time consuming and costly approach, is often performed by a data scientist. Manual labeling can also introduce human bias. Using unlabeled data during training can improve accuracy and often semi-supervised methods perform considerably better than unsupervised methods. For instance, the human genome consists of approximately 3 billion base pairs. Labeling the whole DNA for whole genome sequencing is virtually impossible. Using semi-supervised methods gives access to large amounts of unlabeled data where assigning supervision information would be impossible. Semi-supervised methods attempt to improve classification accuracy by using both, labeled and unlabeled data instead of training the model just on a small portion of manually labeled data or using an unsupervised approach on the unlabeled data. However, using semi-supervised methods is not always possible and we often do not know the distribution of the unlabeled data.
Toxic and genotoxic effects of graphene and multi-walled carbon nanotubes
Published in Journal of Toxicology and Environmental Health, Part A, 2018
In order to resolve the issue of genotoxic potential of graphene and MWCNT the mouse lymphoma assay (MLA) was used. The MLA assay detects mutations at the thymidine kinase (TK) gene based upon the fact that mutant cells are resistant to the cytotoxic actions of pyrimidine analogs such as trifluorothymidine (TFT). This assay is under OECD guidelines (OECD, 2015) and consequently recommended by several international regulatory agencies. The assay utilizes a specific mammalian cell line, namely L5178Y/Tk+/–3.7.2C mouse lymphoma cell line, and a forward mutation in the TK locus (from TK± to TK−/-) to generate TK deficient cells sensitive to TFT. Mutations may be induced by base pair changes, frameshift, and small deletions. At this point, it should be emphasized that although many genotoxicity studies were carried out testing graphene and MWCNT, there is a lack of data using gene mutation approaches. In fact, no apparent reports utilizing MLA were found examining the influence of graphene or MWCNT on gene mutations. Thus, the aim of the present study was to determine the influence of graphene platelets and MWCNT as pure, COOH functionalized, and NH2 functionalized on cytotoxic and mutagenic responses in MLA. In addition to mutagenicity, other endpoints were also assessed to establish underlying mechanisms of action.
A Chaotic Approach to Recognize the Characteristics of Genetic Codes of Covid Patients
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
DNA is composed of two strands that spiral around one another like a twisted ladder and four nucleotides adenine(A), thymine(T), guanine(G), cytosine(C). In which a base pair (bp) consists of two nucleotides joined together by hydrogen bonds. According to traditional Watson–Crick base pairing, A forms a base pair with T using two hydrogen bonds, whereas G forms a base pair with C using three hydrogen bonds. As a result, A and T are complementary to one another, just as C and G. The structure and base pairing of DNA is shown in Figure 1.
Secure, Lossless, and Noise-resistive Image Encryption using Chaos, Hyper-chaos, and DNA Sequence Operation
Published in IETE Technical Review, 2020
K. Abhimanyu Kumar Patro, Bibhudendra Acharya, Vijay Nath
A DNA sequence is composed of four different nucleic acid bases such as Adenine (A), Cytosine (C), Guanine (G), and Thymine (T). According to Watson–Crick base pairing rule [38], the DNA bases A and G are always in pairs with T and C, respectively. Hence the base pairs A and T, G and C are complementary to each other.