Topics In Demand
Notification
New

No notification found.

The Rise Of Data Science In Biotechnology
The Rise Of Data Science In Biotechnology

October 10, 2022

215

0

 

Proteins are twisted and folded into specific shapes in every human cell. Protein shapes influence protein function, making them important for understanding disease mechanisms and developing new drugs. DeepMind announced in July 2021 that it had used artificial intelligence (AI) to predict the shape of nearly every protein in the human body and hundreds of thousands of proteins in other organisms. Despite varying degrees of accuracy, they could share over 350,000 newly predicted protein structures.

 

Omics, deep learning, and bioinformatics

The fusion of computer science and biology has traditionally been referred to as "bioinformatics," focusing on the sequencing of proteins in the early 1950s and DNA in the 1970s. Bioinformatics aims to evaluate and make sense of these enormous and intricate biological data sets, which include studies on anything from proteins to metabolites, including genomics (the study of genomes) and transcriptomics (the study of RNA transcripts).

 

For biotechnologists attempting to identify, stop, and cure human diseases, analyzing this data, generally known as "omics," is important. Researchers can use the data from these various fields to better understand and cure diseases. Pharmaceutical businesses do, in fact, employ biological data in a variety of ways throughout their research and development processes.

 

More Than Drug Development

 

In addition to changing how drugs are developed, data science is also altering how diseases are understood, identified, and tracked by researchers. 

  • By examining genetic changes in the SARS-CoV-2 virus and gauging the resilience of human antibodies to the virus, Amgen's subsidiary deCode Genetics monitored the spread of COVID-19 in Iceland in 2020.
  • However, biological information was also in use during the pandemic in more obvious ways, such as apps to track COVID-19 symptoms and wearables to monitor baseline vitals. 
  • Fitbits and other wearable devices are, in fact, adding to the body of human health data that may be studied to aid in the development of novel biotechnology. These devices also enable biopharmaceutical firms to monitor patients and track the negative effects of medications in novel ways.
  • Other researchers are using deep learning to assist radiologists in interpreting medical imaging results. For instance, machine learning can be able to identify a particular type of stroke faster than an experienced professional using the results of brain imaging. Studies are now evaluating the optimal use cases for this kind of machine-assisted diagnostics. 

 

 

The prospects for new job paths in data science within biotechnology are growing as the uses for biological data are diversifying. ABE will highlight some of the outstanding individuals working at the nexus of biotechnology and data science in the upcoming articles in this series.

 

The creation of tools to analyze the data and anticipate the targets of T-cell responses with high accuracy and specificity was forced by the need for computation and, in particular, the advances in machine learning.

 

The resources needed to understand and evaluate biological data have expanded along with the volume of that data. Biologists now have access to powerful supercomputers, rapid sequencing technologies, and machine learning techniques, as opposed to the slow computers, primitive sequencers, and microscopes of the past.

 

Machine learning is a subset of AI that uses algorithms to efficiently complete data analysis tasks previously carried out manually or were just impractical due to the intricate connections between multiple sets of data. When combined with powerful computation, machine learning has facilitated "deep learning" innovations like the most recent DeepMind protein shape predictions. Researchers can test known drug libraries against possible disease targets and detect genetic and other risk factors using the same set of technologies.

 

Learning in-depth information about a certain topic or domain is called domain specialization.


 


That the contents of third-party articles/blogs published here on the website, and the interpretation of all information in the article/blogs such as data, maps, numbers, opinions etc. displayed in the article/blogs and views or the opinions expressed within the content are solely of the author's; and do not reflect the opinions and beliefs of NASSCOM or its affiliates in any manner. NASSCOM does not take any liability w.r.t. content in any manner and will not be liable in any manner whatsoever for any kind of liability arising out of any act, error or omission. The contents of third-party article/blogs published, are provided solely as convenience; and the presence of these articles/blogs should not, under any circumstances, be considered as an endorsement of the contents by NASSCOM in any manner; and if you chose to access these articles/blogs , you do so at your own risk.


© Copyright nasscom. All Rights Reserved.