At a glance
- Dr. T. Madhan Mohan emphasized the role of Big Data in current biotechnology research.
- Dr. Binay Panda, in his talk elaborated on the recent advancements in the field of genome sequencing which have aided our understanding on many human diseases, especially cancer.
- Dr. A.K. Mishra’s highlighted the role of biological data analytics in agriculture.
- Dr. Dinesh Gupta reviewed the applications of machine learning for analysis of high throughput data, especially related to oncology.
- Dr. M. Michael Gromiha highlighted the use of algorithms to identify protein-protein interactions based on proteins structures and function.
- Young India should take advantage of the time in leveraging the skills in Data science and related areas to solve problems in biology and biotechnology.
Brief plenary session held at Mysore at 103rd Indian Science Congress started with a talk on overview of the topic by Dr. T. Madhan Mohan (Adviser, Department of Biotechnology, Government of India) the session Chairman. He kick started the session by emphasizing the role of Big Data in current biotechnology research. The session had four speakers namely: Dr. Binay Panda (IBAB, Bangalore), Dr. Dinesh Gupta (ICGEB, New Delhi), Dr. M. Michael Gromiha (IIT, Chennai) and Dr. A.K. Mishra (IARI, New Delhi).Dr. Binay Panda, in his talk “Big Data and Personalized Medicine: Opportunities and Gaps”, elaborated on the recent advancements in the field of genome sequencing which have aided our understanding on many human diseases, especially cancer. He highlighted the role of computational biologists and bioinformatics specialists, who use various tools to discover, analyze and interpret molecular changes from terabytes of data generated from cancer sequencing studies. He also spoke about various opportunities that Big Data presents in personalized medicine and how a young and vibrant India can take advantage of the time in leveraging the skills in Information Technology to solve problems in biology in general and in the practice of precision and personalized medicine in particular.
The talk was followed by Dr. A.K. Mishra’s talk on “Big Data and Cloud Computing in Agri-bioinformatics”. He highlighted the role of biological data analytics in agriculture, especially related to climate condition, crop cultivation, crop diseases, weather forecast and irrigation related data. He pointed out that Big data in agriculture needs to be analyzed on cloud based networks to reduce costs and improve efficiency. The next talk was delivered by Dr. Dinesh Gupta, who spoke on “Big data analysis in biotechnology: applications of machine learning and challenges towards clinical applications”. He reviewed the applications of machine learning for analysis of high throughput data, especially related to oncology. He illustrated this by citing his research work to develop a machine learning method for classification of early stages of ccRcc from late stages, using transcriptional gene expression data. He concluded that the machine learning algorithms are potentially quite useful in the analysis of clinical Big Data; however, he highlighted the gap areas, which need to be addressed urgently in order to translate Big Data analysis for clinical use.
The last talk of the session was delivered by Dr. M. Michael Gromiha. His talk, entitled “Algorithms and Applications of Bioinformatics in Bigdata analysis”, was focused on big data analysis challenges emerging due to advancement of sequencing technologies, analysis of sequences for disease causing mutations. He highlighted the use of algorithms to identify protein-protein interactions based on proteins structures and function.
While highlighting the importance of Big Data analysis for India, the speakers and audience made certain recommendations:-
- Big Data collection should be done systematically, keeping in view its future applications.
- Due importance should be given to quality of data so that it is reliable and reproducible.
- For machine learning methods, a formal repositorythat sets minimal guidelines for machine learning investigation with potential clinical implementation could be developed.
- There is a need for national genome sequence database meant for clinical diagnostics and personalized medicine.
- Health care data should be collected for transforming diagnosis and improvement of treatment outcomes.
- Cloud is a good option for connecting several agricultural institutions across the country; therefore development of user friendly computational algorithms and tools is needed.
- With over 2.5 quintillion bytes created every day, data storage and analysis has become a great challenge. Cloud computing can be the solution to Big data problem.
- Along with biological data analytics, weather forecast and irrigation related data is also crucial for agricultural development and needs to be stored and analyzed.
- Technologies like, Agro-Mobile and Agro-Cloud should be made accessible to all as they provide assistance to researchers and farmers for analyzing soil and climate condition, crop cultivation, crop diseases etc.
- Considering various bottlenecks in drug discovery and development one should see a new data driven research and technology (DDRT) as highly promising approach in genomics to ease the pain.
- The large data generated with personalized diagnostics and therapy requires usage of sophisticated and multi-dimensional data analysis tools and platforms. This data deluge in modern biology also requires effective data storage, analyses, interpretation, sharing and archival policy.
- The use of machine learning approach for analysis of high throughput data especially related to oncology needs to be focused.
- The prospective applications of Big Data Analytics in different spheres of biotechnology, clinical research and gap areas need to be addressed urgently in order to get ready for real Big Data analysis for true applications for human welfare ad science.
- Bioinformatics algorithms developed should be implicated usefully in analyzing the high throughput data and high level machine learning approaches including mathematical, statistical and computational methods need to be used for various features identification and validation procedures.
- Young India should take advantage of the time in leveraging the skills in Data Science and related areas to solve problems in biology and biotechnology. The generation and availability of Big Data, along with a push for Open Data, presents an attractive opportunity to contribute to and get benefited from.
With inputs from :Dr Madhan Mohan, Adviser, Department of Biotechnology