Abstract
Today, genomic data holds great potential to improve healthcare strategies across various dimensions – be it disease prevention, enhanced diagnosis, or optimized treatment. The biggest hurdle faced by the medical and research community in India is the lack of genotype-phenotype correlations for Indians at a population-wide and an individual level. This leads to inefficient translation of genomic information during clinical decision making. Population-wide sequencing projects for Indian genomes help overcome hurdles and enable us to unearth and validate the genetic markers for different health conditions. Machine learning algorithms are essential to analyze huge amounts of genotype data in synergy with gene expression, demographic, clinical, and pathological data. Predictive models developed through these algorithms help in classifying the individuals into different risk groups, so that preventive measures and personalized therapies can be designed. They also help in identifying the impact of each genetic marker with the associated condition, from a clinical perspective. In India, genome sequencing technologies have now become more accessible to the general population. However, information on variants associated with several major diseases is not available in publicly-accessible databases. Creating a centralized database of variants facilitates early detection and mitigation of health risks in individuals. In this article, we discuss the challenges faced by genetic researchers and genomic testing facilities in India, in terms of dearth of public databases, people with knowledge on machine learning algorithms, computational resources and awareness in the medical community in interpreting genetic variants. Potential solutions to enhance genomic research in India, are also discussed.
Highlights
Dynamic migration history, ethnic and genetic diversity and a high degree of consanguinity contribute to the complex and heterogeneous nature of the Indian population
While tried and tested statistical methods work fairly well for biomarker discovery, advanced solutions like machine learning algorithms bring a promise of genomics driven clinical solutions
Establishing the genetic cause of disease is vital for patient care and treatment, and clinical findings must be reported with high precision and accuracy (Singh et al, 2016)
Summary
Ethnic and genetic diversity and a high degree of consanguinity contribute to the complex and heterogeneous nature of the Indian population. Genetic diagnosis via clinical sequencing (e.g., genome-, exome-, single-, or multi-gene) is the front-line test recommended for many inherited diseases (Verma et al, 2018; Ganapathy et al, 2019). Establishing the genetic cause of disease is vital for patient care and treatment, and clinical findings must be reported with high precision and accuracy (Singh et al, 2016).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
