Harnessing Artificial Intelligence in Genomics for the Prevention of Recessive Disorders: An Overview
Jatin Dahiya
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Mohammad Salman Khan
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Shivam Jaiswar
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Rashmi Ojha
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Akanksha Maurya
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Parvez Ahmad
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Manoj Kumar Mishra
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Pankaj Gupta
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
Amit Mani Tiwari
Department of Biotechnology, Era University, Lucknow-226003, Uttar Pradesh, India.
Ritika Saxena
Faculty of Biotechnology, Institute of Biosciences & Technology, SRM University, Barabanki, Uttar Pradesh, India.
Sanjay Mishra
*
Department of Biotechnology, SR Institute of Management and Technology, Bakshi ka Talab, Sitapur Road, NH-24, Lucknow-226201, Uttar Pradesh, India.
*Author to whom correspondence should be addressed.
Abstract
Recessive genetic disorders, frequently concealed within heterozygous carriers, reveal a substantial challenge in context of clinical genetics owing to their asymptomatic characteristics in carriers and the profound consequences when transmitted in a bi-allelic manner. These disorders contribute significantly to the global burden of inherited diseases, with prevalence influenced by ethnicity, population genetics, and consanguinity patterns. The emergence of next-generation sequencing has facilitated the accessibility of extensive genomic data; nonetheless, the intricacies of interpretation continue to present a significant impediment. The fields of artificial intelligence (AI) and machine learning are now transforming the genomic landscape by facilitating comprehensive analyses of genomic variants, amalgamating phenotype data, and forecasting disease risks with enhanced speed and precision. This review examines the contemporary AI-driven methodologies employed in the prevention of recessive disorders through carrier screening, embryo selection, and extensive population analyses. We reference recent advancements, including AI systems such as PhenIX, X rare, Deep Variant, and prioritization frameworks based on GPT-4. Additionally, we address ethical considerations, challenges pertaining to clinical translation, and the potential of generative artificial intelligence in the context of genetic counseling. By scrutinizing both the technical evolution and translational significance, this review positions artificial intelligence as an indispensable instrument in predictive and preventive genomic medicine. However, the integration of artificial intelligence in genomics is not without limitations, including algorithmic bias, data privacy concerns, and underrepresentation of diverse populations in training datasets. These challenges may affect diagnostic accuracy and equitable clinical implementation, underscoring the need for careful validation and ethical oversight.
Keywords: Artificial intelligence, bioinformatics, carrier screening, clinical decision support, genomic analysis, machine learning, predictive genomics, rare diseases, recessive disorder