From function to translation: Decoding genetic susceptibility to human diseases via artificial intelligence

• Published in: Cell genomics 2023-06, Vol.3 (6), p.100320-100320, Article 100320
• Main Authors: Long, Erping, Wan, Peixing, Chen, Qingyu, Lu, Zhiyong, Choi, Jiyeon
• Format: Article
• Language: English
• Subjects: artificial intelligence; functional genomics; genome-wide association studies; translational genomics
• ISSN: 2666-979X; 2666-979X
• DOI: 10.1016/j.xgen.2023.100320

While genome-wide association studies (GWAS) have discovered thousands of disease-associated loci, molecular mechanisms for a considerable fraction of the loci remain to be explored. The logical next steps for post-GWAS are interpreting these genetic associations to understand disease etiology (GWAS functional studies) and translating this knowledge into clinical benefits for the patients (GWAS translational studies). Although various datasets and approaches using functional genomics have been developed to facilitate these studies, significant challenges remain due to data heterogeneity, multiplicity, and high dimensionality. To address these challenges, artificial intelligence (AI) technology has demonstrated considerable promise in decoding complex functional datasets and providing novel biological insights into GWAS findings. This perspective first describes the landmark progress driven by AI in interpreting and translating GWAS findings and then outlines specific challenges followed by actionable recommendations related to data availability, model optimization, and interpretation, as well as ethical concerns. [Display omitted] Long et al. summarize the artificial intelligence (AI) approaches used to decode the gene regulatory roles of non-coding variants from genome-wide association studies (GWAS) and to link them to target genes and downstream pathways in the cellular context. They highlight the potential impact of AI in two main directions of GWAS translational studies: drug repurposing and disease risk prediction. They outline specific challenges in these areas and provide actionable recommendations related to data availability, model interpretation, and ethical concerns.