Predicting functional consequences of SNPs on mRNA translation via machine learning

Area of Science:

• Genomics
• Molecular Biology
• Computational Biology

Background:

• Single nucleotide polymorphisms (SNPs) are crucial in genome-wide association studies (GWAS) for identifying disease links.
• The impact of SNPs on mRNA translation and ribosome occupancy remains underexplored in disease prioritization.
• Understanding translational regulation offers new insights into genetic disease mechanisms.

Purpose of the Study:

• To investigate the functional impact of SNPs on translation by analyzing ribosome collisions.
• To identify SNPs that significantly alter ribosome occupancy (RibOc-SNPs) and their association with diseases.
• To explore the role of translational regulation in SNP-driven pathogenesis.

Main Methods:

• Application of machine learning models to genome-wide ribosome profiling data.
• Prediction of SNP function based on forecasting ribosome collisions during mRNA translation.
• Analysis of nucleotide and amino acid conversion patterns in RibOc-SNPs.

Main Results:

• Disease-related SNPs frequently cause significant changes in ribosome occupancy, termed RibOc-SNPs.
• Specific nucleotide conversions ('G → T', 'T → G', 'C → A') are enriched in RibOc-SNPs.
• RibOc-SNPs are concentrated in 5'-coding regions, indicating roles in translation initiation regulation.
• A notable percentage of RibOc-SNPs oppositely affect translation efficiency in alternative transcript isoforms.

Conclusions:

• Translational regulation is a key factor in SNP-associated disease pathogenesis.
• RibOc-SNPs provide a novel layer for prioritizing disease-causing variants from GWAS.
• SNPs can modulate gene expression by altering translation efficiency, potentially exacerbating isoform-specific effects.