Transformers significantly improve splice site prediction
2024

Transformers Improve Splice Site Prediction

Sample size: 17848 publication 10 minutes Evidence: high

Author Information

Author(s): Jónsson Benedikt A., Halldórsson Gísli H., Árdal Steinþór, Rögnvaldsson Sölvi, Einarsson Eyþór, Sulem Patrick, Guðbjartsson Daníel F., Melsted Páll, Stefánsson Kári, Úlfarsson Magnús Ö.

Primary Institution: deCODE Genetics/Amgen Inc.

Hypothesis

Large contexts are essential for tracking splice sites in pre-mRNA sequences.

Conclusion

The transformer-based method outperforms existing tools in detecting splice sites and disease-related variants.

Supporting Evidence

  • The transformer model achieved a PR-AUC of 0.834, outperforming SpliceAI's 0.820.
  • Transformer-45k detected 744 more splice sites than SpliceAI-10k.
  • The model demonstrated superior accuracy in identifying pathogenic splice variants.

Takeaway

This study shows that a new method using transformers can better find important parts of genes that help make proteins.

Methodology

The study used a transformer model trained on RNA sequencing data to predict splice sites from long nucleotide sequences.

Potential Biases

Potential bias due to reliance on specific training datasets.

Limitations

The model's performance may be affected by the quality of splice site annotations from RNA-Seq data.

Participant Demographics

The Icelandic cohort consisted of 17,848 individuals, including 9,784 females and 8,064 males.

Statistical Information

P-Value

0.001

Confidence Interval

[0.833, 0.835]

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1038/s42003-024-07298-9

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication