By correcting these issues we found an increase of 18.2% predicted splice-altering variants compared with variants identified using precomputed scores alone. When assessed using diagnostic variants, updated SpliceAI scores resulted in a diagnostic increase of 11.7%.

Unfortunately these scores have limitations that can reduce their accuracy in certain contexts: For example changes in transcript annotations, altered transcript boundaries, absence of annotated genes, and changes to exon composition can mean that scores are missed or altered.

Looking at the burden that these variants may represent in rare disease we did see an appreciable increase in variants with the potential to disrupt regulation in cases vs controls, though this did not meet the threshold for significance.
link.springer.com/article/10.1...

After clinical review, 10 were selected that likely contribute to the participant’s phenotype, 6 of which are confirmed diagnoses. (huge thanks to Alex Blakes, Sid Banka and @drjennylord.bsky.social here! )

link.springer.com/article/10.1...

Looking at the genomes of 8,040 participants from @genomicsengland.bsky.social’s 100k genomes project, we systematically identified de novo variants that likely disrupt regulatory processes.

link.springer.com/article/10.1...

Super late to rare disease weekend, but how awesome is this lady! A stellar scientist, advocate for the rare disease community, mentor, & person. As a rare human, I’m so glad that people like Nicky are doing their absolute best for the rare condition community ♥️ @nickywhiffin.bsky.social

I had the honour of accompanying the wonderful Yuyang Chen to the Genetic Alliance #rareDiseaseDay2025 reception today.
It was fantastic to meet so many incredible people, and hear such powerful stories. Read the anthology “More than you can imagine” here: geneticalliance.org.uk/campaigns-an...