Is masking working for this variant?

[DELAMHACH]

Hi -

For the variant at 17-41256878-C-T, with or without masking, and with the Max distance >=95, SpliceAI is showing an Acceptor Gain | 0.21 | 95 bp. 95bp is the distance to the nearest native acceptor site: https://grch37.ensembl.org/Homo_sapiens/Location/View?db=core;g=ENSG00000012048;r=17:41256878-41256974

I am struggling to understand if this is a true gain of strength at the native acceptor or if masking is failing in this instance.

I have not yet found a second variant with this issue and have tested at least one other on a different exon without issue. However Pangolin is not showing such a gain.

VARIANT: https://spliceailookup.broadinstitute.org/#variant=17-41256878-C-T&hg=37&distance=500&mask=1&ra=0

Mostly highlighting to make sure it is not a systematic issue.

[bw2]

I think the donor loss score is being masked correctly because the +16bp position is not at an annotated splice site.
The masking behavior of the donor/acceptor gain scores seems inconsistent, the same as in
#58

Either both of them should be masked or neither of them. This appears to be a common bug for spliceai gain scores whose positions fall on the last base of an exon. I haven't yet tracked it down in the code.

[RubyDawes]

Hiya, did you ever track down a bug causing this? i have a few more variants showing the same behaviour.

[bw2]

Could you please share additional examples?

[RubyDawes]

1-237727120-T-C
1-237727203-G-A

These two are on the same exon. When I retrieve masked scores for the first it still shows the donor gain score for the annotated donor at 237727120, the second variant masked still shows the acceptor gain score for the annotated acceptor at 237727087.

19-1425963-G-A

This one masked shows acceptor gain score for the annotated acceptor at 1425878.

Thanks so much for responding so quickly! I'm fairly sure these seem to be missing masking, but not sure if i've overlooked something! :)

[bw2]

The recommendation from SpliceAI authors is to ignore the masking property for junctions that are not the closest junctions to the variant. I'm not sure how to best address this in the user interface.

[RubyDawes]

Thanks for following that up!