SpliceAI icon indicating copy to clipboard operation
SpliceAI copied to clipboard

How to make a custom annotation set?

Open dudududu12138 opened this issue 1 year ago • 2 comments

Hello, I saw the built-in annotation file (https://github.com/Illumina/SpliceAI/blob/master/spliceai/annotations/grch38.txt). But I want to make a custom annotation set. And I want to know how did you define exons? I mean, there are more than one transcripts in some genes. And the exons may overlap. How do you deal with the situation? I list an example below : This gene has two transcripts. Exon30976-31097 and exon 30976-31109 have the same start position but different end position.

1704197258038

Thank you very much for helping me!

dudududu12138 avatar Jan 02 '24 12:01 dudududu12138

You may find this script useful https://github.com/broadinstitute/SpliceAI-lookup/blob/master/annotations/convert_gtf_to_SpliceAI_annotation_input_format.py

It's used for updating the annotations that underly https://spliceailookup.broadinstitute.org/

On Tue, Jan 2, 2024, 7:10 AM dudududu12138 @.***> wrote:

Hello, I saw the built-in annotation file ( https://github.com/Illumina/SpliceAI/blob/master/spliceai/annotations/grch38.txt http://url). But I want to make a custom annotation set. And I want to know how did you define exons? I mean, there are more than one transcripts in some genes. And the exons may overlap. How do you deal with the situation? I list an example below : This gene has two transcripts. Exon<30976-31097> and exon <30976-31109> have the same start position but different end position. 1704197258038.png (view on web) https://github.com/Illumina/SpliceAI/assets/125525648/9ec9d784-f7bb-4ebf-8d5c-17d5dbaa9398

Thank you very much for helping me!

— Reply to this email directly, view it on GitHub https://github.com/Illumina/SpliceAI/issues/143, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABPTPKTADSKXOFPKZAL5BU3YMP2KVAVCNFSM6AAAAABBJ6KD4GVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA3DEMZTGI4DANA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

bw2 avatar Jan 02 '24 14:01 bw2

You may find this script useful https://github.com/broadinstitute/SpliceAI-lookup/blob/master/annotations/convert_gtf_to_SpliceAI_annotation_input_format.py It's used for updating the annotations that underly https://spliceailookup.broadinstitute.org/ On Tue, Jan 2, 2024, 7:10 AM dudududu12138 @.> wrote: Hello, I saw the built-in annotation file ( https://github.com/Illumina/SpliceAI/blob/master/spliceai/annotations/grch38.txt http://url). But I want to make a custom annotation set. And I want to know how did you define exons? I mean, there are more than one transcripts in some genes. And the exons may overlap. How do you deal with the situation? I list an example below : This gene has two transcripts. Exon<30976-31097> and exon <30976-31109> have the same start position but different end position. 1704197258038.png (view on web) https://github.com/Illumina/SpliceAI/assets/125525648/9ec9d784-f7bb-4ebf-8d5c-17d5dbaa9398 Thank you very much for helping me! — Reply to this email directly, view it on GitHub <#143>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABPTPKTADSKXOFPKZAL5BU3YMP2KVAVCNFSM6AAAAABBJ6KD4GVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA3DEMZTGI4DANA . You are receiving this because you are subscribed to this thread.Message ID: @.>

Thanks!!

dudududu12138 avatar Jan 03 '24 02:01 dudududu12138