Input should be in "chromosome_offset_reference_alternation" format. (hg38)
The button reports error if wrong reference allele was given. We will revise the hint messages soon.
Result
Description
Predict splicing changes and identify the specific tissues affected by the variant.
ΔSplice score > 0.27 : The variant is likely to affect splicing in a pathogenic manner.
ΔSplice score > 0.09 : The variant may affect splicing but has uncertain clinical significance.
ΔSplice score < 0.09 : The variant is unlikely to impact splicing.
The tissue columns display the predicted tissue specificity of the variant.
The Tissue z-score has been calculated and displayed. If a z-score exceeds the 95% threshold, it is marked as Sp, indicating that the variant may affect this tissue specifically.
If no columns are marked as Sp, the variant is likely to affect splicing in all tissues.
When ΔSplice score is < 0.09, the tissue specificity information is not meaningful.
Local deployment
SpTransformer source code is available at GithubThe model can be deployed locally to predict massive variants from VCF files. The model output may vary slightly depending on the CUDA version and GPU model. The results in the paper are based on CUDA 11.5 and A100 GPU.
