Pangolin
Pangolin copied to clipboard
tkzeng
Pangolin is a deep-learning method for predicting splice site strengths.
Updated one_hot_encode function to handle non-ATGCN bases more elegantly without failing
Dear Team, We are trying to run the Pangolin tool with one of the GiaB (Genome in a Bottle) WGS sample VCF file. Is there a system configuration recommendation for...
Replace PyVCF, which has been abandoned for years now and can be buggy, with pysam, which offers stricter VCF parsing rules.
Hello, I am getting this kind of error. The input files are hg38 based, db and and reference used were the same as the ones suggested in theGoogle Colab code....
Hey, These are the versions for packages I used: pangolin (1.0.2) pyvcf (0.6.8) pyfaidx (0.8.1.1) gffutils (0.12) biopython (1.83) I used this command with vcf as input file: `pangolin /Pangolin/examples/cosmic_pangolin.vcf...
Great tool! Just a future suggestion - maybe give the user the option to output pangolin results in separate columns rather than just in the INFO column of VCF files...
Pangolin provides both maximum scores and minimum scores. However, determining the cutoff value is crucial. We need to establish the specific values that indicate the significance of a splice variant...
The Pangolin seems to be computing intensive and takes a long time even with GPU, is it possible to provide an hg38 genome wide score file similar to spliceAI? Thanks.
Hi, I had some issues finding the right versions for pangolin to run. It worked by running: ``` conda install python=3.6 pip3 install torch==1.8.2 torchvision==0.9.2 torchaudio==0.8.2 --extra-index-url https://download.pytorch.org/whl/lts/1.8/cpu conda install...
https://github.com/tkzeng/Pangolin/blob/5cf94b8db938c658391b4305cd7ce33297d44ff7/pangolin/pangolin.py#LL110C1-L111C1 Trying to run pangolin with the UCSC hg38 genome, which has some lowercase sequences. "[Line 64] WARNING, skipping variant: Mismatch between FASTA (ref base: g) and variant file (ref...
