gagneurlab / absplice Goto Github PK

Hey guys, your tool looks really interesting to me! :)
And so I wanted to give it a try.

However, I stumbled over this error when running the example on my Linux-server.
Do you know how to get around it?

[Sat Dec 24 01:35:02 2022]
rule absplice_dna:
    input: mmsplice_splicemap.csv, spliceai.vcf
    output: absplice_dna.csv
    jobid: 1
    reason: Missing output files: absplice_dna.csv; Input files updated by another job: mmsplice_splicemap.csv
    resources: tmpdir=/tmp

2022-12-24 01:35:06.874355: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
  File "/home/mi/olivek95/git_projects/absplice/example/.snakemake/scripts/tmp5a1c9dig.absplice_dna.py", line 11, in <module>
    splicing_result.predict_absplice_dna()
  File "/home/mi/olivek95/git_projects/absplice/absplice/result.py", line 568, in predict_absplice_dna
    model = pickle.load(open(pickle_file, 'rb'))
AttributeError: Can't get attribute 'EBMPreprocessor' on <module 'interpret.glassbox.ebm.ebm' from '/buffer/ag_bsc/PS_SEQAN_STUDENTS/olivek95/miniconda3/envs/absplice/lib/python3.9/site-packages/interpret/glassbox/ebm/ebm.py'>
[Sat Dec 24 01:35:17 2022]
Error in rule absplice_dna:
    jobid: 1
    input: mmsplice_splicemap.csv, spliceai.vcf
    output: absplice_dna.csv

RuleException:
CalledProcessError in file /home/mi/olivek95/git_projects/absplice/example/Snakefile, line 88:
Command 'set -euo pipefail;  /buffer/ag_bsc/PS_SEQAN_STUDENTS/olivek95/miniconda3/envs/absplice/bin/python /home/mi/olivek95/git_projects/absplice/example/.snakemake/scripts/tmp5a1c9dig.absplice_dna.py' returned non-zero exit status 1.
  File "/home/mi/olivek95/git_projects/absplice/example/Snakefile", line 88, in __rule_absplice_dna
  File "/buffer/ag_bsc/PS_SEQAN_STUDENTS/olivek95/miniconda3/envs/absplice/lib/python3.9/concurrent/futures/thread.py", line 58, in run
Shutting down, this might take some time.
Exiting because a job execution failed. Look above for error message
Complete log: .snakemake/log/2022-12-24T013405.664404.snakemake.log

Initial command:
cd example; python -m snakemake -j 1

pip-installing interpret pulls a myriad of other awful pip dependencies like e.g. seaborn.
=> https://github.com/interpretml/ebm2onnx

Hi,

I am trying to implement Absplice-RNA with a VCF file and RNAseq data from the same individual. I see the example code in README is made for Absplice-DNA. Could you point out how to use Absplice-RNA?

Thanks!
Yan

I want to get CATs data to validate the absplice performance. How to get CATs data?

create a snakemake rule that joins the necessary columns from MMSplice + SpliceMap output to AbSplice

Dear Developer

Thank you for your making docker container.

I want to know about "Splicemap_tissues"

If I have a blood DNA sample but want to know the splicing mutations in the liver, can I select Splicemap_tissues for the liver?

Dear Dr. Gagneur.

We are also working on the implementation of the Absplice reported in this issue.
However, I have been working on it based on the readme at the following URL, but an error occurred in the test sample.
I would like to know what to do in this case.

The command that caused the error is as follows
python -m snakemake -j 1 --use-conda

The following is the ERROR message.

Error in rule download_splicemaps:
jobid: 4
output: splicemap_gtex_v8
shell:
splicemap_download --version gtex_v8 --splicemap_dir splicemap_gtex_v8 --tissues Testis --tissues Cells_Cultured_fibroblasts
(one of the commands exited with non-zero exit code; note that snakemake uses bash strict mode!)

Shutting down, this might take some time.
Exiting because a job execution failed. Look above for error message
Complete log: .snakemake/log/2023-05-17T141553.827340.snakemake.log

conda env create -f environment.yaml

stop at
"Solving environment: |"

I noticed that specific tissues like the retina are not included in the existing information. Could you kindly provide guidance on how to incorporate additional tissues, such as the retina, into your source code? Thanks for your help!

AbSplice was launched with the command from tutorial python -m snakemake -j 1 --use-conda from the AbSplice container, installed strictly by instructions in READ.md

End of the output:

[Fri Feb  9 17:37:54 2024]
Error in rule mmsplice_splicemap:
    jobid: 8
    input: ../data/resources/analysis_files/vcf_files/DIV_train_all_annotated.vcf.gz, ../data/resources/downloaded_files/GRCh38.primary_assembly.genome.fa, ../data/resources/downloaded_files/splicemap_hg38/Adipose_Subcutaneous_splicemap_psi5_method=kn_event_filter=median_cutoff.csv.gz, ../data/resources/downloaded_files/splicemap_hg38/Adipose_Subcutaneous_splicemap_psi3_method=kn_event_filter=median_cutoff.csv.gz
    output: ../data/results/hg38/model_scores_from_absplice_features/DIV_train_all_annotated.vcf.gz_MMSplice_SpliceMap.csv

Shutting down, this might take some time.
Exiting because a job execution failed. Look above for error message
Complete

I think that the VCF file can be the cause of the problem(despite successful annotation by SpliceAI and SPiP). It's attached below (modified extension to txt to upload it on github).
DIV_train_all_annotated.txt

Can you help me to find the cause of the error? Thank you!

Hello,

We are trying to make the container work on our slurm based HPCC. We don't have docker available to us on the server and images before allowing them to be used but .oci isn't accepted. They asked for a tar.gz version of the image to convert to a sif before we could use it.

I installed docker locally, loaded the oci following the commands on git:
docker load -i absplice.oci docker run -it --name absplice_container localhost/absplice:latest /bin/bash
Then saved to a tar.gz
docker save localhost/absplice:latest | gzip > absplice_latest.tar.gz)
The IT team created a sif for us using this and gave us the following command to load it.
singularity shell -B /n /n/app/singularity/containers/absplice.sif

However, I run into an error trying to load the conda environment and conda init bash has no effect. Is this a problem with the system that we have to run it, the process of converting to tar.gz, or the image itself? And are there any recommendations for how to get around this problem?

`[user@compute-node ~]$ singularity shell -B /n /path/to/absplice.sif
Apptainer> conda activate absplice_dock

CommandNotFoundError: Your shell has not been properly configured to use 'conda activate'.
To initialize your shell, run

$ conda init <SHELL_NAME>

Currently supported shells are:

• bash
• fish
• tcsh
• xonsh
• zsh
• powershell

See 'conda init --help' for more information and options.

IMPORTANT: You may need to close and restart your shell after running 'conda init'.`

Thank you so much for your help!!!
Shayna

Hello developers of absplice,

First of all many thanks for such a nice open-source project to improve splicing variant prediction and annotation.
I'm opening this issue because I struggle to find a license for using the code or precomputed scores. Do you happen to have a license for your wonderful project?

git+https://github.com/gagneurlab/absplice.git

Hello,
I an testing absplice on a human WGS sample using default configurations (and tissues).
Currently I ran snakemake workflow inside the docker container using 20 threads.

MMSplice finished quite qwickly, but SpliceAI in running since 6 days and is still at chr2...

Is there a way for speeding SpliceAI up?
Does SpliceAI scale up with the threads given as input to snakemake?

Do you have any plans to officially support the T2T CHM13v2.0 (hs1) reference genome?