-
Notifications
You must be signed in to change notification settings - Fork 32
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
annotate_esm error #63
Comments
I had the same issue. Below is the error from log:
Seems like from torch._C import * is not working. |
@yotsa To figure out what went wrong we need the log of the rule that failed. In your case it is rule @zihhuafang Not sure if it is the same error because right now we do not know the exact caus eof the faile. Just that the rule exited unexpected. About you error: seems that the conda environment is not correct. Did you use conda or mamba? (recommend to use mamba). And the channel priority have to be set to strict. |
Max, Thanks for the reply. How do I prevent the log file getting deleted after a failed run though?
Yot
Get Outlook for Android<https://aka.ms/AAb9ysg>
…________________________________
From: Max ***@***.***>
Sent: Thursday, April 25, 2024 2:42:34 PM
To: kircherlab/CADD-scripts ***@***.***>
Cc: Yotsawat ***@***.***>; Mention ***@***.***>
Subject: Re: [kircherlab/CADD-scripts] annotate_esm error (Issue #63)
@yotsa<https://github.com/yotsa> To figure out what went wrong we need the log of the rule that failed. In your case it is rule annotate_esm /tmp/tmp.5xupN9W1bE/input.annotate_esm.log. Log might be already deleted because in the tmp directory. Maybe rerun again.
@zihhuafang<https://github.com/zihhuafang> Not sure if it is the same error because right now we do not know the exact caus eof the faile. Just that the rule exited unexpected. About you error: seems that the conda environment is not correct. Did you use conda or mamba? (recommend to use mamba). And the channel priority have to be set to strict.
—
Reply to this email directly, view it on GitHub<#63 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AB3Z6XAUX3C5E5Q53ZLSNQLY7CXWVAVCNFSM6AAAAABGUQPLJ6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANZWGU3DSMRUG4>.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Don't use the CADD.sh script :-) You can run snakemake seperately as described also in the readme. E.g. via |
I confirmed that I use mamba and set the channel priority to strict. I attached the list of packages installed by snakemake (7.32.3).
|
So what's the final fix? did any of you figure out? |
how did you set the priority? and confirm that you are using mamba itself? |
Even my log file prints the same error.
not sure how to go ahead! |
seems to be a recent bug with torch and mkl 2024.1.0 (new mkl release from 26th of March), see here: pytorch/pytorch#123097 and here https://pypi.org/project/mkl/#history. Apparently downgrading to mkl 2024.0.0 solves it for now. Can you try this by manually going into the respective environment ( |
Hey, I tried convert the mkl 2024.1.0 to 2024.0.0 After all this, I faced another issue! Which has been raised and closed i.e mmsplice1.0.1 but hasn't been resolved yet. The issue is that installing mmsplice1.0.1 has too many issues with its dependency libraries and upon installing the latest version of mmsplice does work out at the end but the predicted values arent right. |
I released a new CADD-scripts version v1.7.1. Maybe you try that one. Now it is recommended to use apptainer/singularity and all environments are packed within a container and no conda builds are needed (container is 17GB large). You also need now snakemake 8. Also I updated the environments. So If you use mamba/conda instead I hope you will not face the issues you had above |
Hi,
I installed CADD v 1.7 and downloaded the annotations/prescored files separately and put them in the appropriate folders. I then run ./CADD.sh test/input.vcf to test the software, then I get this error
Can you diagnose what's wrong and how to solve this?
Thank you
Yot
The text was updated successfully, but these errors were encountered: