ColabFold
ColabFold copied to clipboard
Batch input_dir result_dir
Expected Behavior
I have successfully mounted my google drive and the batch ColaFold states using the Alphafold2 batch notebook at https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/batch/AlphaFold2_batch.ipynb
#@title Mount google drive from google.colab import drive drive.mount('/content/drive') Mounted at /content/drive
Subsequently I tried to specify the input_dir and results_dir through input_dir: /content/drive/MyDrive/input_fasta result_dir: /content/drive/MyDrive/result
Followed by successful "Install dependencies" and "Run Prediction"
Current Behavior
For "Run Prediction" I get an error message
OSError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/colabfold/batch.py in get_queries(input_path, sort_queries_by) 389 input_path = Path(input_path) 390 if not input_path.exists(): --> 391 raise OSError(f"{input_path} could not be found") 392 393 if input_path.is_file():
OSError: /content/drive/MyDrive/input_fasta could not be found
I am using a Mac book and my Google drive is mounted at /Users/name/Google Drive/My Drive This directory contains the two directories "input_fasta" and "result".
Steps to Reproduce (for bugs)
I am using https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/batch/AlphaFold2_batch.ipynb
ColabFold Output (for bugs)
See above
Context
So I guess I have to specify the input_dir and result_dir in a different manner. Any help would be appreciated.
Your Environment
macOS High Sierra Version 10.13.6 MacBook Pro
It seems that the input path could not be resolved. One way to get the correct path is to navigate to your input_fasta
folder using the file navigator in Colab (see screenshot). Once you found your input_fasta
folder use the right click on it and select "Copy path". Now the correct path should be in your clipboard, just past it in the input_dir
form-field.

Thanks! Now it seems to be running. Best Markus
From: Martin Steinegger @.> Reply-To: sokrypton/ColabFold @.> Date: Monday, 7. March 2022 at 15:49 To: sokrypton/ColabFold @.> Cc: "Zweckstetter, Markus" @.>, Author @.***> Subject: Re: [sokrypton/ColabFold] Batch input_dir result_dir (Issue #173)
It seems that the input path could not be resolved. One way to get the correct path is to navigate to your input_fasta folder using the file navigator in Colab (see screenshot). Once you found your input_fasta folder use the right click on it and select "Copy path". Now the correct path should be in your clipboard, just past it in the input_dir form-field.
[Screenshot 2022-03-07 at 23 45 35]https://user-images.githubusercontent.com/1413571/157056388-cd452b36-fff2-4432-be7f-555079f60eab.png
— Reply to this email directly, view it on GitHubhttps://github.com/sokrypton/ColabFold/issues/173#issuecomment-1060768589, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AYDMBSQCUHQGW24S6FZZUDTU6YJQJANCNFSM5QC5FCMA. Triage notifications on the go with GitHub Mobile for iOShttps://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Androidhttps://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub. You are receiving this because you authored the thread.Message ID: @.***>