Rappsilber-Laboratory / AlphaLink2

AlphaLink2: Integrating crosslinking MS data into Uni-Fold-Multimer
Creative Commons Attribution 4.0 International
42 stars 11 forks source link

Colab Notebook fails at generate MSA step - T4 GPU runtime #17

Open RCowan1983 opened 6 months ago

RCowan1983 commented 6 months ago

I've tried running a test case for some cross link data we have for a fusion protein, and the colab notebook fails at the Generate MSA cell with the following error text:

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
[<ipython-input-5-a035946cd06a>](https://d2zmhxae1bj-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab_20231228-060138_RC00_594230591#) in <cell line: 14>()
     12 import gzip
     13 from unifold.msa import parsers
---> 14 from unifold.msa import pipeline
     15 from unifold.data.utils import compress_features
     16 from unifold.data.protein import PDB_CHAIN_IDS

2 frames
[/usr/local/lib/python3.10/dist-packages/unifold/msa/mmcif.py](https://d2zmhxae1bj-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab_20231228-060138_RC00_594230591#) in <module>
     23 from Bio import PDB
     24 from Bio.PDB.MMCIFParser import MMCIFParser
---> 25 from Bio.Data import SCOPData
     26 
     27 # Type aliases:

ImportError: cannot import name 'SCOPData' from 'Bio.Data' (/usr/local/lib/python3.10/dist-packages/Bio/Data/__init__.py)

I'm also getting warnings about the GPU runtime not making use of the GPU, so there may also be an issue with the loading of unifold?

lhatsk commented 6 months ago

Thanks for reporting this! The latest Biopython update moved a module. I updated the notebook.

The GPU runtime warning is fine. Only the prediction step utilizes the GPU.