Git Product home page Git Product logo

alphafold_non_docker's Introduction

Hi! I'm Alex

  • ๐Ÿ”ญ Iโ€™m currently working on applications of geometric deep learning and generative modeling for structural biology and computational biology more generally.
  • ๐ŸŒฑ Iโ€™m currently learning about generative flow matching with equivariant neural networks.
  • ๐Ÿ’ฌ Ask me about machine learning, artificial intelligence, computational biology, music, cardio and strength training, etc.
  • ๐Ÿ“ซ How to reach me: LinkedIn, Twitter, Gmail, etc.
  • โšก Fun fact: I can understand (i.e., read) more Chinese and Japanese than I can speak.

๐ŸŒ Website ยท ๐Ÿ“ฐ Google Scholar ยท ๐Ÿ‘” LinkedIn ยท ๐Ÿฆ Twitter

Github profile Trophy

Top Langs lambdalisue's github stats

alphafold_non_docker's People

Contributors

amorehead avatar andycowie avatar augustin-zidek avatar mfigurnov avatar rich12321 avatar saran-t avatar tfgg avatar tomwardio avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

alphafold_non_docker's Issues

problems with installation and "GPU not found"

First, I run into a few problems with the installation that I was able to resolve:

  1. The run_alphafold.py requires --use_gpu_relax flag
    ERROR: flag --use_gpu_relax=None: Flag --use_gpu_relax must have a value other than None.

fix: adding the parameter to python commands in the sh script:
(this issue was also reported in this blog: https://programs.team/alphafold-installation-non-docker-image.html )

if [[ "$db_preset" == "reduced_dbs" && "$model_preset" == "monomer" ]]; then
  $(python $alphafold_script --use_gpu_relax --hhblits_binary_path=$hhblits_binary_path --hhsearch_binary_path=$hhsearch_binary_path --jackhmmer_binary_path=$jackhmmer_binary_path --kalign_binary_path=$kalign_binary_path --small_bfd_database_path=$small_bfd_database_path --mgnify_database_path=$mgnify_database_path --template_mmcif_dir=$template_mmcif_dir --obsolete_pdbs_path=$obsolete_pdbs_path --pdb70_database_path=$pdb70_database_path --uniref90_database_path=$uniref90_database_path --data_dir=$data_dir --output_dir=$output_dir --fasta_paths=$fasta_path --max_template_date=$max_template_date --model_preset=$model_preset --db_preset=$db_preset --benchmark=$benchmark --use_precomputed_msas=$use_precomputed_msas --remove_msas_after_use=$remove_msas_after_use --logtostderr)
elif [[ "$db_preset" == "reduced_dbs" ]]; then
  $(python $alphafold_script --use_gpu_relax --hhblits_binary_path=$hhblits_binary_path --hhsearch_binary_path=$hhsearch_binary_path --jackhmmer_binary_path=$jackhmmer_binary_path --kalign_binary_path=$kalign_binary_path --small_bfd_database_path=$small_bfd_database_path --mgnify_database_path=$mgnify_database_path --template_mmcif_dir=$template_mmcif_dir --obsolete_pdbs_path=$obsolete_pdbs_path --pdb_seqres_database_path=$pdb_seqres_database_path --uniprot_database_path=$uniprot_database_path --uniref90_database_path=$uniref90_database_path --data_dir=$data_dir --output_dir=$output_dir --fasta_paths=$fasta_path --max_template_date=$max_template_date --model_preset=$model_preset --db_preset=$db_preset --benchmark=$benchmark --use_precomputed_msas=$use_precomputed_msas --remove_msas_after_use=$remove_msas_after_use --logtostderr --is_prokaryote_list=$is_prokaryote)
elif [[ "$db_preset" == "full_dbs" && "$model_preset" == "monomer" ]]; then
  $(python $alphafold_script --use_gpu_relax --hhblits_binary_path=$hhblits_binary_path --hhsearch_binary_path=$hhsearch_binary_path --jackhmmer_binary_path=$jackhmmer_binary_path --kalign_binary_path=$kalign_binary_path --bfd_database_path=$bfd_database_path --mgnify_database_path=$mgnify_database_path --template_mmcif_dir=$template_mmcif_dir --obsolete_pdbs_path=$obsolete_pdbs_path --pdb70_database_path=$pdb70_database_path --uniclust30_database_path=$uniclust30_database_path --uniref90_database_path=$uniref90_database_path --data_dir=$data_dir --output_dir=$output_dir --fasta_paths=$fasta_path --max_template_date=$max_template_date --model_preset=$model_preset --db_preset=$db_preset --benchmark=$benchmark --use_precomputed_msas=$use_precomputed_msas --remove_msas_after_use=$remove_msas_after_use --logtostderr)
else
  $(python $alphafold_script --use_gpu_relax --hhblits_binary_path=$hhblits_binary_path --hhsearch_binary_path=$hhsearch_binary_path --jackhmmer_binary_path=$jackhmmer_binary_path --kalign_binary_path=$kalign_binary_path --bfd_database_path=$bfd_database_path --mgnify_database_path=$mgnify_database_path --template_mmcif_dir=$template_mmcif_dir --obsolete_pdbs_path=$obsolete_pdbs_path --pdb_seqres_database_path=$pdb_seqres_database_path --uniclust30_database_path=$uniclust30_database_path --uniprot_database_path=$uniprot_database_path --uniref90_database_path=$uniref90_database_path --data_dir=$data_dir --output_dir=$output_dir --fasta_paths=$fasta_path --max_template_date=$max_template_date --model_preset=$model_preset --db_preset=$db_preset --benchmark=$benchmark --use_precomputed_msas=$use_precomputed_msas --remove_msas_after_use=$remove_msas_after_use --logtostderr --is_prokaryote_list=$is_prokaryote)
fi
  1. ERROR: mgy_clusters.fa not found
    fix: rename mgnify database file to mgy_clusters.fa (deleted the date at the end)

3) ERROR: unable to initialize backend 'gpu': not_found
This one I was not able to resolve.

alphafold reverts to CPU but this is much slower.

The nvidia-smi command gives a normal output and other software that uses GPU is able to find it:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.73.01    Driver Version: 460.73.01    CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Quadro RTX 4000     On   | 00000000:27:00.0 Off |                  N/A |
| 30%   49C    P8    10W / 125W |      3MiB /  7982MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.