OpenFold を使用してタンパク質の立体構造予測をやってみた

$ nvidia-smi
Tue Dec 24 05:18:02 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.127.05             Driver Version: 550.127.05     CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| 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  NVIDIA L4                      On  |   00000000:31:00.0 Off |                    0 |
| N/A   23C    P8             11W /   72W |       1MiB /  23034MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

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

$ df -h
Filesystem                      Size  Used Avail Use% Mounted onk
/dev/nvme1n1                    3.3T  2.8T  347G  90% /database

cd /mnt/ebs
git clone https://github.com/aws-samples/aws-do-openfold-inference.git
cd /mnt/ebs/aws-do-openfold-inference/download-openfold-data
sudo apt install aria2 -y

nohup bash scripts/download_alphafold_params_s3.sh /mnt/ebs/openfold/data/ > 1.log &
nohup bash scripts/download_mgnify_s3.sh /mnt/ebs/openfold/data/ > 2.log &
nohup bash scripts/download_pdb_mmcif_s3.sh /mnt/ebs/openfold/data/ > 3.log &
nohup bash scripts/download_small_bfd_s3.sh /mnt/ebs/openfold/data/ > 4.log &
nohup bash scripts/download_uniprot_s3.sh /mnt/ebs/openfold/data/ > 5.log &
nohup bash scripts/download_bfd_s3.sh /mnt/ebs/openfold/data/ > 6.log &
nohup bash scripts/download_pdb70_s3.sh /mnt/ebs/openfold/data/ > 7.log &
nohup bash scripts/download_pdb_seqres_s3.sh /mnt/ebs/openfold/data/ > 8.log &
nohup bash scripts/download_uniclust30_s3.sh /mnt/ebs/openfold/data/ > 9.log &
nohup bash scripts/download_uniref90_s3.sh /mnt/ebs/openfold/data/ > 10.log &

DOWNLOAD_DIR="/database/openfold/data"
mkdir -p "${DOWNLOAD_DIR}"
aws s3 cp --no-sign-request --region us-east-1 s3://openfold/openfold_params/ "${DOWNLOAD_DIR}" --recursive

# Add Docker's official GPG key
sudo apt-get update
sudo apt-get install ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

# Add the repository to Apt sources
echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
sudo apt-get update

sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin -y

cd ~
git clone -b pl_upgrades https://github.com/aqlaboratory/openfold.git

cd openfold
docker build -t openfold .

name: openfold-env
channels:
  - conda-forge
  - bioconda
  - pytorch
  - nvidia
dependencies:
  - cuda
  - gcc=12.4
-  - python=3.10
+  - python=3.9.x
+  - numpy=1.22.4
  - libgcc=7.2
  - setuptools=59.5.0
  - pip
  - openmm=7.7
  - pdbfixer
  - pytorch-lightning
  - biopython
  - numpy<2.0.0
  - pandas
  - PyYAML==5.4.1
  - requests
  - scipy
  - tqdm==4.62.2
  - typing-extensions
  - wandb
  - modelcif==0.7
  - awscli
  - ml-collections
  - mkl=2022.1
  - aria2
  - git
  - bioconda::hmmer
  - bioconda::hhsuite
  - bioconda::kalign2
  - pytorch::pytorch=2.1
  - pytorch::pytorch-cuda=12.1
  - pip:
      - deepspeed==0.12.4
      - dm-tree==0.1.6
      - git+https://github.com/NVIDIA/dllogger.git
      - flash-attn

#!/bin/sh
cd /home/ubuntu/openfold/examples/monomer
docker run \
       --gpus all \
       -v $PWD/:/data \
       -v /database/openfold/data/:/database \
       -ti openfold:latest \
       python3 /opt/openfold/run_pretrained_openfold.py \
       /data/fasta_dir \
       /database/pdb_mmcif/mmcif_files/ \
       --uniref90_database_path /database/uniref90/uniref90.fasta \
       --mgnify_database_path /database/mgnify/mgy_clusters_2022_05.fa \
       --pdb70_database_path /database/pdb70/pdb70 \
       --uniclust30_database_path /database/uniclust30/uniclust30_2018_08/uniclust30_2018_08 \
       --bfd_database_path /database/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt \
       --jackhmmer_binary_path /opt/conda/bin/jackhmmer \
       --hhblits_binary_path /opt/conda/bin/hhblits \
       --hhsearch_binary_path /opt/conda/bin/hhsearch \
       --kalign_binary_path /opt/conda/bin/kalign \
       --openfold_checkpoint_path /database/openfold_params/finetuning_ptm_2.pt \
       --config_preset "model_1_ptm" \
       --model_device "cuda:0" \
       --output_dir /data/results

==========
== CUDA ==
==========

CUDA Version 12.1.1

Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.

[2024-12-27 03:17:59,782] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
INFO:/opt/openfold/openfold/utils/script_utils.py:Loaded OpenFold parameters at /database/openfold_params/finetuning_ptm_2.pt...
INFO:/opt/openfold/run_pretrained_openfold.py:Generating alignments for 6KWC_1...

$ tree .
.
├── alignments
│   └── 6KWC_1
│       ├── bfd_uniclust_hits.a3m
│       ├── hhsearch_output.hhr
│       ├── mgnify_hits.sto
│       └── uniref90_hits.sto
├── predictions
│   ├── 6KWC_1_model_1_ptm_relaxed.pdb
│   ├── 6KWC_1_model_1_ptm_unrelaxed.pdb
│   └── timings.json
└── timings.json