AlphaFold2/docker/run_docker.py阅读理解

我想阅读源码看一下alphafold2的实现细节，但是看完这个py文件里面并没有实现细节。只有对传入参数的设置，但读完代码也做一下记录。

---

1. 检查特定的参数：数据库文件夹、fasta文件、模板

运行main函数

if __name__ == '__main__':
  flags.mark_flags_as_required([
      'data_dir',
      'fasta_paths',
      'max_template_date',
  ])
  app.run(main)

2. main()函数

设置数据库路径（8个）、模板路径、输出文件路径

if len(argv) > 1:
    raise app.UsageError('Too many command-line arguments.')

  # You can individually override the following paths if you have placed the
  # data in locations other than the FLAGS.data_dir.

  # Path to the Uniref90 database for use by JackHMMER.
  uniref90_database_path = os.path.join(
      FLAGS.data_dir, 'uniref90', 'uniref90.fasta')

  # Path to the Uniprot database for use by JackHMMER.
  uniprot_database_path = os.path.join(
      FLAGS.data_dir, 'uniprot', 'uniprot.fasta')

  # Path to the MGnify database for use by JackHMMER.
  mgnify_database_path = os.path.join(
      FLAGS.data_dir, 'mgnify', 'mgy_clusters_2018_12.fa')

  # Path to the BFD database for use by HHblits.
  bfd_database_path = os.path.join(
      FLAGS.data_dir, 'bfd',
      'bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt')

  # Path to the Small BFD database for use by JackHMMER.
  small_bfd_database_path = os.path.join(
      FLAGS.data_dir, 'small_bfd', 'bfd-first_non_consensus_sequences.fasta')

  # Path to the Uniclust30 database for use by HHblits.
  uniclust30_database_path = os.path.join(
      FLAGS.data_dir, 'uniclust30', 'uniclust30_2018_08', 'uniclust30_2018_08')

  # Path to the PDB70 database for use by HHsearch.
  pdb70_database_path = os.path.join(FLAGS.data_dir, 'pdb70', 'pdb70')

  # Path to the PDB seqres database for use by hmmsearch.
  pdb_seqres_database_path = os.path.join(
      FLAGS.data_dir, 'pdb_seqres', 'pdb_seqres.txt')

  # Path to a directory with template mmCIF structures, each named <pdb_id>.cif.
  template_mmcif_dir = os.path.join(FLAGS.data_dir, 'pdb_mmcif', 'mmcif_files')

  # Path to a file mapping obsolete PDB IDs to their replacements.
  obsolete_pdbs_path = os.path.join(FLAGS.data_dir, 'pdb_mmcif', 'obsolete.dat')

  alphafold_path = pathlib.Path(__file__).parent.parent
  data_dir_path = pathlib.Path(FLAGS.data_dir)
  if alphafold_path == data_dir_path or alphafold_path in data_dir_path.parents:
    raise app.UsageError(
        f'The download directory {FLAGS.data_dir} should not be a subdirectory '
        f'in the AlphaFold repository directory. If it is, the Docker build is '
        f'slow since the large databases are copied during the image creation.')

为模型使用的每个文件和目录创建装入点，并传回命令行修改参数为挂载目录

for i, fasta_path in enumerate(FLAGS.fasta_paths):
    mount, target_path = _create_mount(f'fasta_path_{i}', fasta_path)
    mounts.append(mount)
    target_fasta_paths.append(target_path)
  command_args.append(f'--fasta_paths={",".join(target_fasta_paths)}')

把fasta文件的路径映射到/mnt/fasta文件路径下，返回挂载器和挂载目录

def _create_mount(mount_name: str, path: str) -> Tuple[types.Mount, str]:
  """Create a mount point for each file and directory used by the model."""
  path = pathlib.Path(path).absolute()
  target_path = pathlib.Path(_ROOT_MOUNT_DIRECTORY, mount_name)

  if path.is_dir():
    source_path = path
    mounted_path = target_path
  else:
    source_path = path.parent
    mounted_path = pathlib.Path(target_path, path.name)
  if not source_path.exists():
    raise ValueError(f'Failed to find source directory "{source_path}" to '
                     'mount in Docker container.')
  logging.info('Mounting %s -> %s', source_path, target_path)
  mount = types.Mount(target=str(target_path), source=str(source_path),
                      type='bind', read_only=True)
  return mount, str(mounted_path)

将path相对路径转换为绝对路径

path = pathlib.Path(path).absolute()

目标路径为：/mnt/fasta_path_{i}   i=1,2,3,...

target_path = pathlib.Path(_ROOT_MOUNT_DIRECTORY, mount_name)

根据传入参数的不同（有无多聚体），选择不同的数据库

if FLAGS.model_preset == 'multimer':
    database_paths.append(('uniprot_database_path', uniprot_database_path))
    database_paths.append(('pdb_seqres_database_path',
                           pdb_seqres_database_path))
  else:
    database_paths.append(('pdb70_database_path', pdb70_database_path))

挂载数据库路径

for name, path in database_paths:
    if path:
      mount, target_path = _create_mount(name, path)
      mounts.append(mount)
      command_args.append(f'--{name}={target_path}')

挂载输出路径/mnt/output/

output_target_path = os.path.join(_ROOT_MOUNT_DIRECTORY, 'output')
mounts.append(types.Mount(output_target_path, FLAGS.output_dir, type='bind'))

初始化docker客户端

client = docker.from_env()

运行docker容器，返回一个Container对象

container = client.containers.run(
      image=FLAGS.docker_image_name,
      command=command_args,
      device_requests=device_requests,
      remove=True,
      detach=True,
      mounts=mounts,
      user=FLAGS.docker_user,
      environment={
          'NVIDIA_VISIBLE_DEVICES': FLAGS.gpu_devices,
          # The following flags allow us to make predictions on proteins that
          # would typically be too long to fit into GPU memory.
          'TF_FORCE_UNIFIED_MEMORY': '1',
          'XLA_PYTHON_CLIENT_MEM_FRACTION': '4.0',
      })

environment：以下标志允许我们对通常太长而无法放入GPU内存的蛋白质进行预测。

run()函数的解析如下图：参考 http://t.csdn.cn/Qwqel

有一些没有写出来，应该就是运行时设置的一些参数

更多关于Python第三方库操作Docker的内容可以参考官方手册：https://docker-py.readthedocs.io/en/stable/index.html

 查看官方文档后把剩下的参数列出：

device_requests	list列表	将主机的所有资源公开给容器
mounts	list列表	容器转载列表（规范后的）
environment	dict or list 字典或列表	要在容器内设置的环境变量