MDAnalysisData 0.9.1__py3-none-any.whl

MDAnalysisData/CG_fiber.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+
+"""Coarse-grained molecular dynamics of an amphiphilic fiber.
+
+https://figshare.com/articles/126chains_dcd/7259915
+"""
+
+from os.path import dirname, exists, join
+from os import makedirs, remove
+
+import logging
+
+from .base import get_data_home
+from .base import _fetch_remote, _read_description
+from .base import RemoteFileMetadata
+from .base import Bunch
+
+NAME = "CG_fiber"
+DESCRIPTION = "CG_fiber.rst"
+# The original data can be found at the figshare URL.
+# The SHA256 checksum of the zip file changes with every download so we
+# cannot check its checksum. Instead we download individual files.
+# separately. The keys of this dict are also going to be the keys in the
+# Bunch that is returned.
+ARCHIVE = {
+    'topology': RemoteFileMetadata(
+        filename='126chains.psf',
+        url='https://ndownloader.figshare.com/files/13374146',
+        checksum='3ddb654b68549ac2ad5107a4282899f41fad233d09ea572446031711af4e57da',
+    ),
+    'trajectory':  RemoteFileMetadata(
+        filename='126chains.dcd',
+        url='https://ndownloader.figshare.com/files/13375838',
+        checksum='e0b47d422f31ec209ea810edcf6cf3830da04bb2e1540f520477c27f4433d849',
+    ),
+}
+
+logger = logging.getLogger(__name__)
+
+
+def fetch_CG_fiber(data_home=None, download_if_missing=True):
+    """Load the CG fiber self-assembly trajectory
+
+    Parameters
+    ----------
+    data_home : optional, default: None
+        Specify another download and cache folder for the datasets. By default
+        all MDAnalysisData data is stored in '~/MDAnalysis_data' subfolders.
+        This dataset is stored in ``<data_home>/CG_fiber``.
+    download_if_missing : optional, default=True
+        If ``False``, raise a :exc:`IOError` if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    Returns
+    -------
+    dataset : dict-like object with the following attributes:
+    dataset.topology : filename
+        Filename of the topology file
+    dataset.trajectory : filename
+        Filename of the trajectory file
+    dataset.DESCR : string
+        Description of the trajectory.
+
+
+    See :ref:`CG_fiber-dataset` for description.
+    """
+    name = NAME
+    data_location = join(get_data_home(data_home=data_home),
+                         name)
+    if not exists(data_location):
+        makedirs(data_location)
+
+    records = Bunch()
+    for file_type, meta in ARCHIVE.items():
+        local_path = join(data_location, meta.filename)
+        records[file_type] = local_path
+
+        if not exists(local_path):
+            if not download_if_missing:
+                raise IOError("Data {0}={1} not found and `download_if_missing` is "
+                              "False".format(file_type, local_path))
+            logger.info("Downloading {0}: {1} -> {2}...".format(
+                file_type, meta.url, local_path))
+            archive_path = _fetch_remote(meta, dirname=data_location)
+
+    records.DESCR = _read_description(DESCRIPTION)
+
+    return records

MDAnalysisData/PEG_1chain.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+
+"""Molecular dynamics trajectory of a single PEG chain in TIP3P water.
+
+https://doi.org/10.6084/m9.figshare.7325774
+"""
+
+from os.path import dirname, exists, join
+from os import makedirs, remove
+
+import logging
+
+from .base import get_data_home
+from .base import _fetch_remote, _read_description
+from .base import RemoteFileMetadata
+from .base import Bunch
+
+NAME = "PEG_1chain"
+DESCRIPTION = "PEG_1chain.rst"
+# The original data can be found at the figshare URL.
+# The SHA256 checksum of the zip file changes with every download so we
+# cannot check its checksum. Instead we download individual files.
+# separately. The keys of this dict are also going to be the keys in the
+# Bunch that is returned.
+ARCHIVE = {
+    'topology': RemoteFileMetadata(
+        filename='PEG.prmtop',
+        url='https://ndownloader.figshare.com/files/13532462',
+        checksum='2d7955b9a8cb6e008171e0c5a1c31e3e458246ea3ee7302281eafefafa7cede9',
+    ),
+    'trajectory':  RemoteFileMetadata(
+        filename='PEG_03_prod.nc',
+        url='https://ndownloader.figshare.com/files/13532465',
+        checksum='b978714ec2f93d1cbe99564cb257959f0cb38872359aa745c8eba720a7d85225',
+    ),
+}
+
+logger = logging.getLogger(__name__)
+
+
+def fetch_PEG_1chain(data_home=None, download_if_missing=True):
+    """Load the PEG polymer trajectory
+
+    Parameters
+    ----------
+    data_home : optional, default: None
+        Specify another download and cache folder for the datasets. By default
+        all MDAnalysisData data is stored in '~/MDAnalysis_data' subfolders.
+        This dataset is stored in ``<data_home>/CG_fiber``.
+    download_if_missing : optional, default=True
+        If ``False``, raise a :exc:`IOError` if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    Returns
+    -------
+    dataset : dict-like object with the following attributes:
+    dataset.topology : filename
+        Filename of the topology file
+    dataset.trajectory : filename
+        Filename of the trajectory file
+    dataset.DESCR : string
+        Description of the trajectory.
+
+
+    See :ref:`PEG_1chain-dataset` for description.
+    """
+    name = NAME
+    data_location = join(get_data_home(data_home=data_home),
+                         name)
+    if not exists(data_location):
+        makedirs(data_location)
+
+    records = Bunch()
+    for file_type, meta in ARCHIVE.items():
+        local_path = join(data_location, meta.filename)
+        records[file_type] = local_path
+
+        if not exists(local_path):
+            if not download_if_missing:
+                raise IOError("Data {0}={1} not found and `download_if_missing` is "
+                              "False".format(file_type, local_path))
+            logger.info("Downloading {0}: {1} -> {2}...".format(
+                file_type, meta.url, local_path))
+            archive_path = _fetch_remote(meta, dirname=data_location)
+
+    records.DESCR = _read_description(DESCRIPTION)
+
+    return records

MDAnalysisData/__init__.py

@@ -0,0 +1,22 @@
+# MDAnalysisData package
+#
+# Modelled after sklearn.datasets
+# https://github.com/scikit-learn/scikit-learn/tree/0.20.X/sklearn/datasets
+
+__all__ = ['datasets']
+
+from . import datasets
+
+
+from importlib.metadata import version
+__version__ = version("MDAnalysisData")
+
+
+try:
+    from .authors import __authors__
+except ImportError:
+    import warnings
+    warnings.warn('Could not find authors.py, __authors__ will be the '
+                  'generic MDAnalysis team.')
+    __authors__ = ["The MDAnalysis Development Team"]
+    del warnings

MDAnalysisData/adk_equilibrium.py

@@ -0,0 +1,88 @@
+# -*- coding: utf-8 -*-
+
+"""AdK equilibrium trajectory without water.
+
+https://figshare.com/articles/Molecular_dynamics_trajectory_for_benchmarking_MDAnalysis/5108170/1
+"""
+
+from os.path import dirname, exists, join
+from os import makedirs, remove
+
+import logging
+
+from .base import get_data_home
+from .base import _fetch_remote, _read_description
+from .base import RemoteFileMetadata
+from .base import Bunch
+
+NAME = "adk_equilibrium"
+DESCRIPTION = "adk_equilibrium.rst"
+# The original data can be found at the figshare URL.
+# The SHA256 checksum of the zip file changes with every download so we
+# cannot check its checksum. Instead we download individual files.
+# separately. The keys of this dict are also going to be the keys in the
+# Bunch that is returned.
+ARCHIVE = {
+    'topology': RemoteFileMetadata(
+        filename='adk4AKE.psf',
+        url='https://ndownloader.figshare.com/files/8672230',
+        checksum='1aa947d58fb41b6805dc1e7be4dbe65c6a8f4690f0bd7fc2ae03e7bd437085f4',
+    ),
+    'trajectory':  RemoteFileMetadata(
+        filename='1ake_007-nowater-core-dt240ps.dcd',
+        url='https://ndownloader.figshare.com/files/8672074',
+        checksum='598fcbcfcc425f6eafbe9997238320fcacc6a4613ecce061e1521732bab734bf',
+    ),
+}
+
+logger = logging.getLogger(__name__)
+
+
+def fetch_adk_equilibrium(data_home=None, download_if_missing=True):
+    """Load the AdK 1us equilibrium trajectory (without water)
+
+    Parameters
+    ----------
+    data_home : optional, default: None
+        Specify another download and cache folder for the datasets. By default
+        all MDAnalysisData data is stored in '~/MDAnalysis_data' subfolders.
+        This dataset is stored in ``<data_home>/adk_equilibrium``.
+    download_if_missing : optional, default=True
+        If ``False``, raise a :exc:`IOError` if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    Returns
+    -------
+    dataset : dict-like object with the following attributes:
+    dataset.topology : filename
+        Filename of the topology file
+    dataset.trajectory : filename
+        Filename of the trajectory file
+    dataset.DESCR : string
+        Description of the trajectory.
+
+
+    See :ref:`adk-equilibrium-dataset` for description.
+    """
+    name = NAME
+    data_location = join(get_data_home(data_home=data_home),
+                         name)
+    if not exists(data_location):
+        makedirs(data_location)
+
+    records = Bunch()
+    for file_type, meta in ARCHIVE.items():
+        local_path = join(data_location, meta.filename)
+        records[file_type] = local_path
+
+        if not exists(local_path):
+            if not download_if_missing:
+                raise IOError("Data {0}={1} not found and `download_if_missing` is "
+                              "False".format(file_type, local_path))
+            logger.info("Downloading {0}: {1} -> {2}...".format(
+                file_type, meta.url, local_path))
+            archive_path = _fetch_remote(meta, dirname=data_location)
+
+    records.DESCR = _read_description(DESCRIPTION)
+
+    return records

MDAnalysisData/adk_transitions.py

@@ -0,0 +1,196 @@
+# -*- coding: utf-8 -*-
+
+"""Ensembles of AdK transitions.
+
+https://figshare.com/articles/Simulated_trajectory_ensembles_for_the_closed-to-open_transition_of_adenylate_kinase_from_DIMS_MD_and_FRODA/7165306
+"""
+
+
+from os.path import dirname, exists, join
+from os import makedirs, remove
+import tarfile
+import glob
+
+import logging
+
+from .base import get_data_home
+from .base import _fetch_remote, _read_description
+from .base import RemoteFileMetadata
+from .base import Bunch
+
+
+METADATA = {
+    'DIMS': {
+        'NAME': "adk_transitions_DIMS",
+        'DESCRIPTION': "adk_transitions_DIMS.rst",
+        'ARCHIVE': {
+            'tarfile': RemoteFileMetadata(
+                filename='DIMS.tar.gz',
+                url='https://ndownloader.figshare.com/files/13182490',
+                checksum='81dfd247da7084bc7f47889c098069978b61f8f8b4f7706841266d284bfd3b55',
+            ),
+        },
+        'CONTENTS': {
+            'topology': "DIMS/topologies/adk4ake.psf",
+            'trajectories': "DIMS/trajectories/dims*_fit-core.dcd",
+            'N_trajectories': 200,
+        },
+    },
+    'FRODA': {
+        'NAME': "adk_transitions_FRODA",
+        'DESCRIPTION': "adk_transitions_FRODA.rst",
+        'ARCHIVE': {
+            'tarfile': RemoteFileMetadata(
+                filename='FRODA.tar.gz',
+                url='https://ndownloader.figshare.com/files/13182493',
+                checksum='fc2c90b9819fd07720e7effada033d4045663919ba7d2c8bd84f548dfbeee73c',
+            ),
+        },
+        'CONTENTS': {
+            'topology': "FRODA/topologies/1ake.pdb",
+            'trajectories': "FRODA/trajectories/pathway*_fit-core.dcd",
+            'N_trajectories': 200,
+        },
+    },
+}
+
+logger = logging.getLogger(__name__)
+
+def fetch_adk_transitions_DIMS(data_home=None, download_if_missing=True):
+    """Load the AdK DIMS transititions dataset
+
+    Parameters
+    ----------
+    data_home : optional, default: None
+        Specify another download and cache folder for the datasets. By default
+        all MDAnalysisData data is stored in '~/MDAnalysis_data' subfolders.
+        This dataset is stored in ``<data_home>/adk_transitions_DIMS``.
+    download_if_missing : optional, default=True
+        If ``False``, raise a :exc:`IOError` if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    Returns
+    -------
+    dataset : dict-like object with the following attributes:
+    dataset.topology : filename
+        Filename of the topology file
+    dataset.trajectories : list
+        list with filenames of the trajectory ensemble
+    dataset.N_trajectories : int
+        number of trajectories in the ensemble
+    dataset.DESCR : string
+        Description of the ensemble
+
+
+    See :ref:`adk-transitions-DIMS-dataset` for description.
+    """
+    return _fetch_adk_transitions(METADATA['DIMS'],
+                                  data_home=data_home,
+                                  download_if_missing=download_if_missing)
+
+def fetch_adk_transitions_FRODA(data_home=None, download_if_missing=True):
+    """Load the AdK FRODA transititions dataset
+
+    Parameters
+    ----------
+    data_home : optional, default: None
+        Specify another download and cache folder for the datasets. By default
+        all MDAnalysisData data is stored in '~/MDAnalysis_data' subfolders.
+        This dataset is stored in ``<data_home>/adk_transitions_FRODA``.
+    download_if_missing : optional, default=True
+        If ``False``, raise a :exc:`IOError` if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    Returns
+    -------
+    dataset : dict-like object with the following attributes:
+    dataset.topology : filename
+        Filename of the topology file
+    dataset.trajectories : list
+        list with filenames of the trajectory ensemble
+    dataset.N_trajectories : int
+        number of trajectories in the ensemble
+    dataset.DESCR : string
+        Description of the ensemble
+
+
+    See :ref:`adk-transitions-FRODA-dataset` for description.
+    """
+    return _fetch_adk_transitions(METADATA['FRODA'],
+                                  data_home=data_home,
+                                  download_if_missing=download_if_missing)
+
+
+def _fetch_adk_transitions(metadata, data_home=None, download_if_missing=True):
+    """Generic function to load the AdK transititions datasets
+
+    Parameters
+    ----------
+    metdata : dict
+        dictionary with `NAME`, `DESCRIPTION` and `ARCHIVE` that contains
+        a tar.gz file with directories topologies and trajectories
+    data_home : optional, default: None
+        Specify another download and cache folder for the datasets. By default
+        all MDAnalysisData data is stored in '~/MDAnalysis_data' subfolders.
+    download_if_missing : optional, default=True
+        If ``False``, raise a :exc:`IOError` if the data is not locally available
+        instead of trying to download the data from the source site.
+
+    Returns
+    -------
+    dataset : dict-like object with the following attributes:
+    dataset.topology : filename
+        Filename of the topology file
+    dataset.trajectories : list
+        list with filenames of the trajectory ensemble
+    dataset.DESCR : string
+        Description of the ensemble
+
+    Note
+    ----
+    Assumptions that are built in:
+    - download a single tar.gz file
+    - trajectories are given with a glob pattern
+
+    """
+    name = metadata['NAME']
+    data_location = join(get_data_home(data_home=data_home),
+                         name)
+    if not exists(data_location):
+        makedirs(data_location)
+
+    records = Bunch()
+
+    meta = metadata['ARCHIVE']['tarfile']
+    local_path = join(data_location, meta.filename)
+
+    if not exists(local_path):
+        if not download_if_missing:
+            raise IOError("Data {0}={1} not found and `download_if_missing` is "
+                          "False".format(file_type, local_path))
+        logger.info("Downloading {0}: {1} -> {2}...".format(
+            "tarfile", meta.url, local_path))
+        archive_path = _fetch_remote(meta, dirname=data_location)
+
+        logger.info("Unpacking {}...".format(archive_path))
+        with tarfile.open(archive_path, 'r') as tar:
+            tar.extractall(path=data_location)
+
+    records.topology = join(data_location, metadata['CONTENTS']['topology'])
+    if not exists(records.topology):
+        # should not happen...
+        raise RuntimeError("topology file {} is missing".format(records.topology))
+
+    trajectory_pattern = join(data_location, metadata['CONTENTS']['trajectories'])
+    records.trajectories = glob.glob(trajectory_pattern)
+    records.N_trajectories = metadata['CONTENTS']['N_trajectories']
+    if len(records.trajectories) != records.N_trajectories:
+        # should not happen...
+        raise RuntimeError("trajectory files in {0} are incomplete: only {1} "
+                           "but should be {2}.".format(
+                               trajectory_pattern, len(records.trajectories),
+                               records.N_trajectories))
+
+    records.DESCR = _read_description(metadata['DESCRIPTION'])
+
+    return records

MDAnalysisData/authors.py

@@ -0,0 +1,12 @@
+#-*- coding:utf-8 -*-
+# This file is generated from the AUTHORS file during the installation process.
+# Do not edit it as your changes will be overwritten.
+
+__authors__ = [
+    u"Irfan Alibay",
+    u"Oliver Beckstein",
+    u"Shujie Fan",
+    u"Richard J. Gowers",
+    u"Micaela Matta",
+    u"Lily Wang"
+]