from typing import Callable
import bioversions
import pystow
__all__ = [
"RAW_DIRECTORY",
"DATABASE_DIRECTORY",
"SPECIES_REMAPPING",
"get_sqlalchemy_uri",
"version_getter",
]
logger = logging.getLogger(__name__)
PYOBO_MODULE = pystow.module("pyobo")
RAW_MODULE = PYOBO_MODULE.submodule("raw")
RAW_DIRECTORY = RAW_MODULE.base
DATABASE_MODULE = PYOBO_MODULE.submodule("database")
DATABASE_DIRECTORY = DATABASE_MODULE.base
SPECIES_REMAPPING = {
"Canis familiaris": "Canis lupus familiaris",
}
GLOBAL_SKIP = {
"rnao",
"mo", # deprecated
"resid", # deprecated
"adw", # deprecated
}
from pathlib import Path
import pystow
__all__ = [
'PYKEEN_HOME',
'PYKEEN_DATASETS',
'PYKEEN_BENCHMARKS',
'PYKEEN_EXPERIMENTS',
'PYKEEN_CHECKPOINTS',
]
#: A manager around the PyKEEN data folder. It defaults to ``~/.data/pykeen``.
# This can be overridden with the envvar ``PYKEEN_HOME``.
#: For more information, see https://github.com/cthoyt/pystow
PYKEEN_MODULE: pystow.Module = pystow.module('pykeen')
#: A path representing the PyKEEN data folder
PYKEEN_HOME: Path = PYKEEN_MODULE.base
#: A subdirectory of the PyKEEN data folder for datasets, defaults to ``~/.data/pykeen/datasets``
PYKEEN_DATASETS: Path = PYKEEN_MODULE.get('datasets')
#: A subdirectory of the PyKEEN data folder for benchmarks, defaults to ``~/.data/pykeen/benchmarks``
PYKEEN_BENCHMARKS: Path = PYKEEN_MODULE.get('benchmarks')
#: A subdirectory of the PyKEEN data folder for experiments, defaults to ``~/.data/pykeen/experiments``
PYKEEN_EXPERIMENTS: Path = PYKEEN_MODULE.get('experiments')
#: A subdirectory of the PyKEEN data folder for checkpoints, defaults to ``~/.data/pykeen/checkpoints``
PYKEEN_CHECKPOINTS: Path = PYKEEN_MODULE.get('checkpoints')
PYKEEN_DEFAULT_CHECKPOINT = "PyKEEN_just_saved_my_day.pt"
DEFAULT_DROPOUT_HPO_RANGE = dict(type=float, low=0.0, high=0.5, q=0.1)
#: We define the embedding dimensions as a multiple of 16 because it is computational beneficial (on a GPU)
_USER_CONFIG_DIRECTORY = os.path.abspath(
os.path.join(os.path.expanduser('~'), '.config'))
DEFAULT_CONFIG_PATHS = [
'bio2bel.cfg',
'bio2bel.ini',
'pybel.cfg',
'pybel.ini',
os.path.join(_USER_CONFIG_DIRECTORY, 'bio2bel.ini'),
os.path.join(_USER_CONFIG_DIRECTORY, 'bio2bel.cfg'),
os.path.join(_USER_CONFIG_DIRECTORY, 'bio2bel', 'config.ini'),
os.path.join(_USER_CONFIG_DIRECTORY, 'bio2bel', 'bio2bel.cfg'),
os.path.join(_USER_CONFIG_DIRECTORY, 'bio2bel', 'bio2bel.ini'),
os.path.join(_USER_CONFIG_DIRECTORY, 'pybel.ini'),
os.path.join(_USER_CONFIG_DIRECTORY, 'pybel.cfg'),
os.path.join(_USER_CONFIG_DIRECTORY, 'pybel', 'config.ini'),
os.path.join(_USER_CONFIG_DIRECTORY, 'pybel', 'pybel.cfg'),
os.path.join(_USER_CONFIG_DIRECTORY, 'pybel', 'pybel.ini'),
]
BIO2BEL_MODULE = pystow.module('bio2bel')
BIO2BEL_HOME = BIO2BEL_MODULE.base
directory_option = click.option(
'-d',
'--directory',
type=click.Path(file_okay=False, dir_okay=True),
default=os.getcwd(),
help='output directory, defaults to current.',
show_default=True,
)
__all__ = [
'HERE',
'DATA_DIRECTORY',
'BIOREGISTRY_PATH',
'METAREGISTRY_PATH',
'BIOREGISTRY_MODULE',
'EnsureEntry',
]
HERE = pathlib.Path(os.path.abspath(os.path.dirname(__file__)))
DATA_DIRECTORY = HERE / 'data'
BIOREGISTRY_PATH = DATA_DIRECTORY / 'bioregistry.json'
METAREGISTRY_PATH = DATA_DIRECTORY / 'metaregistry.json'
COLLECTIONS_PATH = DATA_DIRECTORY / 'collections.json'
BIOREGISTRY_MODULE = pystow.module('bioregistry')
EnsureEntry = Any
DOCS = os.path.abspath(os.path.join(HERE, os.pardir, os.pardir, 'docs'))
DOCS_DATA = os.path.join(DOCS, '_data')
DOCS_IMG = os.path.join(DOCS, 'img')
#: The URL of the remote Bioregistry site
BIOREGISTRY_REMOTE_URL = pystow.get_config('bioregistry',
'url') or 'https://bioregistry.io'
#: Resolution is broken on identifiers.org for the following
IDOT_BROKEN = {
'gramene.growthstage',
'oma.hog',
'obi',
from typing import Callable
import bioversions
import pystow
__all__ = [
'RAW_DIRECTORY',
'DATABASE_DIRECTORY',
'SPECIES_REMAPPING',
'get_sqlalchemy_uri',
'version_getter',
]
logger = logging.getLogger(__name__)
PYOBO_MODULE = pystow.module('pyobo')
RAW_MODULE = PYOBO_MODULE.submodule('raw')
RAW_DIRECTORY = RAW_MODULE.base
DATABASE_MODULE = PYOBO_MODULE.submodule('database')
DATABASE_DIRECTORY = DATABASE_MODULE.base
SPECIES_REMAPPING = {
"Canis familiaris": "Canis lupus familiaris",
}
GLOBAL_SKIP = {
'rnao',
'mo', # deprecated
'resid', # deprecated
'adw', # deprecated
}
import click
import pandas as pd
import pybel
import pybel.constants as pc
import pyobo
import pystow
from more_click import verbose_option
from pybel.dsl import BaseConcept
from pyobo.xrefdb.sources.famplex import _get_famplex_df
from tqdm.autonotebook import tqdm
from causal_precedence_training.resources import HERE
logger = logging.getLogger(__name__)
module = pystow.module('causal_precedence_training', 'selventa')
fplx_df = _get_famplex_df()
bel_fplx = dict(fplx_df.loc[fplx_df['target_ns'] == 'BEL',
['target_id', 'source_id']].values)
@click.command()
@verbose_option
@click.option('--force', is_flag=True)
def main(force: bool):
for graph_name in 'large_corpus', 'small_corpus':
click.secho(f'{graph_name} results:', fg='blue')
df = get_normalized_dataframe(graph_name=graph_name, force=force)
click.echo(df.head())
import pystow
import yaml
HERE = os.path.abspath(os.path.dirname(__file__))
# Local resources
VOCABULARY_PATH = os.path.join(HERE, 'vocabulary.json')
RESULTS = os.path.join(HERE, 'results.json')
DATA_PATH = os.path.abspath(os.path.join(HERE, os.pardir, '_data'))
SURVEY_PATH = os.path.join(DATA_PATH, 'surveys.yml')
BENCHMARKS_PATH = os.path.join(DATA_PATH, 'benchmarks.yml')
CURATION_PATH = os.path.join(DATA_PATH, 'curation.yml')
# Cached resources
MOD = pystow.module('pykeen', 'metareview')
PAPERS_PATH = MOD.join(name='papers.json')
# Loaders
def _load_yaml(path):
with open(path) as file:
return yaml.safe_load(file)
def _load_json(path):
with open(path) as file:
return json.load(file)
import bioversions
import click
import more_click
import pystow
from tabulate import tabulate
from tqdm import tqdm
from zenodo_client import Creator, Metadata, ensure_zenodo
# unlike BioGRID, ExCAPE-DB can be considered a static resource
EXCAPE_URL = "https://zenodo.org/record/2543724/files/pubchem.chembl.dataset4publication_inchi_smiles_v2.tsv.xz"
EXCAPE_VERSION = "v2"
DISGENET_URL = "https://www.disgenet.org/static/disgenet_ap1/files/downloads/curated_gene_disease_associations.tsv.gz"
NSOCKG_MODULE = pystow.module("nsockg")
BIO = pystow.module("bio")
metadata = Metadata(
title="Not Scared of Chemistry Knowledge Graph",
upload_type="dataset",
description="A combination of ExCAPE-DB, BioGRID, HomoloGene, and chemical similarities in a knowledge graph.",
creators=[
Creator(
name="Hoyt, Charles Tapley",
affiliation="Harvard Medical School",
orcid="0000-0003-4423-4370",
),
],
)
)
__all__ = [
"PYKEEN_HOME",
"PYKEEN_DATASETS",
"PYKEEN_BENCHMARKS",
"PYKEEN_EXPERIMENTS",
"PYKEEN_CHECKPOINTS",
"PYKEEN_LOGS",
"AGGREGATIONS",
]
#: A manager around the PyKEEN data folder. It defaults to ``~/.data/pykeen``.
# This can be overridden with the envvar ``PYKEEN_HOME``.
#: For more information, see https://github.com/cthoyt/pystow
PYKEEN_MODULE: pystow.Module = pystow.module("pykeen")
#: A path representing the PyKEEN data folder
PYKEEN_HOME: Path = PYKEEN_MODULE.base
#: A subdirectory of the PyKEEN data folder for datasets, defaults to ``~/.data/pykeen/datasets``
PYKEEN_DATASETS: Path = PYKEEN_MODULE.join("datasets")
#: A subdirectory of the PyKEEN data folder for benchmarks, defaults to ``~/.data/pykeen/benchmarks``
PYKEEN_BENCHMARKS: Path = PYKEEN_MODULE.join("benchmarks")
#: A subdirectory of the PyKEEN data folder for experiments, defaults to ``~/.data/pykeen/experiments``
PYKEEN_EXPERIMENTS: Path = PYKEEN_MODULE.join("experiments")
#: A subdirectory of the PyKEEN data folder for checkpoints, defaults to ``~/.data/pykeen/checkpoints``
PYKEEN_CHECKPOINTS: Path = PYKEEN_MODULE.join("checkpoints")
#: A subdirectory for PyKEEN logs
PYKEEN_LOGS: Path = PYKEEN_MODULE.join("logs")
PYKEEN_DEFAULT_CHECKPOINT = "PyKEEN_just_saved_my_day.pt"
