def main(directory: str):
"""Export Hetionet in several BEL formats."""
click.echo(f'Using PyBEL v{pybel.get_version(with_git_hash=True)}')
click.echo('Getting hetionet')
graph = pybel.get_hetionet()
click.echo('Grounding hetionet')
graph = pybel.grounding.ground(graph)
click.echo('Exporting BEL Script')
script_gz_path = os.path.join(directory, 'hetionet-v1.0.bel.gz')
pybel.to_bel_script_gz(graph, script_gz_path)
click.echo('Exporting Nodelink')
nodelink_gz_path = os.path.join(directory,
'hetionet-v1.0.bel.nodelink.json.gz')
pybel.to_nodelink_gz(graph, nodelink_gz_path)
click.echo('Exporting GraphDati')
graphdati_gz_path = os.path.join(directory,
'hetionet-v1.0.bel.graphdati.json.gz')
pybel.to_graphdati_gz(graph, graphdati_gz_path)
click.echo('Exporting Machine Learning-ready TSV')
tsv_path = os.path.join(directory, 'hetionet-v1.0.tsv.gz')
with gzip.open(tsv_path, 'wt') as file:
pybel.to_tsv(graph, file)
def main(directory: str):
"""Make hetionet exports."""
path = os.path.join(directory, 'hetionet.bel.nodelink.json.gz')
if not os.path.exists(path):
graph = get_hetionet()
to_nodelink_gz(graph, path)
else:
click.echo('loading pickle from {}'.format(path))
graph = from_nodelink_gz(path)
output_bel_gz_path = os.path.join(directory, 'hetionet.bel.gz')
if not os.path.exists(output_bel_gz_path):
click.echo('outputting whole hetionet as BEL GZ to {}'.format(output_bel_gz_path))
to_bel_script_gz(graph, output_bel_gz_path, use_identifiers=True)
output_graphdati_jsonl_gz_path = os.path.join(directory, 'hetionet.bel.graphdati.jsonl.gz')
if not os.path.exists(output_graphdati_jsonl_gz_path):
click.echo('outputting whole hetionet as BEL GraphDati JSONL GZ to {}'.format(output_graphdati_jsonl_gz_path))
to_graphdati_jsonl_gz(graph, output_graphdati_jsonl_gz_path, use_identifiers=True)
output_graphdati_gz_path = os.path.join(directory, 'hetionet.bel.graphdati.json.gz')
if not os.path.exists(output_graphdati_gz_path):
click.echo('outputting whole hetionet as BEL GraphDati JSON GZ to {}'.format(output_graphdati_gz_path))
to_graphdati_gz(graph, output_graphdati_gz_path, use_identifiers=True)
summary_tsv_path = os.path.join(directory, 'hetionet_summary.tsv')
if not os.path.exists(summary_tsv_path):
click.echo('getting metaedges')
rows = []
keep_keys = set()
for value in get_metaedge_to_key(graph).values():
u, v, key = choice(list(value))
keep_keys.add(key)
d = graph[u][v][key]
bel = edge_to_bel(u, v, d, use_identifiers=True)
rows.append((key[:8], bel))
df = pd.DataFrame(rows, columns=['key', 'bel'])
df.to_csv(summary_tsv_path, sep='\t', index=False)
non_sample_edges = [
(u, v, k, d)
for u, v, k, d in tqdm(graph.edges(keys=True, data=True), desc='Getting non-sample edges to remove')
if k not in keep_keys
]
click.echo('Removing non-sample edges')
graph.remove_edges_from(non_sample_edges)
graph.remove_nodes_from(list(nx.isolates(graph)))
sample_bel_path = os.path.join(directory, 'hetionet_sample.bel')
click.echo('outputting sample hetionet in BEL to {}'.format(sample_bel_path))
to_bel_script(graph, sample_bel_path, use_identifiers=True)
sample_graphdati_path = os.path.join(directory, 'hetionet_sample.bel.graphdati.json')
click.echo('outputting sample hetionet in BEL to {}'.format(sample_bel_path))
to_graphdati_file(graph, sample_graphdati_path, use_identifiers=True, indent=2)
def ensure_graph(
name: str,
*,
manager_kwargs: Optional[Mapping[str, Any]] = None) -> BELGraph:
"""Get the BEL graph for a given Bio2BEL package."""
directory = get_data_dir(name)
path = os.path.join(directory, f'{name}.bel.nodelink.json.gz')
if os.path.exists(path):
return from_nodelink_gz(path)
_, module = ensure_bio2bel_installation(name)
manager = module.Manager(**(manager_kwargs or {}))
if not isinstance(manager, BELManagerMixin):
raise ValueError(f'{module} is not enabled for BEL export')
graph = manager.to_bel()
to_nodelink_gz(graph, path)
return graph
def write(
self,
*,
tp_nodes: Mapping[str, Set[Node]],
tp_edges: Mapping[str, Set[Edge]],
tn_nodes: Mapping[str, Set[Node]],
tn_edges: Mapping[str, Set[Edge]],
**kwargs,
) -> None:
"""Write the graph as gzipped BEL graphs."""
from pybel import to_nodelink_gz, to_bel_script_gz
for nodes, edges, name in ((tp_nodes, tp_edges, "positive"), (tn_nodes, tn_edges, "negative")):
graph = convert(nodes=nodes, edges=edges, name=name)
nodelink_path = os.path.join(self.graph_dir_path, f"{name}.bel.nodelink.json.gz")
to_nodelink_gz(graph, nodelink_path)
bel_script_path = os.path.join(self.graph_dir_path, f"{name}.bel.gz")
to_bel_script_gz(graph, bel_script_path)
def main(directory: str):
"""Export Hetionet in several BEL formats."""
click.echo('Getting hetionet')
graph = get_hetionet()
click.echo('Exporting BEL Script')
script_gz_path = os.path.join(directory, 'hetionet-v1.0.bel.gz')
to_bel_script_gz(graph, script_gz_path)
click.echo('Exporting Nodelink')
nodelink_gz_path = os.path.join(directory,
'hetionet-v1.0.bel.nodelink.json.gz')
to_nodelink_gz(graph, nodelink_gz_path)
click.echo('Exporting GraphDati')
graphdati_gz_path = os.path.join(directory,
'hetionet-v1.0.bel.graphdati.json.gz')
to_graphdati_gz(graph, graphdati_gz_path)
def ensure_graph(name: str, *, manager_kwargs: Optional[Mapping[str, Any]] = None) -> BELGraph:
"""Generate, cache, and return the BEL graph for a given Bio2BEL package.
If it has already been cached, it is loaded directly.
:param name: The name of the Bio2BEL package
:param manager_kwargs: Optional mapping to give as keyword arguments to the manager upon instantiation.
"""
directory = get_data_dir(name)
path = os.path.join(directory, f'{name}.bel.nodelink.json.gz')
if os.path.exists(path):
return from_nodelink_gz(path)
_, module = ensure_bio2bel_installation(name)
manager = module.Manager(**(manager_kwargs or {}))
if not isinstance(manager, BELManagerMixin):
raise ValueError(f'{module} is not enabled for BEL export')
graph = manager.to_bel()
to_nodelink_gz(graph, path)
return graph
def write_bel(connection, skip, directory, force):
"""Write all as BEL."""
os.makedirs(directory, exist_ok=True)
from .manager.bel_manager import BELManagerMixin
import pybel
for _, name, manager in _iterate_managers(connection, skip):
if not isinstance(manager, BELManagerMixin):
continue
click.secho(name, fg='cyan', bold=True)
path = os.path.join(directory, f'{name}.bel.pickle')
if os.path.exists(path) and not force:
click.echo('👍 already exported')
continue
if not manager.is_populated():
click.echo('👎 unpopulated')
else:
graph = manager.to_bel()
pybel.to_pickle(graph, path)
pybel.to_nodelink_gz(
graph, os.path.join(directory, f'{name}.bel.nodelink.json.gz'))
pybel.to_bel_script_gz(graph,
os.path.join(directory, f'{name}.bel.gz'))
