def build_masetome(est_path_iterlist, ID):
"""
Embeds structural-functional graph pairs into a common invariant subspace.
Parameters
----------
est_path_iterlist : list
List of list of pairs of file paths (.npy) corresponding to
structural and functional connectomes matched at a given node
resolution.
ID : str
A subject id or other unique identifier.
References
----------
.. [1] Rosenthal, G., Váša, F., Griffa, A., Hagmann, P., Amico, E., Goñi, J.,
Sporns, O. (2018). Mapping higher-order relations between brain structure
and function with embedded vector representations of connectomes.
Nature Communications. https://doi.org/10.1038/s41467-018-04614-w
"""
import numpy as np
from pynets.core.utils import prune_suffices
from pynets.stats.embeddings import _mase_embed
from pynets.core.utils import load_runconfig
# Available functional and structural connectivity models
hardcoded_params = load_runconfig()
try:
n_components = hardcoded_params["gradients"]["n_components"][0]
except KeyError:
import sys
print("ERROR: available gradient dimensionality presets not "
"sucessfully extracted from runconfig.yaml")
sys.exit(1)
out_paths = []
for pairs in est_path_iterlist:
pop_list = []
for _file in pairs:
pop_list.append(np.load(_file))
atlas = prune_suffices(pairs[0].split("/")[-3])
res = prune_suffices("_".join(pairs[0].split("/")[-1].split("modality")
[1].split("_")[1:]).split("_est")[0])
if "rsn" in res:
subgraph = res.split("rsn-")[1].split('_')[0]
else:
subgraph = "all_nodes"
out_path = _mase_embed(pop_list,
atlas,
pairs[0],
ID,
subgraph_name=subgraph,
n_components=n_components)
out_paths.append(out_path)
return out_paths
def build_masetome(est_path_iterlist, ID):
"""
Embeds structural-functional graph pairs into a common invariant subspace.
Parameters
----------
est_path_iterlist : list
List of list of pairs of file paths (.npy) corresponding to
structural and functional connectomes matched at a given node
resolution.
ID : str
A subject id or other unique identifier.
References
----------
.. [1] Rosenthal, G., Váša, F., Griffa, A., Hagmann, P., Amico, E., Goñi, J.,
Sporns, O. (2018). Mapping higher-order relations between brain structure
and function with embedded vector representations of connectomes.
Nature Communications. https://doi.org/10.1038/s41467-018-04614-w
"""
import numpy as np
from pynets.core.utils import prune_suffices
from pynets.stats.embeddings import _mase_embed
out_paths = []
for pairs in est_path_iterlist:
pop_list = []
for _file in pairs:
pop_list.append(np.load(_file))
atlas = prune_suffices(pairs[0].split("/")[-3])
res = prune_suffices("_".join(pairs[0].split("/")[-1].split("modality")
[1].split("_")[1:]).split("_est")[0])
if "rsn" in res:
subgraph = res.split("rsn-")[1]
else:
subgraph = "whole_brain"
out_path = _mase_embed(pop_list,
atlas,
pairs[0],
ID,
subgraph_name=subgraph)
out_paths.append(out_path)
return out_paths
def build_masetome(est_path_iterlist, ID):
"""
Embeds structural-functional graph pairs into a common invariant subspace.
Parameters
----------
est_path_iterlist : list
List of list of pairs of file paths (.npy) corresponding to
structural and functional connectomes matched at a given node
resolution.
ID : str
A subject id or other unique identifier.
References
----------
.. [1] Rosenthal, G., Váša, F., Griffa, A., Hagmann, P., Amico, E., Goñi,
J., Sporns, O. (2018). Mapping higher-order relations between brain
structure and function with embedded vector representations of
connectomes. Nature Communications.
https://doi.org/10.1038/s41467-018-04614-w
"""
from pathlib import Path
import os
import numpy as np
from pynets.core.utils import prune_suffices
from pynets.stats.embeddings import _mase_embed
from pynets.core.utils import load_runconfig
# Available functional and structural connectivity models
hardcoded_params = load_runconfig()
try:
n_components = hardcoded_params["gradients"][
"n_components"][0]
except KeyError:
import sys
print(
"ERROR: available gradient dimensionality presets not "
"sucessfully extracted from runconfig.yaml"
)
sys.exit(1)
out_paths = []
for pairs in est_path_iterlist:
pop_list = []
for _file in pairs:
mat = np.load(_file)
if np.isfinite(mat).all():
pop_list.append(mat)
if len(pop_list) != len(pairs):
continue
atlas = prune_suffices(pairs[0].split("/")[-3])
res = prune_suffices("_".join(pairs[0].split(
"/")[-1].split("modality")[1].split("_")[1:]).split("_est")[0])
if "rsn" in res:
subgraph = res.split("rsn-")[1].split('_')[0]
else:
subgraph = "all_nodes"
out_path = _mase_embed(
pop_list,
atlas,
pairs[0],
ID,
subgraph_name=subgraph, n_components=n_components)
if out_path is not None:
out_paths.append(out_path)
else:
# Add a null tmp file to prevent pool from breaking
dir_path = str(Path(os.path.dirname(pairs[0])))
namer_dir = f"{dir_path}/mplx_embeddings"
if os.path.isdir(namer_dir) is False:
os.makedirs(namer_dir, exist_ok=True)
out_path = (
f"{namer_dir}/gradient-MASE_{atlas}_{subgraph}"
f"_{os.path.basename(pairs[0])}_NULL"
)
if not os.path.exists(out_path):
os.mknod(out_path)
out_paths.append(out_path)
return out_paths
def build_embedded_connectome(est_path_iterlist, ID, multimodal, embed):
"""
Embeds ensemble population of graphs into an embedded ensemble feature vector.
Parameters
----------
est_path_iterlist : list
List of file paths to .npy file containing graph with thresholding applied.
ID : str
A subject id or other unique identifier.
multimodal : list
List of booleans indicating whether multiple modalities of input data have been specified.
embed : str
Specifies which type of ensemble embedding will be performed. Options include `omni` and `mase`.
"""
import yaml
from pathlib import Path
from pynets.stats.embeddings import _mase_embed, _omni_embed
# Available functional and structural connectivity models
with open("%s%s" % (str(Path(__file__).parent.parent), '/runconfig.yaml'),
'r') as stream:
hardcoded_params = yaml.load(stream)
try:
func_models = hardcoded_params['available_models']['func_models']
except KeyError:
print(
'ERROR: available functional models not sucessfully extracted from runconfig.yaml'
)
try:
struct_models = hardcoded_params['available_models'][
'struct_models']
except KeyError:
print(
'ERROR: available structural models not sucessfully extracted from runconfig.yaml'
)
if multimodal is True:
out_path = None
atlases = list(
set([x.split('/')[-3].split('/')[0] for x in est_path_iterlist]))
parcel_dict_func = dict.fromkeys(atlases)
parcel_dict_dwi = dict.fromkeys(atlases)
est_path_iterlist_dwi = list(
set([
i for i in est_path_iterlist
if i.split('est-')[1].split('_')[0] in struct_models
]))
est_path_iterlist_func = list(
set([
i for i in est_path_iterlist
if i.split('est-')[1].split('_')[0] in func_models
]))
func_subnets = list(
set([
i.split('_est')[0].split('/')[-1]
for i in est_path_iterlist_func
]))
dwi_subnets = list(
set([
i.split('_est')[0].split('/')[-1]
for i in est_path_iterlist_dwi
]))
for atlas in atlases:
if len(func_subnets) > 1:
parcel_dict_func[atlas] = {}
for sub_net in func_subnets:
parcel_dict_func[atlas][sub_net] = []
else:
parcel_dict_func[atlas] = []
if len(dwi_subnets) > 1:
parcel_dict_dwi[atlas] = {}
for sub_net in dwi_subnets:
parcel_dict_dwi[atlas][sub_net] = []
else:
parcel_dict_dwi[atlas] = []
for graph_path in est_path_iterlist_dwi:
if atlas in graph_path:
if len(dwi_subnets) > 1:
for sub_net in dwi_subnets:
if sub_net in graph_path:
parcel_dict_dwi[atlas][sub_net].append(
graph_path)
else:
parcel_dict_dwi[atlas].append(graph_path)
for graph_path in est_path_iterlist_func:
if atlas in graph_path:
if len(func_subnets) > 1:
for sub_net in func_subnets:
if sub_net in graph_path:
parcel_dict_func[atlas][sub_net].append(
graph_path)
else:
parcel_dict_func[atlas].append(graph_path)
pop_list = []
for pop_ref in parcel_dict_func[atlas]:
# RSN case
if isinstance(pop_ref, dict):
rsns = [i.split('_')[1] for i in list(pop_ref.keys())]
i = 0
for rsn in rsns:
pop_rsn_list = []
for graph in pop_ref[rsn]:
pop_list.append(np.load(graph))
if len(pop_rsn_list) > 1:
if len(list(set([i.shape
for i in pop_rsn_list]))) > 1:
raise RuntimeWarning(
'ERROR: Inconsistent number of vertices in graph population '
'that precludes embedding')
if embed == 'omni':
out_path = _omni_embed(pop_list, atlas,
graph_path, ID, rsns[i])
elif embed == 'mase':
out_path = _mase_embed(pop_list, atlas,
graph_path, ID, rsns[i])
else:
raise ValueError(
'Embedding type not recognized. Presently supported options include: '
'omni or mase')
else:
print(
'WARNING: Only one graph sampled, omnibus embedding not appropriate.'
)
pass
i = i + 1
else:
pop_list.append(np.load(pop_ref))
if len(pop_list) > 1:
if len(list(set([i.shape for i in pop_list]))) > 1:
raise RuntimeWarning(
'ERROR: Inconsistent number of vertices in graph population that '
'precludes embedding')
if embed == 'omni':
out_path = _omni_embed(pop_list, atlas, graph_path, ID)
elif embed == 'mase':
out_path = _mase_embed(pop_list, atlas, graph_path, ID)
else:
raise ValueError(
'Embedding type not recognized. Presently supported options include: '
'omni or mase')
else:
print(
'WARNING: Only one graph sampled, omnibus embedding not appropriate.'
)
pass
pop_list = []
for pop_ref in parcel_dict_dwi[atlas]:
# RSN case
if isinstance(pop_ref, dict):
rsns = [i.split('_')[1] for i in list(pop_ref.keys())]
i = 0
for rsn in rsns:
pop_rsn_list = []
for graph in pop_ref[rsn]:
pop_list.append(np.load(graph))
if len(pop_rsn_list) > 1:
if len(list(set([i.shape
for i in pop_rsn_list]))) > 1:
raise RuntimeWarning(
'ERROR: Inconsistent number of vertices in graph population '
'that precludes embedding')
if embed == 'omni':
out_path = _omni_embed(pop_list, atlas,
graph_path, ID, rsns[i])
elif embed == 'mase':
out_path = _mase_embed(pop_list, atlas,
graph_path, ID, rsns[i])
else:
raise ValueError(
'Embedding type not recognized. Presently supported options include: '
'omni or mase')
else:
print(
'WARNING: Only one graph sampled, omnibus embedding not appropriate.'
)
pass
i = i + 1
else:
pop_list.append(np.load(pop_ref))
if len(pop_list) > 1:
if len(list(set([i.shape for i in pop_list]))) > 1:
raise RuntimeWarning(
'ERROR: Inconsistent number of vertices in graph population that '
'precludes embedding')
if embed == 'omni':
out_path = _omni_embed(pop_list, atlas, graph_path, ID)
elif embed == 'mase':
out_path = _mase_embed(pop_list, atlas, graph_path, ID)
else:
raise ValueError(
'Embedding type not recognized. Presently supported options include: '
'omni or mase')
else:
print(
'WARNING: Only one graph sampled, omnibus embedding not appropriate.'
)
pass
elif (multimodal is False) and (len(est_path_iterlist) > 1):
atlases = list(
set([x.split('/')[-3].split('/')[0] for x in est_path_iterlist]))
parcel_dict = dict.fromkeys(atlases)
subnets = list(
set([
i.split('_est')[0].split('/')[-1] for i in est_path_iterlist
if i.split('_est')[0].split('/')[-1] != ID
]))
out_path = None
for atlas in atlases:
if len(subnets) > 1:
parcel_dict[atlas] = {}
for sub_net in subnets:
parcel_dict[atlas][sub_net] = []
else:
parcel_dict[atlas] = []
for graph_path in est_path_iterlist:
if atlas in graph_path:
if len(subnets) > 1:
for sub_net in subnets:
if sub_net in graph_path:
parcel_dict[atlas][sub_net].append(graph_path)
else:
parcel_dict[atlas].append(graph_path)
pop_list = []
for pop_ref in parcel_dict[atlas]:
# RSN case
if isinstance(pop_ref, dict):
rsns = [i.split('_')[1] for i in list(pop_ref.keys())]
i = 0
for rsn in rsns:
pop_rsn_list = []
for graph in pop_ref[rsn]:
pop_list.append(np.load(graph))
if len(pop_rsn_list) > 1:
if len(list(set([i.shape
for i in pop_rsn_list]))) > 1:
raise RuntimeWarning(
'ERROR: Inconsistent number of vertices in graph population '
'that precludes embedding')
out_path = _omni_embed(pop_rsn_list, rsns[i])
else:
print(
'WARNING: Only one graph sampled, omnibus embedding not appropriate.'
)
pass
i = i + 1
else:
pop_list.append(np.load(pop_ref))
if len(pop_list) > 1:
if len(list(set([i.shape for i in pop_list]))) > 1:
raise RuntimeWarning(
'ERROR: Inconsistent number of vertices in graph population that '
'precludes embedding')
if embed == 'omni':
out_path = _omni_embed(pop_list, atlas, graph_path, ID)
elif embed == 'mase':
out_path = _mase_embed(pop_list, atlas, graph_path, ID)
else:
raise ValueError(
'Embedding type not recognized. Presently supported options include: '
'omni or mase')
else:
print(
'WARNING: Only one graph sampled, omnibus embedding not appropriate.'
)
pass
else:
raise RuntimeWarning(
'ERROR: Only one graph sampled, omnibus embedding not appropriate.'
)
return out_path