def calc_map_corr(data_file1,
data_file2,
atlas_name,
roi_name,
out_file,
map_names1=None,
map_names2=None,
index=False):
"""
计算指定atlas的ROI内的data1 maps和data2 maps的相关
存出的CSV文件的index是map_names1, column是map_names2
Args:
data_file1 (str): end with .dscalar.nii
shape=(n_map1, LR_count_32k)
data_file2 (str): end with .dscalar.nii
shape=(n_map2, LR_count_32k)
atlas_name (str):
roi_name (str):
out_file (str):
map_names1 (list, optional): Defaults to None.
If is None, use map names in data1_file.
map_names2 (list, optional): Defaults to None.
If is None, use map names in data2_file.
index (bool, optional): Defaults to False.
Save index of DataFrame or not
"""
# prepare
reader1 = CiftiReader(data_file1)
reader2 = CiftiReader(data_file2)
data_maps1 = reader1.get_data()
data_maps2 = reader2.get_data()
atlas = Atlas(atlas_name)
assert atlas.maps.shape == (1, LR_count_32k)
roi_idx_map = atlas.maps[0] == atlas.roi2label[roi_name]
data_maps1 = data_maps1[:, roi_idx_map]
data_maps2 = data_maps2[:, roi_idx_map]
if map_names1 is None:
map_names1 = reader1.map_names()
else:
assert len(map_names1) == data_maps1.shape[0]
if map_names2 is None:
map_names2 = reader2.map_names()
else:
assert len(map_names2) == data_maps2.shape[0]
# calculate
corrs = 1 - cdist(data_maps1, data_maps2, 'correlation')
# save
df = pd.DataFrame(corrs, map_names1, map_names2)
df.to_csv(out_file, index=index)
def extract_net_parcel_info():
"""
把每个网络的编号，名字以及所包含的MMP parcel的编号和名字列出来
"""
from magicbox.io.io import CiftiReader
# inputs
net_file = pjoin(work_dir, 'networks.dlabel.nii')
# outputs
out_file = pjoin(work_dir, 'net_parcel_info.txt')
# prepare
reader = CiftiReader(net_file)
net_names = reader.map_names()
lbl_tables = reader.label_tables()
# calculate & save
wf = open(out_file, 'w')
for net_idx, net_name in enumerate(net_names):
wf.write(f'>>>{net_idx+1}-{net_name}\n')
lbl_tab = lbl_tables[net_idx]
for lbl_k, lbl_v in lbl_tab.items():
if lbl_k == 0:
continue
wf.write(f'{lbl_k}-{lbl_v.label[:-4]}\n')
wf.write('<<<\n')
wf.close()
def calc_pattern_corr_between_twins(meas_name='thickness'):
"""
Calculate spatial pattern correlation between each twin pair.
"""
import pandas as pd
import nibabel as nib
from magicbox.io.io import CiftiReader
from scipy.stats import pearsonr
twins_id_file = pjoin(work_dir, 'twins_id_1080.csv')
meas2file = {
'thickness':
'/nfs/p1/public_dataset/datasets/hcp/DATA/'
'HCP_S1200_GroupAvg_v1/HCP_S1200_GroupAvg_v1/'
'S1200.All.thickness_MSMAll.32k_fs_LR.dscalar.nii',
'myelin':
'/nfs/p1/public_dataset/datasets/hcp/DATA/'
'HCP_S1200_GroupAvg_v1/HCP_S1200_GroupAvg_v1/'
'S1200.All.MyelinMap_BC_MSMAll.32k_fs_LR.dscalar.nii',
'activ':
pjoin(proj_dir, 'analysis/s2/activation.dscalar.nii')
}
hemis = ('lh', 'rh')
hemi2stru = {
'lh': 'CIFTI_STRUCTURE_CORTEX_LEFT',
'rh': 'CIFTI_STRUCTURE_CORTEX_RIGHT'
}
mpm_file = pjoin(
proj_dir, 'analysis/s2/1080_fROI/refined_with_Kevin/'
'MPM_v3_{hemi}_0.25.nii.gz')
roi2label = {'IOG-face': 1, 'pFus-face': 2, 'mFus-face': 3}
zyg2label = {'MZ': 1, 'DZ': 2}
out_file = pjoin(work_dir, f'twins_pattern-corr_{meas_name}.csv')
df = pd.read_csv(twins_id_file)
meas_reader = CiftiReader(meas2file[meas_name])
meas_ids = [int(name.split('_')[0]) for name in meas_reader.map_names()]
twin1_indices = [meas_ids.index(i) for i in df['twin1']]
twin2_indices = [meas_ids.index(i) for i in df['twin2']]
out_df = pd.DataFrame()
out_df['zygosity'] = df['zygosity']
out_df['zyg'] = [zyg2label[zyg] for zyg in df['zygosity']]
for hemi in hemis:
meas1 = meas_reader.get_data(hemi2stru[hemi], True)[twin1_indices]
meas2 = meas_reader.get_data(hemi2stru[hemi], True)[twin2_indices]
mpm = nib.load(mpm_file.format(hemi=hemi)).get_data().squeeze()
for roi, lbl in roi2label.items():
idx_vec = mpm == lbl
out_df[f"{hemi}_{roi.split('-')[0]}"] = [
pearsonr(i[idx_vec], j[idx_vec])[0]
for i, j in zip(meas1, meas2)
]
out_df.to_csv(out_file, index=False)
def zscore_data(data_file, out_file):
"""
对每个被试做全脑zscore
Args:
data_file (str): .dscalar.nii
out_file (str): .dscalar.nii
"""
reader = CiftiReader(data_file)
data = reader.get_data()
data = zscore(data, 1)
save2cifti(out_file, data, reader.brain_models(), reader.map_names())
def check_1096_sid():
"""
检查HCPY_SubjInfo.csv文件中的1096个被试ID及其顺序和
S1200 1096 myelin file, S1200 1096 thickness file
是对的上的
"""
df = pd.read_csv(dataset_name2info['HCPY'])
subj_ids = df['subID'].to_list()
fpaths = (s1200_1096_myelin, s1200_1096_thickness)
for fpath in fpaths:
reader = CiftiReader(fpath)
tmp = [int(i.split('_')[0]) for i in reader.map_names()]
assert tmp == subj_ids
def mask_maps(data_file, atlas_name, roi_name, out_file):
"""
把data map在指定atlas的ROI以外的部分全赋值为nan
Args:
data_file (str): end with .dscalar.nii
shape=(n_map, LR_count_32k)
atlas_name (str):
roi_name (str):
out_file (str):
"""
# prepare
reader = CiftiReader(data_file)
data = reader.get_data()
atlas = Atlas(atlas_name)
assert atlas.maps.shape == (1, LR_count_32k)
roi_idx_map = atlas.maps[0] == atlas.roi2label[roi_name]
# calculate
data[:, ~roi_idx_map] = np.nan
# save
save2cifti(out_file, data, reader.brain_models(), reader.map_names())
