def main():
pvals, prob = [], []
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
for spatnull in simnulls.SPATNULLS:
for alpha in simnulls.ALPHAS:
if spatnull in simnulls.VERTEXWISE:
pvals.append(
combine_nulls('vertex', 'fsaverage5', spatnull, alpha))
prob.append(
combine_shuffle('vertex', 'fsaverage5', spatnull, alpha))
for parcellation, annotations in parcellations.items():
for scale in annotations:
pvals.append(
combine_nulls(parcellation, scale, spatnull, alpha))
prob.append(
combine_shuffle(parcellation, scale, spatnull, alpha))
col = ['parcellation', 'scale', 'spatnull', 'alpha', 'sim', 'corr', 'pval']
pvals = pd.concat(pvals, ignore_index=True)[col]
pvals.to_csv(SIMDIR / 'pval_summary.csv.gz', index=False)
prob = pd.DataFrame(prob)[col[:4] + ['prob']]
prob.to_csv(SIMDIR / 'prob_summary.csv.gz', index=False)
prob['alpha'] = prob['alpha'].astype('category')
auc = prob.groupby(['parcellation', 'scale', 'spatnull']) \
.apply(lambda x: metrics.auc(x['alpha'].cat.codes, x['prob']))
auc.name = 'auc'
auc = auc.reset_index()
auc.to_csv(SIMDIR / 'auc_summary.csv.gz', index=False)
def run_analysis():
""" Runs p-value x n_nulls analysis
Returns
-------
pvals : pd.DataFrame
Data examining p-values based on number of nulls used
"""
OUTDIR.mkdir(parents=True, exist_ok=True)
fn = OUTDIR / 'nnulls_summary.csv'
if fn.exists():
return pd.read_csv(fn)
subsets = []
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
for spatnull in simnulls.SPATNULLS:
for alpha in simnulls.ALPHAS:
if spatnull in simnulls.VERTEXWISE:
subsets.append(
pval_by_subsets('vertex', 'fsaverage5', spatnull, alpha), )
for parcellation, annotations in parcellations.items():
for scale in annotations:
subsets.append(
pval_by_subsets(parcellation, scale, spatnull,
alpha), )
subsets = pd.concat(subsets, ignore_index=True, sort=True)
subsets.to_csv(OUTDIR / 'nnulls_summary.csv.gz', index=False)
return subsets
def main():
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
# output dataframe
cols = ['parcellation', 'scale', 'spintype', 'n_sig']
data = pd.DataFrame(columns=cols)
# let's run all our parcellations
for parcellation, annotations in parcellations.items():
print(f'PARCELLATION: {parcellation}')
for scale in annotations:
for spintype in SPINTYPES:
data = data.append(run_null(parcellation, scale, spintype),
ignore_index=True)
# now calculate parametric null
nsdata = load_data(parcellation, scale, spintype)
corrs = np.corrcoef(nsdata.T)
# this calculates the correlation value for p < ALPHA cutoff
ab = (len(nsdata) / 2) - 1
cutoff = 1 - (special.btdtri(ab, ab, ALPHA / 2) * 2)
# now add the parametric null to our giant summary dataframe
data = data.append(pd.DataFrame({
'parcellation': parcellation,
'scale': scale,
'spintype': 'naive-para',
'n_sig': np.sum(np.triu(corrs > cutoff, k=1))
}, index=[0]), ignore_index=True)
data.to_csv(NSDIR / 'ns_summary.csv.gz', index=False)
def main():
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
# get inputs
args = get_parser()
# reset some stuff
for param in ('n_perm', 'n_proc', 'seed', 'n_sim', 'shuffle', 'use_knn'):
globals()[param.upper()] = args[param]
print(f'N_PERM: {N_PERM}',
f'N_PROC: {N_PROC}',
f'SEED: {SEED}',
f'SHUFFLE: {SHUFFLE}',
f'N_SIM: {N_SIM}',
f'SPATNULLS: {args["spatnull"]}',
f'ALPHAS: {args["alpha"]}\n', sep='\n')
if args['show_params']:
return
# everyone loves a four-level-deep nested for-loop :man_facepalming:
for spatnull in args['spatnull']:
for alpha in args['alpha']:
if spatnull in simnulls.VERTEXWISE:
run_null('vertex', 'fsaverage5', spatnull, alpha)
for parcellation, annotations in parcellations.items():
for scale in annotations:
run_null(parcellation, scale, spatnull, alpha)
def main():
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
# get inputs
args = get_parser()
# reset some stuff
for param in ('n_perm', 'n_proc', 'seed', 'run_moran', 'shuffle',
'use_knn'):
globals()[param.upper()] = args[param]
sims = range(args['start'], args['start'] + args['n_sim'])
print(f'N_PERM: {N_PERM}',
f'N_PROC: {N_PROC}',
f'SEED: {SEED}',
f'RUN_MORAN: {RUN_MORAN}',
f'SHUFFLE: {SHUFFLE}',
f'START: {sims.start}',
f'STOP: {sims.stop}\n',
sep='\n')
if args['show_params']:
return
for spatnull in args['spatnull']:
for alpha in args['alpha']:
# no parallelization here
for sim in sims:
# maybe parallelization here
if spatnull in simnulls.VERTEXWISE:
run_null('vertex', 'fsaverage5', spatnull, alpha, sim)
for parcellation, annotations in parcellations.items():
for scale in annotations:
run_null(parcellation, scale, spatnull, alpha, sim)
def main():
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
data = []
for alpha in simnulls.ALPHAS:
data.append(combine_moran('vertex', 'fsaverage5', alpha))
for parcellation, annotations in parcellations.items():
for scale in annotations:
data.append(combine_moran(parcellation, scale, alpha))
col = ['parcellation', 'scale', 'alpha', 'spatnull', 'sim', 'moran']
data = pd.concat(data, ignore_index=True)[col]
data.to_csv(SIMDIR / 'moran_summary.csv.gz', index=False)
def main():
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
# output dataframe
cols = [
'parcellation', 'scale', 'spintype', 'netclass', 'network', 'zscore',
'pval'
]
data = pd.DataFrame(columns=cols)
# use both Yeo + VEK network groupings
for netclass in ['yeo', 'vek']:
# run all our parcellations + spintypes
for parcellation, annotations in parcellations.items():
print(f'PARCELLATION: {parcellation}')
for scale in annotations.keys():
for spintype in SPINTYPES:
data = data.append(run_null(netclass, parcellation, scale,
spintype),
ignore_index=True)
# parametric null; use mean + p-value from t-statistic
raw = load_data(netclass, parcellation, scale)
raw['myelin'] = stats.zscore(raw['myelin'], ddof=1)
raw = raw.query('networks != 0')
pvals = [
stats.ttest_1samp(raw.loc[idx, 'myelin'], 0)[-1]
for net, idx in raw.groupby('networks').groups.items()
]
# now add the parametric null to our giant summary dataframe
data = data.append(pd.DataFrame({
'parcellation':
parcellation,
'scale':
scale,
'spintype':
'naive-para',
'netclass':
netclass,
'network':
list(NET_CODES[netclass].keys()),
'zscore':
raw.groupby('networks').mean()['myelin'],
'pval':
pvals
}),
ignore_index=True)
# save the output data !
data.to_csv(HCPDIR / 'summary.csv', index=False)
def main():
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
# output dataframe
data = pd.DataFrame(columns=[
'parcellation', 'scale', 'spintype', 'netclass', 'network', 'zscore',
'pval'
])
# use both Yeo + VEK network groupings
for netclass in ['yeo', 'vek']:
# run all our parcellations + spintypes
for parcellation, annotations in parcellations.items():
print(f'PARCELLATION: {parcellation}')
for scale in annotations.keys():
for spintype in SPINTYPES:
data = data.append(run_null(netclass, parcellation, scale,
spintype),
ignore_index=True)
# save the output data !
data.to_csv(HCPDIR / f'summary_thresh{PCTDROPTHRESH * 100:03.0f}.csv.gz',
index=False)
rhout = HCPDIR / 'S1200.R.MyelinMap_BC_MSMSAll.32k_fs_LR.func.gii'
run(CIFTISEP.format(cifti=cifti, lhout=lhout, rhout=rhout), quiet=True)
# for each hemisphere, resample to FreeSurfer fsaverage5 space and convert
# the resulting GII file to MGH (for consistency with NeuroSynth data)
for gii, hemi, surf in zip((lhout, rhout), ('L', 'R'), fsaverage):
out = HCPDIR / f'fsaverage5.MyelinMap.{hemi}.10k_fsavg_{hemi}.func.gii'
mgh = HCPDIR / f'{hemi.lower()}h.myelin.mgh'
run(HCP2FS.format(gii=gii, path=stds, hemi=hemi, out=out), quiet=True)
run(GIITOMGH.format(gii=out, surf=surf, out=mgh), quiet=True)
# remove intermediate file
if out.exists():
out.unlink()
# remove intermediate files
for fn in [lhout, rhout]:
if fn.exists():
fn.unlink()
# get parcellations that we'll use to parcellate data
parcellations = putils.get_cammoun_schaefer(data_dir=ROIDIR)
# get vertex-level data first
get_hcp_data(PARDIR / 'vertex' / 'fsaverage5.csv')
# now do parcellations
for name, annotations in parcellations.items():
for scale, annot in annotations.items():
get_hcp_data(PARDIR / name / f'{scale}.csv', annot=annot)