8.4. Computer Parcel Aggregation.

This example uses the ParcelAggregation marker to compute the mean of each parcel using the Schaefer parcellations (100 rois, 7 Yeo networks) for both 3D and 4D NIfTI.

Authors: Federico Raimondo, Synchon Mandal

License: BSD 3 clause

from junifer.testing.datagrabbers import (
    OasisVBMTestingDataGrabber,
    SPMAuditoryTestingDataGrabber,
)
from junifer.datareader import DefaultDataReader
from junifer.markers import ParcelAggregation
from junifer.utils import configure_logging

Set the logging level to info to see extra information

configure_logging(level="INFO")

/__w/junifer/junifer/junifer/utils/logging.py:155: UserWarning: The '__version__' attribute is deprecated and will be removed in MarkupSafe 3.1. Use feature detection, or `importlib.metadata.version("markupsafe")`, instead.
  vstring = str(getattr(module, "__version__", None))
2025-09-22 15:47:43,828 - JUNIFER - INFO - ===== Lib Versions =====
2025-09-22 15:47:43,828 - JUNIFER - INFO - click: 8.1.8
2025-09-22 15:47:43,828 - JUNIFER - INFO - numpy: 1.26.4
2025-09-22 15:47:43,828 - JUNIFER - INFO - scipy: 1.15.0
2025-09-22 15:47:43,828 - JUNIFER - INFO - datalad: 1.1.6
2025-09-22 15:47:43,828 - JUNIFER - INFO - pandas: 2.1.4
2025-09-22 15:47:43,828 - JUNIFER - INFO - nibabel: 5.3.2
2025-09-22 15:47:43,828 - JUNIFER - INFO - nilearn: 0.10.4
2025-09-22 15:47:43,828 - JUNIFER - INFO - sqlalchemy: 2.0.43
2025-09-22 15:47:43,828 - JUNIFER - INFO - ruamel.yaml: 0.18.15
2025-09-22 15:47:43,828 - JUNIFER - INFO - tqdm: 4.66.6
2025-09-22 15:47:43,828 - JUNIFER - INFO - templateflow: 24.2.2
2025-09-22 15:47:43,828 - JUNIFER - INFO - junifer_data: None
2025-09-22 15:47:43,828 - JUNIFER - INFO - junifer: 0.0.7.dev206
2025-09-22 15:47:43,828 - JUNIFER - INFO - ========================

Perform parcel aggregation on VBM GM data (3D) from OASIS dataset

with OasisVBMTestingDataGrabber() as dg:
    # Get the first element
    element = dg.get_elements()[0]
    # Read the element
    element_data = DefaultDataReader().fit_transform(dg[element])
    # Initialize marker
    marker = ParcelAggregation(parcellation="Schaefer100x7", method="mean")
    # Compute feature
    feature = marker.fit_transform(element_data)
    # Print the output
    print(feature.keys())
    print(feature["VBM_GM"]["aggregation"]["data"].shape)  # Shape is (1 x parcels)

2025-09-22 15:47:43,834 - JUNIFER - INFO - Getting element sub-01
2025-09-22 15:47:43,834 - JUNIFER - INFO - Reading VBM_GM from /github/home/nilearn_data/oasis1/OAS1_0001_MR1/mwrc1OAS1_0001_MR1_mpr_anon_fslswapdim_bet.nii.gz
2025-09-22 15:47:43,834 - JUNIFER - INFO - VBM_GM is of type NIFTI
2025-09-22 15:47:43,835 - JUNIFER - INFO - Computing VBM_GM
2025-09-22 15:47:43,835 - JUNIFER - INFO - Parcellation will be warped from MNI152NLin6Asym to MNI152Lin using highest resolution
2025-09-22 15:47:43,835 - JUNIFER - INFO - Parcellation parameters:
2025-09-22 15:47:43,835 - JUNIFER - INFO -      resolution: None
2025-09-22 15:47:43,835 - JUNIFER - INFO -      n_rois: 100
2025-09-22 15:47:43,836 - JUNIFER - INFO -      yeo_networks: 7
2025-09-22 15:47:43,836 - JUNIFER - INFO - Resolution set to None, using highest resolution.
2025-09-22 15:47:43,911 - JUNIFER - INFO - Loading parcellation: /github/home/junifer_data/v4/parcellations/Schaefer2018/Yeo2011/Schaefer2018_100Parcels_7Networks_order_FSLMNI152_1mm.nii.gz
2025-09-22 15:47:46,219 - JUNIFER - INFO - Downloading template MNI152Lin (T1w in resolution 1)
2025-09-22 15:47:46,723 - JUNIFER - INFO - antsApplyTransforms command to be executed:
antsApplyTransforms -d 3 -e 3 -n 'GenericLabel[NearestNeighbor]' -i /tmp/junifer/tmpsdoq4hv3/ants_parcellation_warper_Schaefer100x7_from_MNI152NLin6Asym_to_MNI152Lin_7ab86cf6-97cb-11f0-a4c0-5ace1b2a80e5or0h1c2y/prewarp_parcellation.nii.gz -r /tmp/junifer/tmpsdoq4hv3/ants_parcellation_warper_Schaefer100x7_from_MNI152NLin6Asym_to_MNI152Lin_7ab86cf6-97cb-11f0-a4c0-5ace1b2a80e5or0h1c2y/MNI152Lin_T1w.nii.gz -t /github/home/junifer_data/v4/.git/annex/objects/JQ/Pp/SHA256E-s145422752--5091350b36f951d455dabd429ebe86c493c75a0217dca311ae355f1d62e080b0.h5/SHA256E-s145422752--5091350b36f951d455dabd429ebe86c493c75a0217dca311ae355f1d62e080b0.h5 -o /tmp/junifer/tmpsdoq4hv3/ants_parcellation_warper_Schaefer100x7_from_MNI152NLin6Asym_to_MNI152Lin_7ab86cf6-97cb-11f0-a4c0-5ace1b2a80e5or0h1c2y/parcellation_warped.nii.gz
2025-09-22 15:47:53,015 - JUNIFER - INFO - antsApplyTransforms command succeeded with the following output:

2025-09-22 15:47:54,412 - JUNIFER - INFO - No storage specified, returning dictionary
dict_keys(['VBM_GM'])
(1, 100)

Perform parcel aggregation on BOLD data (4D) from SPM Auditory dataset

with SPMAuditoryTestingDataGrabber() as dg:
    # Get the first element
    element = dg.get_elements()[0]
    # Read the element
    element_data = DefaultDataReader().fit_transform(dg[element])
    # Initialize marker
    marker = ParcelAggregation(
        parcellation="Schaefer100x7", method="mean", on="BOLD"
    )
    # Compute feature
    feature = marker.fit_transform(element_data)
    # Print the output
    print(feature.keys())
    print(feature["BOLD"]["aggregation"]["data"].shape)  # Shape is (timepoints x parcels)

2025-09-22 15:47:54,414 - JUNIFER - INFO - Getting element sub001

Dataset created in /github/home/nilearn_data/spm_auditory

Data absent, downloading...
Downloading data from https://www.fil.ion.ucl.ac.uk/spm/download/data/MoAEpilot/MoAEpilot.zip ...

Downloaded 5365760 of 34212021 bytes (15.7%,    5.5s remaining)
Downloaded 13172736 of 34212021 bytes (38.5%,    3.2s remaining)
Downloaded 20135936 of 34212021 bytes (58.9%,    2.1s remaining)
Downloaded 26574848 of 34212021 bytes (77.7%,    1.2s remaining)
Downloaded 33161216 of 34212021 bytes (96.9%,    0.2s remaining) ...done. (6 seconds, 0 min)
Extracting data from /github/home/nilearn_data/spm_auditory/sub001/MoAEpilot.zip..... done.
2025-09-22 15:48:03,349 - JUNIFER - INFO - Reading BOLD from /tmp/tmpkwpwounn/sub001_bold.nii.gz
2025-09-22 15:48:03,349 - JUNIFER - INFO - BOLD is of type NIFTI
2025-09-22 15:48:03,350 - JUNIFER - INFO - Reading T1w from /tmp/tmpkwpwounn/sub001_T1w.nii.gz
2025-09-22 15:48:03,350 - JUNIFER - INFO - T1w is of type NIFTI
2025-09-22 15:48:03,351 - JUNIFER - INFO - Computing BOLD
2025-09-22 15:48:03,351 - JUNIFER - INFO - Parcellation will be warped from MNI152NLin6Asym to MNI152Lin using highest resolution
2025-09-22 15:48:03,351 - JUNIFER - INFO - Parcellation parameters:
2025-09-22 15:48:03,351 - JUNIFER - INFO -      resolution: None
2025-09-22 15:48:03,351 - JUNIFER - INFO -      n_rois: 100
2025-09-22 15:48:03,351 - JUNIFER - INFO -      yeo_networks: 7
2025-09-22 15:48:03,352 - JUNIFER - INFO - Resolution set to None, using highest resolution.
2025-09-22 15:48:03,426 - JUNIFER - INFO - Loading parcellation: /github/home/junifer_data/v4/parcellations/Schaefer2018/Yeo2011/Schaefer2018_100Parcels_7Networks_order_FSLMNI152_1mm.nii.gz
2025-09-22 15:48:05,717 - JUNIFER - INFO - Downloading template MNI152Lin (T1w in resolution 1)
2025-09-22 15:48:06,221 - JUNIFER - INFO - antsApplyTransforms command to be executed:
antsApplyTransforms -d 3 -e 3 -n 'GenericLabel[NearestNeighbor]' -i /tmp/junifer/tmpsdoq4hv3/ants_parcellation_warper_Schaefer100x7_from_MNI152NLin6Asym_to_MNI152Lin_865a9516-97cb-11f0-a4c0-5ace1b2a80e5r_bdflpv/prewarp_parcellation.nii.gz -r /tmp/junifer/tmpsdoq4hv3/ants_parcellation_warper_Schaefer100x7_from_MNI152NLin6Asym_to_MNI152Lin_865a9516-97cb-11f0-a4c0-5ace1b2a80e5r_bdflpv/MNI152Lin_T1w.nii.gz -t /github/home/junifer_data/v4/.git/annex/objects/JQ/Pp/SHA256E-s145422752--5091350b36f951d455dabd429ebe86c493c75a0217dca311ae355f1d62e080b0.h5/SHA256E-s145422752--5091350b36f951d455dabd429ebe86c493c75a0217dca311ae355f1d62e080b0.h5 -o /tmp/junifer/tmpsdoq4hv3/ants_parcellation_warper_Schaefer100x7_from_MNI152NLin6Asym_to_MNI152Lin_865a9516-97cb-11f0-a4c0-5ace1b2a80e5r_bdflpv/parcellation_warped.nii.gz
2025-09-22 15:48:12,572 - JUNIFER - INFO - antsApplyTransforms command succeeded with the following output:

2025-09-22 15:48:15,591 - JUNIFER - INFO - No storage specified, returning dictionary
dict_keys(['BOLD'])
(96, 100)