9.1.4. Markers¶

Markers for feature extraction.

class junifer.markers.ALFFParcels(parcellation, using, highpass=0.01, lowpass=0.1, tr=None, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for ALFF / fALFF on parcels.

Parameters:

parcellationstr or list of str

The name(s) of the parcellation(s). Check valid options by calling list_parcellations().

using{“junifer”, “afni”}

Implementation to use for computing ALFF:

“junifer” : Use junifer’s own ALFF implementation
“afni” : Use AFNI’s 3dRSFC

highpasspositive float, optional

The highpass cutoff frequency for the bandpass filter. If 0, it will not apply a highpass filter (default 0.01).

lowpasspositive float, optional

The lowpass cutoff frequency for the bandpass filter (default 0.1).

trpositive float, optional

The Repetition Time of the BOLD data. If None, will extract the TR from NIfTI header (default None).

agg_methodstr, optional

The method to perform aggregation using. Check valid options in get_aggfunc_by_name() (default “mean”).

agg_method_paramsdict, optional

Parameters to pass to the aggregation function. Check valid options in get_aggfunc_by_name() (default None).

masksstr, dict or list of dict or str, optional

The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).

namestr, optional

The name of the marker. If None, will use the class name (default None).

Notes

The tr parameter is crucial for the correctness of fALFF/ALFF computation. If a dataset is correctly preprocessed, the tr should be extracted from the NIfTI without any issue. However, it has been reported that some preprocessed data might not have the correct tr in the NIfTI header.

ALFF/fALFF are computed using a bandpass butterworth filter. See scipy.signal.butter() and scipy.signal.filtfilt() for more details.

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: The BOLD data as dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

alff : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str
falff : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.ALFFSpheres(coords, using, radius=None, allow_overlap=False, highpass=0.01, lowpass=0.1, tr=None, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for computing ALFF / fALFF on spheres.

Parameters:

coordsstr

The name of the coordinates list to use. See list_coordinates() for options.

using{“junifer”, “afni”}

Implementation to use for computing ALFF:

“junifer” : Use junifer’s own ALFF implementation
“afni” : Use AFNI’s 3dRSFC

radiusfloat, optional

The radius of the sphere in mm. If None, the signal will be extracted from a single voxel. See nilearn.maskers.NiftiSpheresMasker for more information (default None).

allow_overlapbool, optional

Whether to allow overlapping spheres. If False, an error is raised if the spheres overlap (default is False).

highpasspositive float, optional

The highpass cutoff frequency for the bandpass filter. If 0, it will not apply a highpass filter (default 0.01).

lowpasspositive float, optional

The lowpass cutoff frequency for the bandpass filter (default 0.1).

trpositive float, optional

The Repetition Time of the BOLD data. If None, will extract the TR from NIfTI header (default None).

agg_methodstr, optional

The method to perform aggregation using. Check valid options in get_aggfunc_by_name() (default “mean”).

agg_method_paramsdict, optional

Parameters to pass to the aggregation function. Check valid options in get_aggfunc_by_name().

masksstr, dict or list of dict or str, optional

The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).

namestr, optional

The name of the marker. If None, will use the class name (default None).

Notes

ALFF/fALFF are computed using a bandpass butterworth filter. See scipy.signal.butter() and scipy.signal.filtfilt() for more details.

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: The BOLD data as dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

alff : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str
falff : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.BaseMarker(on=None, name=None)¶

Abstract base class for all markers.

For every interface that is required, one needs to provide a concrete implementation of this abstract class.

Parameters:

onstr or list of str or None, optional: The data type to apply the marker on. If None, will work on all available data types (default None).
namestr, optional: The name of the marker. If None, will use the class name as the name of the marker (default None).

Raises:

AttributeError: If the marker does not have _MARKER_INOUT_MAPPINGS attribute.
ValueError: If required input data type(s) is(are) not found.

abstract compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict: The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter.

get_output_type(input_type, output_feature)¶

Get output type.

Parameters:

input_typestr: The data type input to the marker.
output_featurestr: The feature output of the marker.

Returns:

str: The storage type output of the marker.

get_valid_inputs()¶

Get valid data types for input.

Returns:

list of str: The list of data types that can be used as input for this marker.

store(type_, feature, out, storage)¶

Store.

Parameters:

type_str: The data type to store.
featurestr: The feature to store.
outdict: The computed result as a dictionary to store.
storagestorage-like: The storage class, for example, SQLiteFeatureStorage.

validate_input(input)¶

Validate input.

Parameters:

inputlist of str: The input to the pipeline step. The list must contain the available Junifer Data dictionary keys.

Returns:

list of str: The actual elements of the input that will be processed by this pipeline step.

Raises:

ValueError: If the input does not have the required data.

class junifer.markers.BrainPrint(num=50, skip_cortex=False, keep_eigenvectors=False, norm='none', reweight=False, asymmetry=False, asymmetry_distance='euc', use_cholmod=False, name=None)¶

Class for BrainPrint.

Parameters:

numpositive int, optional

Number of eigenvalues to compute (default 50).

skip_cortexbool, optional

Whether to skip cortical surface or not (default False).

keep_eigenvectorsbool, optional

Whether to also return eigenvectors or not (default False).

normstr, optional

Eigenvalues normalization method (default “none”).

reweightbool, optional

Whether to reweight eigenvalues or not (default False).

asymmetrybool, optional

Whether to calculate asymmetry between lateral structures (default False).

asymmetry_distance{“euc”}, optional

Distance measurement to use if asymmetry=True:

"euc" : Euclidean

(default “euc”).

use_cholmodbool, optional

If True, attempts to use the Cholesky decomposition for improved execution speed. Requires the scikit-sparse library. If it cannot be found, an error will be thrown. If False, will use slower LU decomposition (default False).

namestr, optional

The name of the marker. If None, will use the class name (default None).

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: The FreeSurfer data as dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

eigenvalues : dictionary with the following keys:
- data : eigenvalues as np.ndarray
- col_names : surface labels as list of str
- row_names : eigenvalue count labels as list of str
- row_header_col_name“eigenvalue”
  ()
areas : dictionary with the following keys:
- data : areas as np.ndarray
- col_names : surface labels as list of str
volumes : dictionary with the following keys:
- data : volumes as np.ndarray
- col_names : surface labels as list of str
distancesdictionary with the following keys
if asymmetry = True:
- data : distances as np.ndarray
- col_names : surface labels as list of str

References

[1]

Wachinger, C., Golland, P., Kremen, W. et al. (2015) BrainPrint: A discriminative characterization of brain morphology. NeuroImage, Volume 109, Pages 232-248. https://doi.org/10.1016/j.neuroimage.2015.01.032.

[2]

Reuter, M., Wolter, F.E., Peinecke, N. (2006) Laplace-Beltrami spectra as ‘Shape-DNA’ of surfaces and solids. Computer-Aided Design, Volume 38, Issue 4, Pages 342-366. https://doi.org/10.1016/j.cad.2005.10.011.

class junifer.markers.CrossParcellationFC(parcellation_one, parcellation_two, agg_method='mean', agg_method_params=None, corr_method='pearson', masks=None, name=None)¶

Class for calculating parcel-wise correlations with 2 parcellations.

Parameters:

parcellation_onestr: The name of the first parcellation.
parcellation_twostr: The name of the second parcellation.
agg_methodstr, optional: The method to perform aggregation using. See get_aggfunc_by_name() for options (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. See get_aggfunc_by_name() for options (default None).
corr_methodstr, optional: Any method that can be passed to pandas.DataFrame.corr() (default “pearson”).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use BOLD_CrossParcellationFC (default None).

compute(input, extra_input=None)¶

Compute.

Take a timeseries, parcellate them with two different parcellation schemes, and get parcel-wise correlations between the two different parcellated time series. Shape of output matrix corresponds to number of ROIs in (parcellation_two, parcellation_one).

Parameters:

inputdict: The BOLD data as a dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

functional_connectivity : dictionary with the following keys:
- datacorrelation between the two parcellations as
  numpy.ndarray
- col_namesROI labels for first parcellation as list of
  str
- row_namesROI labels for second parcellation as list of
  str

class junifer.markers.EdgeCentricFCParcels(parcellation, agg_method='mean', agg_method_params=None, conn_method='correlation', conn_method_params=None, masks=None, name=None)¶

Class for edge-centric FC using parcellations.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s) to use. See list_parcellations() for options.
agg_methodstr, optional: The method to perform aggregation using. See get_aggfunc_by_name() for options (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. See get_aggfunc_by_name() for options (default None).
conn_methodstr, optional: The method to perform connectivity measure using. See JuniferConnectivityMeasure for options (default “correlation”).
conn_method_paramsdict, optional: Parameters to pass to JuniferConnectivityMeasure. If None, {"empirical": True} will be used, which would mean sklearn.covariance.EmpiricalCovariance is used to compute covariance. If usage of sklearn.covariance.LedoitWolf is desired, {"empirical": False} should be passed (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use BOLD_EdgeCentricFCParcels (default None).

References

[1]

Jo et al. (2021) Subject identification using edge-centric functional connectivity. https://doi.org/10.1016/j.neuroimage.2021.118204

aggregate(input, extra_input=None)¶

Perform parcel aggregation and ETS computation.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.EdgeCentricFCSpheres(coords, radius=None, allow_overlap=False, agg_method='mean', agg_method_params=None, conn_method='correlation', conn_method_params=None, masks=None, name=None)¶

Class for edge-centric FC using coordinates (spheres).

Parameters:

coordsstr: The name of the coordinates list to use. See list_coordinates() for options.
radiuspositive float, optional: The radius of the sphere around each coordinates in millimetres. If None, the signal will be extracted from a single voxel. See JuniferNiftiSpheresMasker for more information (default None).
allow_overlapbool, optional: Whether to allow overlapping spheres. If False, an error is raised if the spheres overlap (default False).
agg_methodstr, optional: The method to perform aggregation using. See get_aggfunc_by_name() for options (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. See get_aggfunc_by_name() for options (default None).
conn_methodstr, optional: The method to perform connectivity measure using. See JuniferConnectivityMeasure for options (default “correlation”).
conn_method_paramsdict, optional: Parameters to pass to JuniferConnectivityMeasure. If None, {"empirical": True} will be used, which would mean sklearn.covariance.EmpiricalCovariance is used to compute covariance. If usage of sklearn.covariance.LedoitWolf is desired, {"empirical": False} should be passed (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use BOLD_EdgeCentricFCSpheres (default None).

References

[1]

Jo et al. (2021) Subject identification using edge-centric functional connectivity. https://doi.org/10.1016/j.neuroimage.2021.118204

aggregate(input, extra_input=None)¶

Perform sphere aggregation and ETS computation.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.FunctionalConnectivityParcels(parcellation, agg_method='mean', agg_method_params=None, conn_method='correlation', conn_method_params=None, masks=None, name=None)¶

Class for functional connectivity using parcellations.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s) to use. See list_parcellations() for options.
agg_methodstr, optional: The method to perform aggregation using. See get_aggfunc_by_name() for options (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. See get_aggfunc_by_name() for options (default None).
conn_methodstr, optional: The method to perform connectivity measure using. See JuniferConnectivityMeasure for options (default “correlation”).
conn_method_paramsdict, optional: Parameters to pass to JuniferConnectivityMeasure. If None, {"empirical": True} will be used, which would mean sklearn.covariance.EmpiricalCovariance is used to compute covariance. If usage of sklearn.covariance.LedoitWolf is desired, {"empirical": False} should be passed (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use BOLD_FunctionalConnectivityParcels (default None).

aggregate(input, extra_input=None)¶

Perform parcel aggregation.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.FunctionalConnectivitySpheres(coords, radius=None, allow_overlap=False, agg_method='mean', agg_method_params=None, conn_method='correlation', conn_method_params=None, masks=None, name=None)¶

Class for functional connectivity using coordinates (spheres).

Parameters:

coordsstr: The name of the coordinates list to use. See list_coordinates() for options.
radiuspositive float, optional: The radius of the sphere around each coordinates in millimetres. If None, the signal will be extracted from a single voxel. See JuniferNiftiSpheresMasker for more information (default None).
allow_overlapbool, optional: Whether to allow overlapping spheres. If False, an error is raised if the spheres overlap (default False).
agg_methodstr, optional: The method to perform aggregation using. See get_aggfunc_by_name() for options (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. See get_aggfunc_by_name() for options (default None).
conn_methodstr, optional: The method to perform connectivity measure using. See JuniferConnectivityMeasure for options (default “correlation”).
conn_method_paramsdict, optional: Parameters to pass to JuniferConnectivityMeasure. If None, {"empirical": True} will be used, which would mean sklearn.covariance.EmpiricalCovariance is used to compute covariance. If usage of sklearn.covariance.LedoitWolf is desired, {"empirical": False} should be passed (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use BOLD_FunctionalConnectivitySpheres (default None).

aggregate(input, extra_input=None)¶

Perform sphere aggregation.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.MarkerCollection(markers, datareader=None, preprocessors=None, storage=None)¶

Class for marker collection.

Parameters:

markerslist of marker-like: The markers to compute.
datareaderDataReader-like object, optional: The DataReader to use (default None).
preprocessorslist of preprocessing-like, optional: The preprocessors to apply (default None).
storagestorage-like, optional: The storage to use (default None).

Raises:

ValueError: If markers have same names.

fit(input)¶

Fit the pipeline.

Parameters:

inputdict: The input data to fit the pipeline on. Should be the output of indexing the Data Grabber with one element.

Returns:

dict or None: The output of the pipeline. Each key represents a marker name and the values are the computer marker values. If the pipeline has a storage configured, then the output will be None.

validate(datagrabber)¶

Validate the pipeline.

Without doing any computation, check if the marker collection can be fitted without problems i.e., the data required for each marker is present and streamed down the steps. Also, if a storage is configured, check that the storage can handle the markers’ output.

Parameters:

datagrabberDataGrabber-like: The DataGrabber to validate.

class junifer.markers.ParcelAggregation(parcellation, method, method_params=None, time_method=None, time_method_params=None, masks=None, on=None, name=None)¶

Class for parcel aggregation.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling list_parcellations().
methodstr: The method to perform aggregation using. Check valid options in get_aggfunc_by_name().
method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in get_aggfunc_by_name().
time_methodstr, optional: The method to use to aggregate the time series over the time points, after applying method (only applicable to BOLD data). If None, it will not operate on the time dimension (default None).
time_method_paramsdict, optional: The parameters to pass to the time aggregation method (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
on{“T1w”, “T2w”, “BOLD”, “VBM_GM”, “VBM_WM”, “VBM_CSF”, “fALFF”, “GCOR”, “LCOR”} or list of the options, optional: The data types to apply the marker to. If None, will work on all available data (default None).
namestr, optional: The name of the marker. If None, will use the class name (default None).

Raises:

ValueError: If time_method is specified for non-BOLD data or if time_method_params is not None when time_method is None.

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

Warns:

RuntimeWarning: If time aggregation is required but only time point is available.

class junifer.markers.RSSETSMarker(parcellation, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for root sum of squares of edgewise timeseries.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use the class name (default None).

compute(input, extra_input=None)¶

Compute.

Take a timeseries of brain areas, and calculate timeseries for each edge according to the method outlined in [1]. For more information, check https://github.com/brain-networks/edge-ts/blob/master/main.m

Parameters:

inputdict: The BOLD data as dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

data : the actual computed values as a numpy.ndarray
col_names : the column labels for the computed values as list

References

[1]

Zamani Esfahlani et al. (2020) High-amplitude cofluctuations in cortical activity drive functional connectivity doi: 10.1073/pnas.2005531117

class junifer.markers.ReHoParcels(parcellation, using, reho_params=None, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for regional homogeneity on parcels.

Parameters:

parcellationstr or list of str

The name(s) of the parcellation(s). Check valid options by calling list_parcellations().

using{“junifer”, “afni”}

Implementation to use for computing ReHo:

“junifer” : Use junifer’s own ReHo implementation
“afni” : Use AFNI’s 3dReHo

reho_paramsdict, optional

Extra parameters for computing ReHo map as a dictionary (default None). If using="afni", then the valid keys are:

nneigh{7, 19, 27}, optional (default 27)
Number of voxels in the neighbourhood, inclusive. Can be:
- 7 : for facewise neighbours only
- 19 : for face- and edge-wise neighbours
- 27 : for face-, edge-, and node-wise neighbors
neigh_radpositive float, optional
The radius of a desired neighbourhood (default None).
neigh_xpositive float, optional
The semi-radius for x-axis of ellipsoidal volumes (default None).
neigh_ypositive float, optional
The semi-radius for y-axis of ellipsoidal volumes (default None).
neigh_zpositive float, optional
The semi-radius for z-axis of ellipsoidal volumes (default None).
box_radpositive int, optional
The number of voxels outward in a given cardinal direction for a cubic box centered on a given voxel (default None).
box_xpositive int, optional
The number of voxels for +/- x-axis of cuboidal volumes (default None).
box_ypositive int, optional
The number of voxels for +/- y-axis of cuboidal volumes (default None).
box_zpositive int, optional
The number of voxels for +/- z-axis of cuboidal volumes (default None).

else if using="junifer", then the valid keys are:

nneigh{7, 19, 27, 125}, optional (default 27)
Number of voxels in the neighbourhood, inclusive. Can be:
- 7 : for facewise neighbours only
- 19 : for face- and edge-wise neighbours
- 27 : for face-, edge-, and node-wise neighbors
- 125 : for 5x5 cuboidal volume

agg_methodstr, optional

The method to perform aggregation using. Check valid options in get_aggfunc_by_name() (default “mean”).

agg_method_paramsdict, optional

Parameters to pass to the aggregation function. Check valid options in get_aggfunc_by_name() (default None).

masksstr, dict or list of dict or str, optional

The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).

namestr, optional

The name of the marker. If None, it will use the class name (default None).

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: The BOLD data as dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

reho : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.ReHoSpheres(coords, using, radius=None, allow_overlap=False, reho_params=None, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for regional homogeneity on spheres.

Parameters:

coordsstr

The name of the coordinates list to use. See list_coordinates() for options.

using{“junifer”, “afni”}

Implementation to use for computing ReHo:

“junifer” : Use junifer’s own ReHo implementation
“afni” : Use AFNI’s 3dReHo

radiusfloat, optional

The radius of the sphere in millimeters. If None, the signal will be extracted from a single voxel. See nilearn.maskers.NiftiSpheresMasker for more information (default None).

allow_overlapbool, optional

Whether to allow overlapping spheres. If False, an error is raised if the spheres overlap (default is False).

use_afnibool, optional

Whether to use AFNI for computing. If None, will use AFNI only if available (default None).

reho_paramsdict, optional

Extra parameters for computing ReHo map as a dictionary (default None). If using="afni", then the valid keys are:

nneigh{7, 19, 27}, optional (default 27)
Number of voxels in the neighbourhood, inclusive. Can be:
- 7 : for facewise neighbours only
- 19 : for face- and edge-wise neighbours
- 27 : for face-, edge-, and node-wise neighbors
neigh_radpositive float, optional
The radius of a desired neighbourhood (default None).
neigh_xpositive float, optional
The semi-radius for x-axis of ellipsoidal volumes (default None).
neigh_ypositive float, optional
The semi-radius for y-axis of ellipsoidal volumes (default None).
neigh_zpositive float, optional
The semi-radius for z-axis of ellipsoidal volumes (default None).
box_radpositive int, optional
The number of voxels outward in a given cardinal direction for a cubic box centered on a given voxel (default None).
box_xpositive int, optional
The number of voxels for +/- x-axis of cuboidal volumes (default None).
box_ypositive int, optional
The number of voxels for +/- y-axis of cuboidal volumes (default None).
box_zpositive int, optional
The number of voxels for +/- z-axis of cuboidal volumes (default None).

else if using="junifer", then the valid keys are:

nneigh{7, 19, 27, 125}, optional (default 27)
Number of voxels in the neighbourhood, inclusive. Can be:
- 7 : for facewise neighbours only
- 19 : for face- and edge-wise neighbours
- 27 : for face-, edge-, and node-wise neighbors
- 125 : for 5x5 cuboidal volume

agg_methodstr, optional

The aggregation method to use. See get_aggfunc_by_name() for more information (default None).

agg_method_paramsdict, optional

The parameters to pass to the aggregation method (default None).

masksstr, dict or list of dict or str, optional

The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).

namestr, optional

The name of the marker. If None, it will use the class name (default None).

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: The BOLD data as dictionary.
extra_inputdict, optional: The other fields in the pipeline data object (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

reho : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.SphereAggregation(coords, radius=None, allow_overlap=False, method='mean', method_params=None, time_method=None, time_method_params=None, masks=None, on=None, name=None)¶

Class for sphere aggregation.

Parameters:

coordsstr: The name of the coordinates list to use. See list_coordinates() for options.
radiusfloat, optional: The radius of the sphere in millimeters. If None, the signal will be extracted from a single voxel. See nilearn.maskers.NiftiSpheresMasker for more information (default None).
allow_overlapbool, optional: Whether to allow overlapping spheres. If False, an error is raised if the spheres overlap (default is False).
methodstr, optional: The aggregation method to use. See get_aggfunc_by_name() for more information (default “mean”).
method_paramsdict, optional: The parameters to pass to the aggregation method (default None).
time_methodstr, optional: The method to use to aggregate the time series over the time points, after applying method (only applicable to BOLD data). If None, it will not operate on the time dimension (default None).
time_method_paramsdict, optional: The parameters to pass to the time aggregation method (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
on{“T1w”, “T2w”, “BOLD”, “VBM_GM”, “VBM_WM”, “VBM_CSF”, “fALFF”, “GCOR”, “LCOR”} or list of the options, optional: The data types to apply the marker to. If None, will work on all available data (default None).
namestr, optional: The name of the marker. By default, it will use KIND_SphereAggregation where KIND is the kind of data it was applied to (default None).

Raises:

ValueError: If time_method is specified for non-BOLD data or if time_method_params is not None when time_method is None.

compute(input, extra_input=None)¶

Compute.

Parameters:

inputdict: A single input from the pipeline data object in which to compute the marker.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI values as numpy.ndarray
- col_names : ROI labels as list of str

Warns:

RuntimeWarning: If time aggregation is required but only time point is available.

class junifer.markers.TemporalSNRParcels(parcellation, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for temporal signal-to-noise ratio using parcellations.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. If None, will use the class name (default None).

aggregate(input, extra_input=None)¶

Perform parcel aggregation.

Parameters:

inputdict: A single input from the pipeline data object in which the data is the voxelwise temporal SNR map.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI-wise tSNR values as numpy.ndarray
- col_names : ROI labels as list of str

class junifer.markers.TemporalSNRSpheres(coords, radius=None, allow_overlap=False, agg_method='mean', agg_method_params=None, masks=None, name=None)¶

Class for temporal signal-to-noise ratio using coordinates (spheres).

Parameters:

coordsstr: The name of the coordinates list to use. See list_coordinates() for options.
radiusfloat, optional: The radius of the sphere in mm. If None, the signal will be extracted from a single voxel. See nilearn.maskers.NiftiSpheresMasker for more information (default None).
allow_overlapbool, optional: Whether to allow overlapping spheres. If False, an error is raised if the spheres overlap (default is False).
agg_methodstr, optional: The aggregation method to use. See get_aggfunc_by_name() for more information (default None).
agg_method_paramsdict, optional: The parameters to pass to the aggregation method (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
namestr, optional: The name of the marker. By default, it will use KIND_FunctionalConnectivitySpheres where KIND is the kind of data it was applied to (default None).

aggregate(input, extra_input=None)¶

Perform sphere aggregation.

Parameters:

inputdict: A single input from the pipeline data object in which the data is the voxelwise temporal SNR map.
extra_inputdict, optional: The other fields in the pipeline data object. Useful for accessing other data kind that needs to be used in the computation. For example, the functional connectivity markers can make use of the confounds if available (default None).

Returns:

dict

The computed result as dictionary. This will be either returned to the user or stored in the storage by calling the store method with this as a parameter. The dictionary has the following keys:

aggregation : dictionary with the following keys:
- data : ROI-wise tSNR values as numpy.ndarray
- col_names : ROI labels as list of str

Complexity¶

Provide imports for complexity sub-package.

class junifer.markers.complexity.HurstExponent(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for Hurst exponent of a time series.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the Hurst exponent calculation function. For more information, check out junifer.markers.utils._hurst_exponent. If None, value is set to {“method”: “dfa”} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import HurstExponent or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, and calculate Hurst exponent using the detrended fluctuation analysis method assuming the data is monofractal [1].

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.fractal_dfa

References

[1]

Peng, C.; Havlin, S.; Stanley, H.E.; Goldberger, A.L. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos Interdiscip. J. Nonlinear Sci., 5, 82-87, 1995.

class junifer.markers.complexity.MultiscaleEntropyAUC(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for AUC of multiscale entropy of a time series.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the AUC of multiscale entropy calculation function. For more information, check out junifer.markers.utils._multiscale_entropy_auc. If None, value is set to {“m”: 2, “tol”: 0.5, “scale”: 10} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import MultiscaleEntropyAUC or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, calculate multiscale entropy for each region and calculate the AUC of the entropy curves leading to a region-wise map of the brain [1].

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.entropy_multiscale

References

[1]

Costa, M., Goldberger, A. L., & Peng, C. K. Multiscale entropy analysis of complex physiologic time series. Physical review letters, 89(6), 068102, 2002.

class junifer.markers.complexity.PermEntropy(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for permutation entropy of a time series.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the permutation entropy calculation function. For more information, check out junifer.markers.utils._perm_entropy. If None, value is set to {“m”: 2, “delay”: 1} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import PermEntropy or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, and calculate permutation entropy according to the method outlined in [1].

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.entropy_permutation

References

[1]

Bandt, C., & Pompe, B. (2002) Permutation entropy: a natural complexity measure for time series. Physical review letters, 88(17), 174102.

class junifer.markers.complexity.RangeEntropy(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for range entropy of a time series.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the range entropy calculation function. For more information, check out junifer.markers.utils._range_entropy. If None, value is set to {“m”: 2, “tol”: 0.5, “delay”: 1} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import RangeEntropy or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, and calculate range entropy according to the method outlined in [1].

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.entropy_range

References

[1]

A. Omidvarnia et al. (2018) Range Entropy: A Bridge between Signal Complexity and Self-Similarity. Entropy, vol. 20, no. 12, p. 962, 2018.

class junifer.markers.complexity.RangeEntropyAUC(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for AUC of range entropy values of a time series over r = 0 to 1.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the range entropy calculation function. For more information, check out junifer.markers.utils._range_entropy. If None, value is set to {“m”: 2, “delay”: 1, “n_r”: 10} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import RangeEntropyAUC or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, calculate range entropy according to the method outlined in [1] across the range of tolerance value r from 0 to 1, and compute its area under the curve.

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.entropy_range

References

[1]

A. Omidvarnia et al. (2018) Range Entropy: A Bridge between Signal Complexity and Self-Similarity. Entropy, vol. 20, no. 12, p. 962, 2018.

class junifer.markers.complexity.SampleEntropy(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for sample entropy of a time series.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the sample entropy calculation function. For more information, check out junifer.markers.utils._sample_entropy. If None, value is set to {“m”: 2, “delay”: 1, “tol”: 0.5} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import SampleEntropy or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, and calculate sample entropy [1].

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.entropy_sample

References

[1]

Richman, J., Moorman, J. Physiological time-series analysis using approximate entropy and sample entropy. Am. J. Physiol. Heart Circ. Physiol., 278 (6) (2000), pp. H2039-2049

class junifer.markers.complexity.WeightedPermEntropy(parcellation, agg_method='mean', agg_method_params=None, masks=None, params=None, name=None)¶

Class for weighted permutation entropy of a time series.

Parameters:

parcellationstr or list of str: The name(s) of the parcellation(s). Check valid options by calling junifer.data.parcellations.list_parcellations().
agg_methodstr, optional: The method to perform aggregation using. Check valid options in junifer.stats.get_aggfunc_by_name() (default “mean”).
agg_method_paramsdict, optional: Parameters to pass to the aggregation function. Check valid options in junifer.stats.get_aggfunc_by_name() (default None).
masksstr, dict or list of dict or str, optional: The specification of the masks to apply to regions before extracting signals. Check Using Masks for more details. If None, will not apply any mask (default None).
paramsdict, optional: Parameters to pass to the weighted permutation entropy calculation function. For more information, check out junifer.markers.utils._weighted_perm_entropy. If None, value is set to {“m”: 2, “delay”: 1} (default None).
namestr, optional: The name of the marker. If None, it will use the class name (default None).

Warning

This class is not automatically imported by junifer and requires you to import it explicitly. You can do it programmatically by from junifer.markers.complexity import WeightedPermEntropy or in the YAML by with: junifer.markers.complexity.

compute_complexity(extracted_bold_values)¶

Compute complexity measure.

Take a timeseries of brain areas, and calculate weighted permutation entropy according to the method outlined in [1].

Parameters:

extracted_bold_valuesnumpy.ndarray: The BOLD values extracted via parcel aggregation.

Returns:

numpy.ndarray: The values after computing complexity measure.

See also

neurokit2.entropy_permutation

References

[1]

Fadlallah, B., Chen, B., Keil, A., & Principe, J. (2013) Weighted-permutation entropy: A complexity measure for time series incorporating amplitude information. Physical Review E, 87(2), 022911.