junifer 0.0.5.dev93__tar.gz → 0.0.5.dev110__tar.gz

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.5.dev93
+Version: 0.0.5.dev110
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>

junifer-0.0.5.dev110/docs/changes/newsfragments/345.feature

@@ -0,0 +1 @@
+Allow Unix path expansion directives to be used in :class:`.PatternDataGrabber` ``patterns`` by `Synchon Mandal`_

junifer-0.0.5.dev110/docs/changes/newsfragments/346.enh

@@ -0,0 +1 @@
+Adapt :class:`.DataladAOMICID1000`, :class:`.DataladAOMICPIOP1` and :class:`.DataladAOMICPIOP2` to support ``FreeSurfer`` data type by `Synchon Mandal`_

junifer-0.0.5.dev110/docs/changes/newsfragments/346.feature

@@ -0,0 +1 @@
+Add support for ``FreeSurfer`` data type for :class:`.PatternDataGrabber` by `Synchon Mandal`_

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/docs/extending/datagrabber.rst

@@ -314,6 +314,53 @@ This approach can be used directly from the YAML, like so:
      uri: "https://gin.g-node.org/juaml/datalad-example-bids"
      rootdir: example_bids_ses
 
+Advanced: Using Unix-like path expansion directives
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is also possible to use some advanced Unix-like path expansion tricks to
+define our patterns.
+
+A very common thing would be to use ``*`` to match any number of
+characters but we cannot use it right after a replacement like:
+
+.. code-block:: python
+
+    "derivatives/freesurfer/{subject}*"
+
+or if there are multiple files or no files which can be globbed.
+
+We can also use ``[]`` and ``[!]`` to glob certain tricky files like with the
+case of FreeSurfer derivatives. The file structure seen in a typical
+FreeSurfer derivative of a dataset (like ``AOMIC`` ones) is like so:
+
+.. code-block::
+
+      .
+      └── derivatives
+          └── freesurfer
+             ├── fsaverage
+             │   ├── mri
+             │   |   ├── T1.mgz
+             │   |   └── ...
+             │   └── ...
+             ├── sub-01
+             │   ├── mri
+             │   |   ├── T1.mgz
+             │   |   └── ...
+             │   |   └── ...
+             │   └── ...
+             ...
+
+With a structure like this, it would be cumbersome to write custom methods
+for the class and thus we could use a pattern like this:
+
+.. code-block:: python
+
+    "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]"
+
+This would ignore the ``fsaverage`` directory as a subject and let ``T1.mgz`` be
+fetched as there can be many files with the same prefix.
+
 .. _extending_datagrabbers_base:
 
 Option B: Extending from BaseDataGrabber

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/docs/understanding/data.rst

@@ -115,6 +115,9 @@ Data Types
    * - ``VBM_WM``
      - VBM White Matter segmentation (3D)
      - CAT output (`m0wp2` images)
+   * - ``VBM_CSF``
+     - VBM Central Spinal Fluid segmentation (3D)
+     - CAT output (`m0wp3` images)
    * - ``fALFF``
      - Voxel-wise fALFF image (3D)
      - fALFF computed with CONN toolbox
@@ -124,3 +127,9 @@ Data Types
    * - ``LCOR``
      - Local Correlation image (3D)
      - LCOR computed with CONN toolbox
+   * - ``DWI``
+     - Diffusion-weighted image (3D)
+     - Diffusion-weighted image (FSL or MRtrix output)
+   * - ``FreeSurfer``
+     - T1 image (3D)
+     - T1 image computed by FreeSurfer

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/junifer/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.5.dev93'
-__version_tuple__ = version_tuple = (0, 0, 5, 'dev93')
+__version__ = version = '0.0.5.dev110'
+__version_tuple__ = version_tuple = (0, 0, 5, 'dev110')

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/junifer/datagrabber/aomic/id1000.py

@@ -24,8 +24,8 @@ class DataladAOMICID1000(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI"} or \
-           list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI", \
+           "FreeSurfer"} or list of the options, optional
         AOMIC data types. If None, all available data types are selected.
         (default None).
     native_t1w : bool, optional
@@ -112,6 +112,39 @@ class DataladAOMICID1000(PatternDataladDataGrabber):
                     "{subject}_desc-preproc_dwi.nii.gz"
                 ),
             },
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+                "norm": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/norm.mg[z]"
+                    )
+                },
+                "lh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.whit[e]"
+                    )
+                },
+                "rh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.whit[e]"
+                    )
+                },
+                "lh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.pia[l]"
+                    )
+                },
+                "rh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.pia[l]"
+                    )
+                },
+            },
         }
         # Use native T1w assets
         self.native_t1w = False

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/junifer/datagrabber/aomic/piop1.py

@@ -26,8 +26,8 @@ class DataladAOMICPIOP1(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI"} or \
-           list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI", \
+           "FreeSurfer"} or list of the options, optional
         AOMIC data types. If None, all available data types are selected.
         (default None).
     tasks : {"restingstate", "anticipation", "emomatching", "faces", \
@@ -147,6 +147,39 @@ class DataladAOMICPIOP1(PatternDataladDataGrabber):
                     "{subject}_desc-preproc_dwi.nii.gz"
                 ),
             },
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+                "norm": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/norm.mg[z]"
+                    )
+                },
+                "lh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.whit[e]"
+                    )
+                },
+                "rh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.whit[e]"
+                    )
+                },
+                "lh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.pia[l]"
+                    )
+                },
+                "rh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.pia[l]"
+                    )
+                },
+            },
         }
         # Use native T1w assets
         self.native_t1w = False

{junifer-0.0.5.dev93 → junifer-0.0.5.dev110}/junifer/datagrabber/aomic/piop2.py

@@ -26,8 +26,8 @@ class DataladAOMICPIOP2(PatternDataladDataGrabber):
         The directory where the datalad dataset will be cloned. If None,
         the datalad dataset will be cloned into a temporary directory
         (default None).
-    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI"} or \
-           list of the options, optional
+    types: {"BOLD", "T1w", "VBM_CSF", "VBM_GM", "VBM_WM", "DWI", \
+           "FreeSurfer"} or list of the options, optional
         AOMIC data types. If None, all available data types are selected.
         (default None).
     tasks : {"restingstate", "stopsignal", "workingmemory"} or \
@@ -144,6 +144,39 @@ class DataladAOMICPIOP2(PatternDataladDataGrabber):
                     "{subject}_desc-preproc_dwi.nii.gz"
                 ),
             },
+            "FreeSurfer": {
+                "pattern": "derivatives/freesurfer/[!f]{subject}/mri/T1.mg[z]",
+                "aseg": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/aseg.mg[z]"
+                    )
+                },
+                "norm": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/mri/norm.mg[z]"
+                    )
+                },
+                "lh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.whit[e]"
+                    )
+                },
+                "rh_white": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.whit[e]"
+                    )
+                },
+                "lh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/lh.pia[l]"
+                    )
+                },
+                "rh_pial": {
+                    "pattern": (
+                        "derivatives/freesurfer/[!f]{subject}/surf/rh.pia[l]"
+                    )
+                },
+            },
         }
         # Use native T1w assets
         self.native_t1w = False

junifer-0.0.5.dev110/junifer/datagrabber/aomic/tests/test_id1000.py

@@ -0,0 +1,124 @@
+"""Provide tests for DataladAOMICID1000 DataGrabber."""
+
+# Authors: Federico Raimondo <f.raimondo@fz-juelich.de>
+#          Vera Komeyer <v.komeyer@fz-juelich.de>
+#          Xuan Li <xu.li@fz-juelich.de>
+#          Leonard Sasse <l.sasse@fz-juelich.de>
+#          Synchon Mandal <s.mandal@fz-juelich.de>
+# License: AGPL
+
+from typing import List, Optional, Union
+
+import pytest
+
+from junifer.datagrabber.aomic.id1000 import DataladAOMICID1000
+
+
+URI = "https://gin.g-node.org/juaml/datalad-example-aomic1000"
+
+
+@pytest.mark.parametrize(
+    "type_, nested_types",
+    [
+        ("BOLD", ["confounds", "mask"]),
+        ("T1w", ["mask"]),
+        ("VBM_CSF", None),
+        ("VBM_GM", None),
+        ("VBM_WM", None),
+        ("DWI", None),
+        ("FreeSurfer", None),
+    ],
+)
+def test_DataladAOMICID1000(
+    type_: str,
+    nested_types: Optional[List[str]],
+) -> None:
+    """Test DataladAOMICID1000 DataGrabber.
+
+    Parameters
+    ----------
+    type_ : str
+        The parametrized type.
+    nested_types : list of str or None
+        The parametrized nested types.
+
+    """
+    dg = DataladAOMICID1000(types=type_)
+    # Set URI to Gin
+    dg.uri = URI
+
+    with dg:
+        # Get all elements
+        all_elements = dg.get_elements()
+        # Get test element
+        test_element = all_elements[0]
+        # Get test element data
+        out = dg[test_element]
+        # Assert data type
+        assert type_ in out
+        assert out[type_]["path"].exists()
+        assert out[type_]["path"].is_file()
+        # Asserts data type metadata
+        assert "meta" in out[type_]
+        meta = out[type_]["meta"]
+        assert "element" in meta
+        assert "subject" in meta["element"]
+        assert test_element == meta["element"]["subject"]
+        # Assert nested data type if not None
+        if nested_types is not None:
+            for nested_type in nested_types:
+                assert out[type_][nested_type]["path"].exists()
+                assert out[type_][nested_type]["path"].is_file()
+
+
+@pytest.mark.parametrize(
+    "types",
+    [
+        "BOLD",
+        "T1w",
+        "VBM_CSF",
+        "VBM_GM",
+        "VBM_WM",
+        "DWI",
+        ["BOLD", "VBM_CSF"],
+        ["T1w", "VBM_CSF"],
+        ["VBM_GM", "VBM_WM"],
+        ["DWI", "BOLD"],
+    ],
+)
+def test_DataladAOMICID1000_partial_data_access(
+    types: Union[str, List[str]],
+) -> None:
+    """Test DataladAOMICID1000 DataGrabber partial data access.
+
+    Parameters
+    ----------
+    types : str or list of str
+        The parametrized types.
+
+    """
+    dg = DataladAOMICID1000(types=types)
+    # Set URI to Gin
+    dg.uri = URI
+
+    with dg:
+        # Get all elements
+        all_elements = dg.get_elements()
+        # Get test element
+        test_element = all_elements[0]
+        # Get test element data
+        out = dg[test_element]
+        # Assert data type
+        if isinstance(types, list):
+            for type_ in types:
+                assert type_ in out
+        else:
+            assert types in out
+
+
+def test_DataladAOMICID1000_incorrect_data_type() -> None:
+    """Test DataladAOMICID1000 DataGrabber incorrect data type."""
+    with pytest.raises(
+        ValueError, match="`patterns` must contain all `types`"
+    ):
+        _ = DataladAOMICID1000(types="Scooby-Doo")

junifer-0.0.5.dev110/junifer/datagrabber/aomic/tests/test_piop1.py

@@ -0,0 +1,166 @@
+"""Provide tests for DataladAOMICPIOP1 DataGrabber."""
+
+# Authors: Federico Raimondo <f.raimondo@fz-juelich.de>
+#          Vera Komeyer <v.komeyer@fz-juelich.de>
+#          Xuan Li <xu.li@fz-juelich.de>
+#          Leonard Sasse <l.sasse@fz-juelich.de>
+#          Synchon Mandal <s.mandal@fz-juelich.de>
+# License: AGPL
+
+from typing import List, Optional, Union
+
+import pytest
+
+from junifer.datagrabber import DataladAOMICPIOP1
+
+
+URI = "https://gin.g-node.org/juaml/datalad-example-aomicpiop1"
+
+
+@pytest.mark.parametrize(
+    "type_, nested_types, tasks",
+    [
+        ("BOLD", ["confounds", "mask"], None),
+        ("BOLD", ["confounds", "mask"], ["anticipation"]),
+        ("BOLD", ["confounds", "mask"], ["emomatching", "faces"]),
+        ("BOLD", ["confounds", "mask"], ["restingstate"]),
+        ("BOLD", ["confounds", "mask"], ["workingmemory", "gstroop"]),
+        (
+            "BOLD",
+            ["confounds", "mask"],
+            ["anticipation", "faces", "restingstate"],
+        ),
+        ("T1w", ["mask"], None),
+        ("VBM_CSF", None, None),
+        ("VBM_GM", None, None),
+        ("VBM_WM", None, None),
+        ("DWI", None, None),
+        ("FreeSurfer", None, None),
+    ],
+)
+def test_DataladAOMICPIOP1(
+    type_: str,
+    nested_types: Optional[List[str]],
+    tasks: Optional[List[str]],
+) -> None:
+    """Test DataladAOMICPIOP1 DataGrabber.
+
+    Parameters
+    ----------
+    type_ : str
+        The parametrized type.
+    nested_types : list of str or None
+        The parametrized nested types.
+    tasks : list of str or None
+        The parametrized task values.
+
+    """
+    dg = DataladAOMICPIOP1(types=type_, tasks=tasks)
+    # Set URI to Gin
+    dg.uri = URI
+
+    with dg:
+        # Get all elements
+        all_elements = dg.get_elements()
+        # Get test element
+        test_element = all_elements[0]
+        # Get test element data
+        out = dg[test_element]
+        # Get all elements
+        all_elements = dg.get_elements()
+        # Get test element
+        test_element = all_elements[0]
+        # Get test element data
+        out = dg[test_element]
+        # Assert data type
+        assert type_ in out
+        # Check task name if BOLD
+        if type_ == "BOLD" and tasks is not None:
+            # Depending on task 'acquisition is different'
+            task_acqs = {
+                "anticipation": "seq",
+                "emomatching": "seq",
+                "faces": "mb3",
+                "gstroop": "seq",
+                "restingstate": "mb3",
+                "workingmemory": "seq",
+            }
+            assert task_acqs[test_element[1]] in out[type_]["path"].name
+        assert out[type_]["path"].exists()
+        assert out[type_]["path"].is_file()
+        # Asserts data type metadata
+        assert "meta" in out[type_]
+        meta = out[type_]["meta"]
+        assert "element" in meta
+        assert "subject" in meta["element"]
+        assert test_element[0] == meta["element"]["subject"]
+        # Assert nested data type if not None
+        if nested_types is not None:
+            for nested_type in nested_types:
+                assert out[type_][nested_type]["path"].exists()
+                assert out[type_][nested_type]["path"].is_file()
+
+
+@pytest.mark.parametrize(
+    "types",
+    [
+        "BOLD",
+        "T1w",
+        "VBM_CSF",
+        "VBM_GM",
+        "VBM_WM",
+        "DWI",
+        ["BOLD", "VBM_CSF"],
+        ["T1w", "VBM_CSF"],
+        ["VBM_GM", "VBM_WM"],
+        ["DWI", "BOLD"],
+    ],
+)
+def test_DataladAOMICPIOP1_partial_data_access(
+    types: Union[str, List[str]],
+) -> None:
+    """Test DataladAOMICPIOP1 DataGrabber partial data access.
+
+    Parameters
+    ----------
+    types : str or list of str
+        The parametrized types.
+
+    """
+    dg = DataladAOMICPIOP1(types=types)
+    # Set URI to Gin
+    dg.uri = URI
+
+    with dg:
+        # Get all elements
+        all_elements = dg.get_elements()
+        # Get test element
+        test_element = all_elements[0]
+        # Get test element data
+        out = dg[test_element]
+        # Assert data type
+        if isinstance(types, list):
+            for type_ in types:
+                assert type_ in out
+        else:
+            assert types in out
+
+
+def test_DataladAOMICPIOP1_incorrect_data_type() -> None:
+    """Test DataladAOMICPIOP1 DataGrabber incorrect data type."""
+    with pytest.raises(
+        ValueError, match="`patterns` must contain all `types`"
+    ):
+        _ = DataladAOMICPIOP1(types="Ceres")
+
+
+def test_DataladAOMICPIOP1_invalid_tasks():
+    """Test DataladAOMICIDPIOP1 DataGrabber invalid tasks."""
+    with pytest.raises(
+        ValueError,
+        match=(
+            "thisisnotarealtask is not a valid task in "
+            "the AOMIC PIOP1 dataset!"
+        ),
+    ):
+        DataladAOMICPIOP1(tasks="thisisnotarealtask")