Merge pull request #31 from pgleeson/main

Much improved cell pages & add Britten conatactome data

.gitignore

@@ -669,3 +669,6 @@ __pycache__
 /docs/vspR.md
 /docs/vsrL.md
 /docs/vsrR.md
+/docs/Brittin*_data*.md
+/docs/assets/Brittin2021*
+/docs/*_Brittin2021_data*.md

cect/BrittinDataReader.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+
+############################################################
+
+#    A script to read the values from Brittin et al 2021
+
+############################################################
+
+
+from cect.ConnectomeReader import ConnectionInfo
+from cect.ConnectomeReader import analyse_connections
+
+from cect.ConnectomeDataset import ConnectomeDataset
+from cect.ConnectomeDataset import get_dataset_source_on_github
+
+import os
+from openpyxl import load_workbook
+
+from cect import print_
+
+
+spreadsheet_location = os.path.dirname(os.path.abspath(__file__)) + "/data/"
+
+filename = "%s41586_2021_3284_MOESM5_ESM.xlsx" % spreadsheet_location
+
+READER_DESCRIPTION = (
+    """Data extracted from %s for membrane contact information."""
+    % get_dataset_source_on_github(filename.split("/")[-1])
+)
+
+
+class BrittinDataReader(ConnectomeDataset):
+    """Reader for datasets from [Brittin et al. 2021](../../Brittin_2021.md)"""
+
+    verbose = False
+
+    def __init__(self, reference_graph):
+        ConnectomeDataset.__init__(self)
+        self.reference_graph = reference_graph
+
+        cells, neuron_conns = self.read_data()
+        for conn in neuron_conns:
+            self.add_connection_info(conn)
+
+    def read_data(self):
+        cells = []
+        conns = []
+
+        wb = load_workbook(filename)
+
+        sheet = wb.get_sheet_by_name(self.reference_graph)
+
+        print_("Opened sheet %s in Excel file: %s" % (sheet, filename))
+        print(dir(sheet))
+
+        for row in sheet.rows:
+            print(row[0].value)
+            if "cell_1" not in row[0].value:
+                delta = int(row[3].value)
+                if delta == 4:
+                    pre = row[0].value
+                    post = row[1].value
+                    num = float(row[2].value)
+                    syntype = "Contact"
+                    synclass = "%s%s" % (self.reference_graph, row[3].value)
+                    synclass = "Contact"
+                    ci = ConnectionInfo(pre, post, num, syntype, synclass)
+                    print("Adding  %s" % ci)
+                    conns.append(ci)
+
+                    if pre not in cells:
+                        cells.append(pre)
+                    if post not in cells:
+                        cells.append(post)
+
+        return cells, conns
+
+
+def get_instance():
+    return BrittinDataReader("M")
+
+
+my_instance = get_instance()
+
+if __name__ == "__main__":
+    wdr = get_instance()
+
+    cells, neuron_conns = wdr.read_data()
+    neurons2muscles, muscles, muscle_conns = wdr.read_muscle_data()
+
+    analyse_connections(cells, neuron_conns, neurons2muscles, muscles, muscle_conns)

cect/CellInfo.py

@@ -147,15 +147,14 @@ def generate_cell_info_pages(connectomes):
 
         cell_info = '---\ntitle: "Cell: %s"\n---\n\n' % cell
 
+        cell_ref = (
+            cell
+            if not ((cell.startswith("CA") or cell.startswith("CP")) and cell[2] == "0")
+            else "%s%s" % (cell[:2], cell[-1])
+        )  # CA04 -> CA4 etc.
+
         # TODO: investigate  DX1, DX2, DX3, EF1, EF2, EF3
         if is_any_neuron(cell) and "DX" not in cell and "EF" not in cell:
-            cell_ref = (
-                cell
-                if not (
-                    (cell.startswith("CA") or cell.startswith("CP")) and cell[2] == "0"
-                )
-                else "%s%s" % (cell[:2], cell[-1])
-            )  # CA04 -> CA4 etc.
             acronym = cell_data[cell_ref][0]
             lineage = cell_data[cell_ref][1]
             desc = cell_data[cell_ref][2]
@@ -186,15 +185,25 @@ def generate_cell_info_pages(connectomes):
                     cell,
                     get_cell_notes(cell),
                     cell_data[cell_ref][0],
-                    cell_data[cell_ref][1],
-                    cell_data[cell_ref][2],
+                    lineage,
+                    desc,
                 ]
             )
 
         else:
             cell_info += '!!! question "**%s: %s**"\n\n' % (cell, get_cell_notes(cell))
+            cc = cell_classification[cell]
             all_cell_info.append(
-                [cell, get_cell_notes(cell), cell_data[cell_ref][0], '""', '""', '""']
+                [
+                    cell,
+                    get_cell_notes(cell),
+                    cell_data[cell_ref][0]
+                    if cell_ref in cell_data
+                    else "- To be added... - ",
+                    get_cell_notes(cell),
+                    "- To be added... - ",
+                    cc[0].upper() + cc[1:],
+                ]
             )
 
         cell_info += (
@@ -401,33 +410,51 @@ def generate_cell_info_pages(connectomes):
 
 
 if __name__ == "__main__":
-    from cect.White_whole import get_instance
+    import sys
+
+    if "-i" in sys.argv:
+        from cect.Cells import ALL_PREFERRED_NEURON_NAMES
+        from cect.Cells import PREFERRED_MUSCLE_NAMES
+        from cect.Cells import ALL_NON_NEURON_MUSCLE_CELLS
+
+        print("    - 'Individual neurons': ")
+        for cell in sorted(ALL_PREFERRED_NEURON_NAMES):
+            print(f"      - '{cell}': '{cell}.md'")
+        print("    - 'Individual muscles': ")
+        for cell in sorted(PREFERRED_MUSCLE_NAMES, key=lambda v: v.upper()):
+            print(f"      - '{cell}': '{cell}.md'")
+        print("    - 'Other cells': ")
+        for cell in sorted(ALL_NON_NEURON_MUSCLE_CELLS, key=lambda v: v.upper()):
+            print(f"      - '{cell}': '{cell}.md'")
 
-    cds_white = get_instance()
+    else:
+        from cect.White_whole import get_instance
 
-    from cect.WitvlietDataReader8 import get_instance
+        cds_white = get_instance()
 
-    cds_w8 = get_instance()
+        from cect.WitvlietDataReader8 import get_instance
 
-    connectomes = {"White_whole": cds_white, "Witvliet8": cds_w8}
+        cds_w8 = get_instance()
 
-    from cect.Cook2019HermReader import get_instance
+        connectomes = {"White_whole": cds_white, "Witvliet8": cds_w8}
 
-    connectomes["Cook2019Herm"] = get_instance()
+        from cect.Cook2019HermReader import get_instance
 
-    from cect.Cook2019MaleReader import get_instance
+        connectomes["Cook2019Herm"] = get_instance()
 
-    connectomes["Cook2019Male"] = get_instance()
+        from cect.Cook2019MaleReader import get_instance
 
-    """
-    from cect.WormNeuroAtlasMAReader import get_instance
-    connectomes['Bentley2016_MA'] = get_instance()
+        connectomes["Cook2019Male"] = get_instance()
+
+        """
+        from cect.WormNeuroAtlasMAReader import get_instance
+        connectomes['Bentley2016_MA'] = get_instance()
 
-    from cect.WormNeuroAtlasFuncReader import get_instance
-    connectomes['Randi2023'] = get_instance()
+        from cect.WormNeuroAtlasFuncReader import get_instance
+        connectomes['Randi2023'] = get_instance()
 
-    from cect.RipollSanchezShortRangeReader import get_instance
-    connectomes['RipollSanchezShortRange'] = get_instance() """
+        from cect.RipollSanchezShortRangeReader import get_instance
+        connectomes['RipollSanchezShortRange'] = get_instance() """
 
-    # load_individual_neuron_info()
-    generate_cell_info_pages(connectomes)
+        # load_individual_neuron_info()
+        generate_cell_info_pages(connectomes)

cect/Cells.py

@@ -668,14 +668,15 @@ def get_cell_notes(cell):
 
 MOTORNEURONS_COOK = MOTORNEURONS_NONPHARYNGEAL_COOK + PHARYNGEAL_MOTORNEURONS
 
-PREFERRED_NEURON_NAMES_COOK = (
+PREFERRED_HERM_NEURON_NAMES_COOK = (
     INTERNEURONS_COOK
     + SENSORY_NEURONS_COOK
     + MOTORNEURONS_COOK
     + PHARYNGEAL_POLYMODAL_NEURONS
     + UNKNOWN_FUNCTION_NEURONS
 )
 
+ALL_NEURON_NAMES_COOK = PREFERRED_HERM_NEURON_NAMES_COOK + MALE_SPECIFIC_NEURONS
 
 COOK_GROUPING_1 = {
     "Pharyngeal neurons": PHARYNGEAL_NEURONS,
@@ -991,13 +992,13 @@ def get_cell_notes(cell):
 ]
 
 for n in PREFERRED_HERM_NEURON_NAMES:
-    assert n in PREFERRED_NEURON_NAMES_COOK
+    assert n in PREFERRED_HERM_NEURON_NAMES_COOK
 
-for n in PREFERRED_NEURON_NAMES_COOK:
+for n in PREFERRED_HERM_NEURON_NAMES_COOK:
     assert n in PREFERRED_HERM_NEURON_NAMES
 
-assert len(PREFERRED_NEURON_NAMES_COOK) == len(PREFERRED_HERM_NEURON_NAMES)
-assert len(PREFERRED_NEURON_NAMES_COOK) == 302
+assert len(PREFERRED_HERM_NEURON_NAMES_COOK) == len(PREFERRED_HERM_NEURON_NAMES)
+assert len(PREFERRED_HERM_NEURON_NAMES_COOK) == 302
 
 BODY_WALL_MUSCLE_NAMES = [
     "MDL01",
@@ -1447,9 +1448,8 @@ def get_cell_notes(cell):
 cell_notes["int"] = "intestine"
 
 
-KNOWN_OTHER_CELLS_COOK_19 = (
-    []
-    + GLIAL_CELLS
+KNOWN_HERM_NON_NEURON_MUSCLE_CELLS_COOK_19 = (
+    GLIAL_CELLS
     + PHARYNGEAL_MARGINAL_CELLS
     + PHARYNGEAL_EPITHELIUM
     + PHARYNGEAL_GLIAL_CELL
@@ -1461,15 +1461,24 @@ def get_cell_notes(cell):
     + INTESTINE
 )
 
-COOK_GROUPING_1["Other cells"] = list(KNOWN_OTHER_CELLS_COOK_19)
+COOK_GROUPING_1["Other cells"] = list(KNOWN_HERM_NON_NEURON_MUSCLE_CELLS_COOK_19)
 
+"""
 KNOWN_OTHER_CELLS = KNOWN_OTHER_CELLS_COOK_19
 
+
 KNOWN_OTHER_CELLS += (
     MALE_SPECIFIC_NEURONS
     + MALE_RAY_STRUCTURAL_CELLS
     + PROCTODEUM_CELL_MALE
     + GONAD_CELL_MALE
+)"""
+
+ALL_NON_NEURON_MUSCLE_CELLS = (
+    KNOWN_HERM_NON_NEURON_MUSCLE_CELLS_COOK_19
+    + MALE_RAY_STRUCTURAL_CELLS
+    + PROCTODEUM_CELL_MALE
+    + GONAD_CELL_MALE
 )
 
 COOK_GROUPING_1["Male specific neurons"] = MALE_SPECIFIC_NEURONS
@@ -1480,8 +1489,11 @@ def get_cell_notes(cell):
     MALE_RAY_STRUCTURAL_CELLS + PROCTODEUM_CELL_MALE + GONAD_CELL_MALE
 )
 
+ALL_PREFERRED_NEURON_NAMES = PREFERRED_HERM_NEURON_NAMES + MALE_SPECIFIC_NEURONS
+
+
 ALL_PREFERRED_CELL_NAMES = (
-    PREFERRED_HERM_NEURON_NAMES + PREFERRED_MUSCLE_NAMES + KNOWN_OTHER_CELLS
+    ALL_PREFERRED_NEURON_NAMES + PREFERRED_MUSCLE_NAMES + ALL_NON_NEURON_MUSCLE_CELLS
 )
 
 

cect/Comparison.py

@@ -22,6 +22,7 @@
     "Cook2019Herm": "Cook2019Herm_data",
     "Cook2019Male": "Cook2019Male_data",
     "Cook2020": "Cook2020_data",
+    "Brittin2021": "Brittin2021_data",
     "Witvliet1": "Witvliet1_data",
     "Witvliet2": "Witvliet2_data",
     "Witvliet3": "Witvliet3_data",
@@ -169,6 +170,8 @@ def generate_comparison_page(quick: bool, color_table=True):
 
     readers["Cook2020"] = ["cect.Cook2020DataReader", "Cook_2020"]
 
+    readers["Brittin2021"] = ["cect.BrittinDataReader", "Brittin_2021"]
+
     if not quick:
         readers["Witvliet1"] = ["cect.WitvlietDataReader1", "Witvliet_2021"]
         readers["Witvliet2"] = ["cect.WitvlietDataReader2", "Witvliet_2021"]