Merge pull request #130 from eastgenomics/v2.3.0-release

v2.3.0 release (#130)

Co-Authored-By: Yu-jinKim <yujin.kim@hotmail.fr>
Co-Authored-By: mattgarner <mattgarner@users.noreply.github.com>

Readme.md

@@ -57,6 +57,21 @@ This app may be executed as a standalone app.
 
 `--additional_sheet_names` (`list`): Names to use for additional file sheets, if specified these MUST be the same number as the number of files passed and in the same order (`-iadditional_files=file1 -iadditional_files=file2 -iadditional_sheet_names='name_1 name_2'`). If not given, the first 31 characters of the filename will be used.
 
+`--colour_cells` (`string`): Add conditional colouring of cells for a given column, this should be specified as column:value_range:colour, where colour is a valid hex value or colour name. Multiple conditions may be given in a single `value_range` for the same column and colour values by chaining multiple with either `&` for all or `|` for any condition (n.b. `&` and `|` cannot be used in the same expression). Column names should be given as they appear in the VCF, except for cases where renaming has been specified with `--rename`, in which case the given column name should be used. Example formats:
+```
+  # single condition
+  -icolour_cells "VF:>=0.9:green"
+
+  # both of two conditions
+  -icolour_cells "VF:<0.8&>=0.6:orange"
+
+  # either of two conditions
+  -icolour_cells "VF:>0.9|<0.1:red"
+
+  # multiple conditions to colour column across multiple ranges and colours
+  -icolour_cells "VF:>=0.9:green VF:<0.9&>=0.4:orange VF:>0.4:red"
+```
+
 `--output_prefix` (`string`): Prefix for naming output xlsx file. If not given for single file, the VCF prefix will be used. For 2+ input VCFs this must be specified.
 
 `--merge_vcfs` (`bool`): Determines if to merge multiple VCFs to one sheet (default: `False`).

dxapp.json

@@ -3,16 +3,17 @@
   "title": "eggd_generate_variant_workbook",
   "summary": "Create Excel workbook from VEP annotated vcf",
   "dxapi": "1.0.0",
-  "version": "2.2.0",
+  "version": "2.3.0",
+  "properties": {
+    "githubRelease": "v2.3.0"
+  },
+  "whatsNew": "* v2.0.0 Rewrite of previous app to generate xlsx file from a VEP annotated VCF(s); * v2.0.1 Bug fix to correctly treat CHROM as string values; * v2.0.2 Bug fix for ACMG report template structure; * v2.0.3 Bug fixes for issues with hyperlinks, changed app name to eggd_generate_variant_workbook; * v2.1.0 Handle VCFs from GATK gCNV and Illumina TSO500, readability tweaks to variant sheets; * v2.1.1 Bug fix for typing of numeric values in hyperlinks; * v2.2.0 Added ability to pass in non VCF files (tsvs/csvs and images) to additional sheets, optional adding of links to DECIPHER with --decipher; * v2.3.0 Added conditional colouring of cells in variant sheets, new 'basic' summary sheet;",
   "authorizedUsers": [
     "org-emee_1"
   ],
   "developers":[
     "org-emee_1"
   ],
-  "properties": {
-    "githubRelease": "v2.2.0"
-  },
   "inputSpec": [
     {
       "name": "vcfs",
@@ -159,6 +160,14 @@
       "help": "Prefix for naming output xlsx file",
       "group": "generate_workbook.py"
     },
+    {
+      "name": "colour_cells",
+      "label": "colour cells",
+      "class": "string",
+      "optional": true,
+      "help": "Add conditional colouring of cells for a given column, this should be specified as column:value_range:colour, where colour is a valid hex value or colour name. See readme for futher details.",
+      "group": "generate_workbook.py"
+    },
     {
       "name": "merge_vcfs",
       "label": "Merge",

requirements.txt

@@ -1,3 +1,4 @@
+colour==0.1.5
 python-Levenshtein==0.12.2
 openpyxl==3.0.9
 pandas==1.3.5

resources/home/dnanexus/generate_workbook/generate_workbook.py

@@ -27,6 +27,7 @@ def __init__(self):
         self.set_sheet_names()
         self.verify_sheets()
         self.verify_images()
+        self.verify_colours()
 
         print(f"Arguments passed: ", ''.join([
             f"\n\t\t{' : '.join((str(x), str(self.args.__dict__[x])))}"
@@ -264,14 +265,21 @@ def parse_args(self) -> argparse.Namespace:
                 'before writing to the Excel file.'
             )
         )
-
         parser.add_argument(
             '--decipher', required=False, action='store_true',
             help=(
                 'Determines whether or not to include column of DECIPHER links'
                 'n.b. DECIPHER is only available for variants in build 38 '
             )
         )
+        parser.add_argument(
+            '--colour', required=False, nargs='+',
+            help=(
+                'Add conditional colouring of cells for a given column, this '
+                'should be specified as column:value_range:colour, where '
+                'colour is a valid hex value or colour name'
+            )
+        )
 
         return parser.parse_args()
 
@@ -347,6 +355,7 @@ def verify_sheets(self) -> None:
                 f"of sheet names passed: {len(self.args.additional_sheets)}"
             )
 
+
     def verify_images(self) -> None:
         """
         Checks where images with names and / or sizes are passed that
@@ -394,6 +403,27 @@ def verify_images(self) -> None:
             )
 
 
+    def verify_colours(self) -> None:
+        """
+        Checks when colouring for cells specified with --colour that
+        the arguments passed are do not contain both & and |
+
+        Raises
+        ------
+        AssertionError
+            raised when a mix of '&' and '|' are used in the same condition
+        """
+        if not self.args.colour:
+            return
+
+        assert max([
+            len(set(re.findall(r'[&|]', x))) for x in self.args.colour
+        ]) <= 1, (
+            'invalid colouring expression - can not contain both & and | in '
+            'a single expression'
+        )
+
+
     def set_sheet_names(self) -> None:
         """
         Sets list of names for naming output sheets in Excel file

resources/home/dnanexus/generate_workbook/tests/test_generate_workbook.py

@@ -71,3 +71,38 @@ def test_invalid_image_sizes(self):
             self.args_obj.verify_images()
 
         self.args_obj.args.image_sheets = None
+
+
+class TestVerifyColours():
+    """
+    Tests for generate_workbook.verify_colours to check for valid
+    colouring expressions being given
+    """
+    with patch("sys.argv", []):
+        args_obj = object.__new__(arguments)
+        args_obj.args = args_obj.parse_args()
+
+
+    def test_valid_colour_expressions(self):
+        """
+        Test a range of valid expressions pass the check
+        """
+        self.args_obj.args.colour = [
+            'VF:>=0.9:green',
+            'VF:>0.4:red',
+            'VF:<0.9&>=0.4:orange',
+            'Consequence:=synonymous_variant|=upstream_variant:green'
+        ]
+
+        self.args_obj.verify_colours()
+
+
+    def test_invalid_colour_expression(self):
+        """
+        Test that the assertion in verify_colours() is correctly
+        raised if both & and | are used in the same expression
+        """
+        self.args_obj.args.colour = ['VF:<0.9&>=0.4|<1:orange']
+
+        with pytest.raises(AssertionError):
+            self.args_obj.verify_colours()