Merge pull request #671 from populationgenomics/dev

Release

scripts/parse_existing_cohort.py

@@ -111,6 +111,7 @@ def __init__(
         batch_number,
         include_participant_column,
         allow_missing_files,
+        sequencing_type,
     ):
         if include_participant_column:
             participant_column = Columns.PARTICIPANT_COLUMN
@@ -131,6 +132,7 @@ def __init__(
             assay_meta_map=Columns.sequence_meta_map(),
             batch_number=batch_number,
             allow_extra_files_in_search_path=True,
+            default_sequencing_type=sequencing_type,
         )
 
     def _get_dict_reader(self, file_pointer, delimiter: str):
@@ -210,6 +212,11 @@ def get_existing_external_sequence_ids(self, participant_map: dict[str, dict]):
     '--project',
     help='The metamist project to import manifest into',
 )
+@click.option(
+    '--sequencing-type',
+    type=click.Choice(['genome', 'exome']),
+    help='Sequencing type: genome or exome',
+)
 @click.option('--search-location', 'search_locations', multiple=True)
 @click.option(
     '--confirm', is_flag=True, help='Confirm with user input before updating server'
@@ -236,6 +243,7 @@ async def main(
     dry_run=False,
     include_participant_column=False,
     allow_missing_files=False,
+    sequencing_type: str = 'genome',
 ):
     """Run script from CLI arguments"""
 
@@ -245,6 +253,7 @@ async def main(
         batch_number=batch_number,
         include_participant_column=include_participant_column,
         allow_missing_files=allow_missing_files,
+        sequencing_type=sequencing_type,
     )
 
     for manifest_path in manifests:

test/test_parse_existing_cohort.py

@@ -45,6 +45,7 @@ async def test_single_row(
             search_locations=[],
             project=self.project_name,
             allow_missing_files=False,
+            sequencing_type='genome',
         )
 
         parser.filename_map = {
@@ -116,6 +117,7 @@ async def test_no_header(self):
             search_locations=[],
             project=self.project_name,
             allow_missing_files=False,
+            sequencing_type='genome',
         )
 
         parser.filename_map = {
@@ -217,6 +219,7 @@ async def test_existing_row(
             search_locations=[],
             project=self.project_name,
             allow_missing_files=False,
+            sequencing_type='genome',
         )
 
         parser.filename_map = {
@@ -248,6 +251,7 @@ async def test_get_read_filenames_no_reads_fail(self):
             search_locations=[],
             project=self.project_name,
             allow_missing_files=False,
+            sequencing_type='genome',
         )
         parser.filename_map = {}
 
@@ -268,6 +272,7 @@ async def test_get_read_filenames_no_reads_pass(self):
             search_locations=[],
             project=self.project_name,
             allow_missing_files=True,
+            sequencing_type='genome',
         )
         parser.filename_map = {}
 
@@ -280,3 +285,117 @@ async def test_get_read_filenames_no_reads_pass(self):
         self.assertIn('No read files found for ', cm.output[0])
 
         self.assertEqual(len(read_filenames), 0)
+
+    @run_as_sync
+    async def test_genome_sequencing_type(self):
+        """Test that the sequencing type is set correctly when the --sequencing-type flag is set to 'genome''"""
+
+        # Test with 'genome'
+        parser = ExistingCohortParser(
+            include_participant_column=False,
+            batch_number='M01',
+            search_locations=[],
+            project=self.project_name,
+            allow_missing_files=True,
+            sequencing_type='genome',
+        )
+        self.assertEqual(parser.default_sequencing_type, 'genome')
+
+    @run_as_sync
+    async def test_exome_sequencing_type(self):
+        """Test that the sequencing type is set correctly when the --sequencing-type flag is set to 'exome'"""
+
+        # Test with 'exome'
+        parser = ExistingCohortParser(
+            include_participant_column=False,
+            batch_number='M01',
+            search_locations=[],
+            project=self.project_name,
+            allow_missing_files=True,
+            sequencing_type='exome',
+        )
+        self.assertEqual(parser.default_sequencing_type, 'exome')
+
+    @run_as_sync
+    @patch('metamist.parser.generic_parser.query_async')
+    @patch('metamist.parser.cloudhelper.CloudHelper.datetime_added')
+    @patch('metamist.parser.cloudhelper.CloudHelper.file_exists')
+    @patch('metamist.parser.cloudhelper.CloudHelper.file_size')
+    async def test_sequencing_type_in_assay_meta(
+        self,
+        mock_filesize,
+        mock_fileexists,
+        mock_datetime_added,
+        mock_graphql_query,
+    ):
+        """Test that the sequencing type is set correctly when the --sequencing-type flag is set to 'genome' or 'exome'"""
+
+        mock_graphql_query.side_effect = self.run_graphql_query_async
+
+        mock_filesize.return_value = 111
+        mock_fileexists.return_value = False
+        mock_datetime_added.return_value = datetime.fromisoformat('2022-02-02T22:22:22')
+
+        rows = [
+            'HEADER',
+            '""',
+            'Application\tExternal ID\tSample Concentration (ng/ul)\tVolume (uL)\tSex\tSample/Name\tReference Genome\tParticipant ID\t',
+            'App\tEXTID1234\t100\t100\tFemale\t220405_FLUIDX1234\thg38\tPID123',
+        ]
+
+        for sequencing_type in ['genome', 'exome']:
+            with self.subTest(sequencing_type=sequencing_type):
+                parser = ExistingCohortParser(
+                    include_participant_column=False,
+                    batch_number='M01',
+                    search_locations=[],
+                    project=self.project_name,
+                    allow_missing_files=False,
+                    sequencing_type=sequencing_type,
+                )
+                parser.filename_map = {
+                    'HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R1.fastq': '/path/to/HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R1.fastq',
+                    'HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R2.fastq': '/path/to/HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R2.fastq',
+                }
+
+                file_contents = '\n'.join(rows)
+                participants: list[ParsedParticipant]
+                _, participants = await parser.parse_manifest(
+                    StringIO(file_contents), delimiter='\t', dry_run=True
+                )
+
+                sample_to_add = participants[0].samples[0]
+                expected_sequence_dict = {
+                    'reference_genome': 'hg38',
+                    'platform': 'App',
+                    'concentration': '100',
+                    'volume': '100',
+                    'fluid_x_tube_id': '220405_FLUIDX1234',
+                    'reads_type': 'fastq',
+                    'reads': [
+                        {
+                            'location': '/path/to/HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R1.fastq',
+                            'basename': 'HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R1.fastq',
+                            'class': 'File',
+                            'checksum': None,
+                            'size': 111,
+                            'datetime_added': '2022-02-02T22:22:22',
+                        },
+                        {
+                            'location': '/path/to/HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R2.fastq',
+                            'basename': 'HG3F_2_220405_FLUIDX1234_Homo-sapiens_AAC-TAT_R_220208_VB_BLAH_M002_R2.fastq',
+                            'class': 'File',
+                            'checksum': None,
+                            'size': 111,
+                            'datetime_added': '2022-02-02T22:22:22',
+                        },
+                    ],
+                    'sequencing_platform': 'illumina',
+                    'sequencing_technology': 'short-read',
+                    'sequencing_type': f'{sequencing_type}',
+                    'batch': 'M01',
+                }
+                assay = sample_to_add.sequencing_groups[0].assays[0]
+                self.maxDiff = None
+                self.assertDictEqual(expected_sequence_dict, assay.meta)
+        return

web/src/pages/billing/BillingInvoiceMonthCost.tsx

@@ -169,7 +169,7 @@ const BillingCurrentCost = () => {
         const year = invoiceMonth.substring(0, 4)
         const month = invoiceMonth.substring(4, 6)
         let nextYear = year
-        let nextMonth = (parseInt(month, 10) + 1).toString()
+        let nextMonth = (parseInt(month, 10) + 1).toString().padStart(2, '0')
         if (month === '12') {
             nextYear = (parseInt(year, 10) + 1).toString()
             nextMonth = '01'

web/src/shared/components/Graphs/DonutChart.tsx

@@ -79,14 +79,15 @@ export const DonutChart: React.FC<IDonutChartProps> = ({ data, maxSlices, colors
     const margin = 15
     const radius = Math.min(width, height) / 2 - margin
 
-    // keep order of the slices
+    // keep order of the slices, declare custom sort function to keep order of slices as passed in
+    // by default pie function starts from index 1 and sorts by value
     const pieFnc = pie()
         .value((d) => d.value)
         .sort((a) => {
             if (typeof a === 'object' && a.type === 'inc') {
                 return 1
             }
-            return -1
+            return 0 // works both on Safari and Firefox, any other value will break one of them
         })
     const data_ready = pieFnc(data)
     const innerRadius = radius / 1.75 // inner radius of pie, in pixels (non-zero for donut)