Merge pull request #167 from apriltuesday/submission-fixes

Fixes from submission processing
EBIvariation · Aug 7, 2023 · c65adb5 · c65adb5
2 parents 832aca3 + e199906
commit c65adb5
Show file tree

Hide file tree

Showing 5 changed files with 14 additions and 9 deletions.
diff --git a/eva_submission/eload_preparation.py b/eva_submission/eload_preparation.py
@@ -103,7 +103,7 @@ def check_submitted_filenames(self):
                        f'{", ".join(set(submitted_vcfs).difference(set(spreadsheet_vcfs)))}')
             analysis_alias = ''
             if len(eva_xls_reader.analysis) == 1:
-                analysis_alias = self._unique_alias(eva_xls_reader.analysis[0].get('Analysis Alias')) or ''
+                analysis_alias = eva_xls_reader.analysis[0].get('Analysis Alias') or ''
             elif len(eva_xls_reader.analysis) > 1:
                 self.error("Multiple analyses found, can't add submitted VCF to spreadsheet")
                 raise ValueError("Multiple analyses found, can't add submitted VCF to spreadsheet")

diff --git a/eva_submission/eload_submission.py b/eva_submission/eload_submission.py
@@ -151,11 +151,19 @@ def update_metadata_spreadsheet(self, input_spreadsheet, output_spreadsheet=None
         elif self.eload not in project_row['Project Alias']:
             # Add the eload id to ensure that the project alias is unique
             project_row['Project Alias'] = self._unique_alias(project_row['Project Alias'])
+
+        analysis_rows = reader.analysis
+        for analysis_row in analysis_rows:
+            if self.eload not in analysis_row['Analysis Alias']:
+                # Add the eload id to ensure that the analysis alias is unique
+                analysis_row['Analysis Alias'] = self._unique_alias(analysis_row['Analysis Alias'])
+
         if output_spreadsheet:
             eva_xls_writer = EvaXlsxWriter(input_spreadsheet, output_spreadsheet)
         else:
             eva_xls_writer = EvaXlsxWriter(input_spreadsheet)
         eva_xls_writer.set_project(project_row)
+        eva_xls_writer.set_analysis(analysis_rows)
         eva_xls_writer.set_samples(sample_rows)
         eva_xls_writer.set_files(file_rows)
         eva_xls_writer.save()

diff --git a/eva_submission/eload_validation.py b/eva_submission/eload_validation.py
@@ -1,11 +1,8 @@
 #!/usr/bin/env python
-import copy
 import csv
 import os
-import re
 import shutil
 import subprocess
-import gzip
 
 import yaml
 from ebi_eva_common_pyutils import command_utils

diff --git a/eva_submission/nextflow/prepare_brokering.nf b/eva_submission/nextflow/prepare_brokering.nf
@@ -140,7 +140,7 @@ process normalise_vcf {
     trap 'if [[ \$? == 1 || \$? == 139 || \$? == 255 ]]; then exit 0; fi' EXIT
 
     mkdir normalised_vcfs
-    $params.executable.bcftools norm --no-version -f $fasta -O z -o normalised_vcfs/$vcf_file $vcf_file 2> normalised_vcfs/${vcf_file.getBaseName()}_bcftools_norm.log
+    $params.executable.bcftools norm --no-version -cw -f $fasta -O z -o normalised_vcfs/$vcf_file $vcf_file 2> normalised_vcfs/${vcf_file.getBaseName()}_bcftools_norm.log
     $params.executable.bcftools index -c normalised_vcfs/$vcf_file
     """
 }

diff --git a/tests/test_vep_utils.py b/tests/test_vep_utils.py
@@ -63,10 +63,10 @@ def fake_dir(path, callback):
 
     def test_get_vep_versions_from_ensembl(self):
         vep_version, cache_version = get_vep_and_vep_cache_version_from_ensembl('GCA_000827895.1')
-        self.assertEqual(vep_version, 109)
-        self.assertEqual(cache_version, 56)
+        self.assertEqual(vep_version, 110)
+        self.assertEqual(cache_version, 57)
         assert os.path.exists(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei'))
-        assert os.listdir(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei')) == ['56_ASM82789v1']
+        assert os.listdir(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei')) == ['57_ASM82789v1']
 
     def test_get_vep_versions_from_ensembl_not_found(self):
         vep_version, cache_version = get_vep_and_vep_cache_version_from_ensembl('GCA_015220235.1')
@@ -133,7 +133,7 @@ def test_get_species_and_assembly(self):
             'GCA_000001405.1': ('homo_sapiens', 'GRCh37', False, '9606'),
             'GCA_000001405.14': ('homo_sapiens', 'GRCh37.p13', False, '9606'),
             'GCA_000001405.20': ('homo_sapiens', 'GRCh38.p5', False, '9606'),
-            'GCA_000001405.28': ('homo_sapiens', 'GRCh38.p13', True, '9606'),
+            'GCA_000001405.29': ('homo_sapiens', 'GRCh38.p14', True, '9606'),
             'GCA_000001635.2': ('mus_musculus', 'GRCm38', False, '10090'),
             'GCA_000002285.2': ('canis_lupus_familiaris', 'CanFam3.1', False, '9615'),
             'GCA_000002315.5': ('gallus_gallus', 'GRCg6a', True, '9031'),