standardize pipeline options in Load Data UI (#4603)

* fix load data dag parameters * s * a few more * pr comments * oops * more * order on ui
broadinstitute · Jan 23, 2025 · 953453d · 953453d
1 parent cc9e7f8
commit 953453d
Show file tree

Hide file tree

Showing 3 changed files with 14 additions and 3 deletions.
diff --git a/seqr/utils/search/add_data_utils.py b/seqr/utils/search/add_data_utils.py
@@ -115,7 +115,7 @@ def format_loading_pipeline_variables(
 
 def prepare_data_loading_request(projects: list[Project], sample_type: str, dataset_type: str, genome_version: str,
                                  data_path: str, user: User, pedigree_dir: str,  raise_pedigree_error: bool = False,
-                                 individual_ids: list[int] = None, skip_validation: bool = False):
+                                 individual_ids: list[int] = None, skip_validation: bool = False, skip_check_sex_and_relatedness: bool = False):
     variables = format_loading_pipeline_variables(
         projects,
         genome_version,
@@ -125,6 +125,8 @@ def prepare_data_loading_request(projects: list[Project], sample_type: str, data
     )
     if skip_validation:
         variables['skip_validation'] = True
+    if skip_check_sex_and_relatedness:
+        variables['skip_check_sex_and_relatedness'] = True
     file_path = _get_pedigree_path(pedigree_dir, genome_version, sample_type, dataset_type)
     _upload_data_loading_files(projects, user, file_path, individual_ids, raise_pedigree_error)
     return variables, file_path

diff --git a/seqr/views/apis/data_manager_api.py b/seqr/views/apis/data_manager_api.py
@@ -525,7 +525,6 @@ def load_data(request):
     request_json = json.loads(request.body)
     sample_type = request_json['sampleType']
     dataset_type = request_json.get('datasetType', Sample.DATASET_TYPE_VARIANT_CALLS)
-    skip_validation = request_json.get('skipValidation', False)
     projects = [json.loads(project) for project in request_json['projects']]
     project_samples = {p['projectGuid']: p.get('sampleIds') for p in projects}
 
@@ -537,7 +536,11 @@ def load_data(request):
     loading_args = (
         project_models, sample_type, dataset_type, request_json['genomeVersion'], _callset_path(request_json),
     )
-    loading_kwargs = {'user': request.user, 'skip_validation': skip_validation}
+    loading_kwargs = {
+        'user': request.user,
+        'skip_validation': request_json.get('skipValidation', False),
+        'skip_check_sex_and_relatedness': request_json.get('skipSRChecks', False),
+    }
     if AirtableSession.is_airtable_enabled():
         individual_ids = _get_valid_project_samples(project_samples, dataset_type, sample_type, request.user)
         success_message = f'*{request.user.email}* triggered loading internal {sample_type} {dataset_type} data for {len(projects)} projects'

diff --git a/ui/pages/DataManagement/components/LoadData.jsx b/ui/pages/DataManagement/components/LoadData.jsx
@@ -97,6 +97,12 @@ const MULTI_DATA_TYPE_CALLSET_PAGE = {
       placeholder: 'gs://',
       ...FILE_PATH_FIELD,
     },
+    {
+      name: 'skipSRChecks',
+      label: 'Skip Sex and Relatedness Checks',
+      component: InlineToggle,
+      asFormInput: true,
+    },
     ...CALLSET_PAGE_FIELDS,
     {
       name: 'datasetType',