Update datatsets_collector.py

biobricks-ai · Aug 30, 2024 · 7970ed9 · 7970ed9
1 parent 1e3e1d4
commit 7970ed9
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 11 deletions.
diff --git a/dvc.lock b/dvc.lock
@@ -5,26 +5,26 @@ stages:
     deps:
     - path: stages/01_download.sh
       hash: md5
-      md5: df81fe46e4f976d979ae60c7f6c9b793
-      size: 2139
+      md5: 3d2308cb06b9bb143fa0d5e56cb1ccdc
+      size: 825
     outs:
     - path: download
       hash: md5
-      md5: fc3d3f77df3c7d0934a24070aac927ca.dir
-      size: 17731246
-      nfiles: 63
+      md5: e0eda04fa057fd5541a9d895fceb3c53.dir
+      size: 17731243
+      nfiles: 60
     - path: list
       hash: md5
-      md5: 1b7a5c6ef99e89f4715f445520c59f2f.dir
-      size: 5345
+      md5: aeb7edcb20ca7bdb19c9e87056b7a354.dir
+      size: 5075
       nfiles: 1
   build:
     cmd: stages/03_build.sh
     deps:
     - path: list
       hash: md5
-      md5: 1b7a5c6ef99e89f4715f445520c59f2f.dir
-      size: 5345
+      md5: aeb7edcb20ca7bdb19c9e87056b7a354.dir
+      size: 5075
       nfiles: 1
     - path: stages/03_build.sh
       hash: md5

diff --git a/stages/datasets_collector.py b/stages/datasets_collector.py
@@ -122,8 +122,9 @@ def process_pathways(self, datasets):
             dataset = self.api.get_published_dataset(id=dataset_id, version='latest')
             data_frame = dataset.get_data()
             pathways = self.get_pathways_for_gene(data_frame['SYMBOL'].iloc[0])
-            pathways.to_csv(file_path, index=False)
-            self.log_file.write(file_path + "\n")
+            if len(pathways) > 0:
+                pathways.to_csv(file_path, index=False)
+                self.log_file.write(file_path + "\n")
 
     def process_datasets(self):
         """