fix: Allow for large assets in refgenie

sansterbioanalytics · Mar 27, 2023 · 1c99871 · 1c99871
1 parent 60f066f
commit 1c99871
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 1 deletion.
diff --git a/bio/refgenie/test/Snakefile b/bio/refgenie/test/Snakefile
@@ -9,3 +9,15 @@ rule obtain_asset:
         tag="default"
     wrapper:
         "master/bio/refgenie"
+
+rule obtain_large_asset:
+    output:
+        # the name refers to the refgenie seek key (see attributes on http://refgenomes.databio.org)
+        star_index=directory("refs/star_index/hg38/star_index")
+        # Multiple outputs/seek keys are possible here.
+    params:
+        genome="hg38",
+        asset="star_index",
+        tag="default"
+    wrapper:
+        "master/bio/refgenie"
diff --git a/bio/refgenie/wrapper.py b/bio/refgenie/wrapper.py
@@ -15,7 +15,8 @@
 rgc = refgenconf.RefGenConf(conf_path, writable=True)
 
 # pull asset if necessary
-gat, archive_data, server_url = rgc.pull(genome, asset, tag, force=False)
+# BUG Times out when pulling large assets
+gat, archive_data, server_url = rgc.pull(genome, asset, tag, force=False, force_large=True)
 
 for seek_key, out in snakemake.output.items():
     path = rgc.seek(genome, asset, tag_name=tag, seek_key=seek_key, strict_exists=True)