Created file gen_group_samplelists that iterates through all genofiles

and builds each groups' samplelist

2 files changed, 46 insertions, 1 deletions

diff --git a/wqflask/maintenance/gen_select_dataset.py b/wqflask/maintenance/gen_select_dataset.py
index 8cb94f20..d4e47327 100644
--- a/wqflask/maintenance/gen_select_dataset.py
+++ b/wqflask/maintenance/gen_select_dataset.py
@@ -115,7 +115,7 @@ def build_types(species, group):
     (all types except phenotype/genotype are tissues)
      
     """
-    Cursor.execute("""select distinct Tissue.Name, Tissue.Name
+    Cursor.execute("""select distinct Tissue.Name, concat(Tissue.Name, ' mRNA')
                        from ProbeFreeze, ProbeSetFreeze, InbredSet, Tissue, Species
                        where Species.Name = %s and Species.Id = InbredSet.SpeciesId and
                        InbredSet.Name = %s and
@@ -192,6 +192,8 @@ def main():
                 datasets=datasets,
                 )
 
+    print("data:", data)
+
     output_file = """../wqflask/static/new/javascript/dataset_menu_structure.json"""
 
     with open(output_file, 'w') as fh:
diff --git a/wqflask/maintenance/get_group_samplelists.py b/wqflask/maintenance/get_group_samplelists.py
new file mode 100644
index 00000000..2434038e
--- /dev/null
+++ b/wqflask/maintenance/get_group_samplelists.py
@@ -0,0 +1,43 @@
+from __future__ import absolute_import, print_function, division
+
+import os
+import glob
+import gzip
+
+from base import webqtlConfig
+
+
+def get_sample_list_dir(geno_dir="/home/zas1024/gene/web/genotypes/"):
+    os.chdir(geno_dir)
+    
+    for group_file in glob.glob("*"):
+        if group_file.lower().endswith(('.geno', '.geno.gz')):
+            #group_name = genofilename.split('.')[0]
+            sample_list = get_sample_list(group_file)
+            print("\n\n{}\n\n".format(sample_list))
+
+
+def get_sample_list(group_file):
+    print(group_file)
+    genofilename = str(os.path.join(webqtlConfig.GENODIR, group_file))
+    if genofilename.lower().endswith('.geno.gz'):
+        genofile = gzip.open(genofilename)
+    else:
+        genofile = open(genofilename)
+    for line in genofile:
+        line = line.strip()
+        if not line:
+            continue
+        if line.startswith(("#", "@")):
+            continue
+        headline = line
+        break
+    headers = headline.split("\t")
+    if headers[3] == "Mb":
+        samplelist = headers[4:]
+    else:
+        samplelist = headers[3:]
+    return samplelist
+
+if __name__ == '__main__':
+    get_sample_list_dir()