From 4cc4c9952613b9a550bc434309c5c195f0f9d36b Mon Sep 17 00:00:00 2001
From: riasc <richard.schaefer@zoho.com>
Date: Thu, 29 Feb 2024 21:04:29 -0600
Subject: [PATCH] outsource merging of predicted mhccII alleles

---
 .../genotyping/merge_predicted_mhcII.py       | 45 +++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 workflow/scripts/genotyping/merge_predicted_mhcII.py

diff --git a/workflow/scripts/genotyping/merge_predicted_mhcII.py b/workflow/scripts/genotyping/merge_predicted_mhcII.py
new file mode 100644
index 0000000..f5eb331
--- /dev/null
+++ b/workflow/scripts/genotyping/merge_predicted_mhcII.py
@@ -0,0 +1,45 @@
+import sys
+import re
+from pathlib import Path
+
+
+"""
+    This scripts combines the predicted mhc-II alleles from different `groups`
+
+    Usage:
+
+    python merge_predicted_mhcII.py '<input>' <output>
+"""
+
+
+def main():
+    infiles = sys.argv[1]
+    alleles = {}
+
+    for infile in infiles.split(" "):
+        filestem = Path(infile).stem
+        se = re.search(r'^(.+)_(RNA|DNA)', filestem)
+        group = se.group(1)
+
+        fh = open(infile, "r")
+        for line in fh:
+            al = line.strip().split("\t")
+            for a in al[1:]:
+                # make sure the alleles were type successfully
+                if a != "-" and a != "Not typed":
+                    if a not in alleles:
+                        alleles[a] = []
+                    if group not in alleles[a]:
+                        alleles[a].append(group)
+        fh.close()
+
+    out = open(sys.argv[2], 'w')
+    for al in dict(sorted(alleles.items())):
+        for i,v in enumerate(alleles[al]):
+            if i == 0:
+                out.write(v)
+            else:
+                out.write(f',{v}')
+        out.write(f'\t{al}\n')
+
+main()