feb0c6c24faed625f7e15874ade55a3f8968886c
angie
  Sun Mar 20 10:20:35 2022 -0700
Adding some BA.1 Spike/amplicon dropout positions that are problematic but so far don't affect proposed Delta/BA.1 recombinants.

diff --git src/hg/utils/otto/sarscov2phylo/maskDelta.sh src/hg/utils/otto/sarscov2phylo/maskDelta.sh
index 2393232..93ab192 100755
--- src/hg/utils/otto/sarscov2phylo/maskDelta.sh
+++ src/hg/utils/otto/sarscov2phylo/maskDelta.sh
@@ -90,30 +90,37 @@
 done >> $maskFile
 for ((i=21765;  $i <= 21770;  i++)); do
     echo -e "N${i}N\t$BA1Node"
 done >> $maskFile
 # There's a deletion 21987-21995 and then an insertion after 22204 and more messy bases after that.
 for ((i=21988;  $i <= 22217;  i++)); do
     echo -e "N${i}N\t$BA1Node"
 done >> $maskFile
 for ((i=22194;  $i <= 22198;  i++)); do
     echo -e "N${i}N\t$BA1Node"
 done >> $maskFile
 for ((i=28362;  $i <= 28370;  i++)); do
     echo -e "N${i}N\t$BA1Node"
 done >> $maskFile
 
+# BA.1 has a lot of amplicon dropout / Delta contam noise at these sites, but so far they
+# don't affect the Delta/Omicron recombinants identified to date which all have Omicron spike,
+# so mask these out in BA.1:
+for i in 22813 22898 22882 22917 23854; do
+    echo -e "N${i}N\t$BA1Node"
+done >> $maskFile
+
 # BA.2 has some additional deletions.
 for ((i=21633;  $i <= 21641;  i++)); do
     echo -e "N${i}N\t$BA2Node"
 done >> $maskFile
 for ((i=28362;  $i <= 28370;  i++)); do
     echo -e "N${i}N\t$BA1Node"
 done >> $maskFile
 for ((i=29734;  $i <= 29759;  i++)); do
     echo -e "N${i}N\t$BA1Node"
 done >> $maskFile
 set -x
 
 time $matUtils mask -i $treeInPb \
     -m $maskFile \
     -o $treeOutPb