1715fcf5e6c59c033d9f6dfb341e62b1f1b7c629 angie Tue Dec 7 18:38:36 2021 -0800 Mask 21846 (S:95) in Delta branch - Cornelius Roemer and Chris Ruis pointed out phylogeny problems it caused. diff --git src/hg/utils/otto/sarscov2phylo/maskDelta.sh src/hg/utils/otto/sarscov2phylo/maskDelta.sh index 6d767e5..30cba66 100755 --- src/hg/utils/otto/sarscov2phylo/maskDelta.sh +++ src/hg/utils/otto/sarscov2phylo/maskDelta.sh @@ -31,18 +31,22 @@ deltaNode=$(grep IND/GBRC714b/2021 $samplePaths | awk '{print $NF;}' | sed -re 's/:.*//;') # Delta has deletions at S:157-158 (22029-22034), ORF8:119-120 (28248-28253) and 28271. # Mask those locations and some adjacent bases where we get a ton of spurious "mutations". maskFile=$(basename $treeInPb .pb).maskForDelta.tsv set +x for ((i=22027; $i <= 22034; i++)); do echo -e "N${i}N\t$deltaNode" done > $maskFile for ((i=28246; $i <= 28253; i++)); do echo -e "N${i}N\t$deltaNode" done >> $maskFile echo -e "N28271N\t$deltaNode" >> $maskFile set -x +# S:95 (21846) is also very unreliably detected in Delta. Mask it off to avoid tree trouble, +# like split AY.100. +echo -e "N21846N\t$deltaNode" >> $maskFile + time $matUtils mask -i $treeInPb \ -m $maskFile \ -o $treeOutPb