b96a4b4d3d3b9d7dd2e7a1934ff4e4e57fb1348b angie Tue Feb 22 11:07:42 2022 -0800 Mask two new problematic-in-Delta positions (https://github.com/cov-lineages/pango-designation/issues/435) diff --git src/hg/utils/otto/sarscov2phylo/maskDelta.sh src/hg/utils/otto/sarscov2phylo/maskDelta.sh index 251119d..3bc7072 100755 --- src/hg/utils/otto/sarscov2phylo/maskDelta.sh +++ src/hg/utils/otto/sarscov2phylo/maskDelta.sh @@ -42,30 +42,35 @@ 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" >> $maskFile # These three sites are recommended for caution in the Problematic Sites set, and seem to have # create a false lineage (AY.89) from samples that probably should be AY.4. AY.89 is being # withdrawn (https://github.com/cov-lineages/pango-designation/issues/398); mask sites in Delta. echo -e "N21302N\t$deltaNode" >> $maskFile echo -e "N21304N\t$deltaNode" >> $maskFile echo -e "N21305N\t$deltaNode" >> $maskFile +# Mask flaky positions 28254 (ORF8:121) and 28461 (N:63) so that AY.96 is merged into AY.46 +# https://github.com/cov-lineages/pango-designation/issues/435 +echo -e "N28254N\t$deltaNode" >> $maskFile +echo -e "N28461N\t$deltaNode" >> $maskFile + # OK, not just Delta -- Alpha, Beta, and Gamma have a deletion that causes spurious "mutations", # especially at 11296 and 11291, somewhat also at 11288. # Omicron has ~ the same deletion but it aligns 5 bases to the left, probably because it was # combined with an SNV (https://github.com/cov-lineages/pango-designation/issues/361). alphaNode=$(grep Italy/TAA-1900553896/2021 $samplePaths \ | awk '{print $(NF-1);}' | sed -re 's/:.*//;') betaNode=$(grep SouthAfrica/CERI-KRISP-K012031/2021 $samplePaths \ | awk '{print $NF;}' | sed -re 's/:.*//;') gammaNode=$(grep France/PAC-IHU-5193-N1/2021 $samplePaths | awk '{print $NF;}' | sed -re 's/:.*//;') set +x for node in $alphaNode $betaNode $gammaNode; do for ((i=11288; $i <= 11296; i++)); do echo -e "N${i}N\t$node" done done >> $maskFile