b03342c05eb5d5c23ee2a503ee5ce77e874e725c angie Fri Dec 20 15:39:24 2024 -0800 (finally) mask G26530A reversion in BA.1 because it kept splitting BA.1.18. Unmask 21770 in BA.2.86 (alignment boundary change / nextclade / subst of interest). diff --git src/hg/utils/otto/sarscov2phylo/branchSpecificMask.yml src/hg/utils/otto/sarscov2phylo/branchSpecificMask.yml index 1096625..9e24394 100644 --- src/hg/utils/otto/sarscov2phylo/branchSpecificMask.yml +++ src/hg/utils/otto/sarscov2phylo/branchSpecificMask.yml @@ -22,30 +22,32 @@ ranges: [ [ 22027, 22034], [28246, 28254] ] sites: [ 21302, 21304, 21305, # https://github.com/cov-lineages/pango-designation/issues/398 21846, # S:95 noisy -- caused split AY.100 28461, # https://github.com/cov-lineages/pango-designation/issues/435 28271 ] # deletion BA.1: representative: England/DHSC-CYBJ4Y8/2022 ranges: [ [ 6513, 6515 ], [ 11283, 11291 ], # https://github.com/cov-lineages/pango-designation/issues/361 [ 21765, 21770 ], [ 21988, 21995 ], [ 22194, 22217 ], # deletion 22194-22196, insertion after 22204, big mess after that [ 28362, 28370 ] ] sites: [ 203, 22813, 22898, 22882, 23854 ] + # Adding this 2024-09-26 because it keeps splitting BA.1.18 and causing trouble for pangolin-data + reversions: [ G26530A ] BA.1.1: # On the BA.1 branch, so it inherits BA.1 masking. representative: England/ALDP-2BEB0A0/2021 ranges: [ [ 76, 77 ] ] reversions: [ G26530A ] # false reversions on this really messed up the BA.1.1.1 branch. # XD should have this reversion, oh well. BA.2: # I'm including some 5' UTR and 3' UTR sites now; in retrospect could have started earlier. # I would mask 210 too but it's useful for finding breakpoints of Delta/BA.2 recombinants. # 212 is also noisy but I'm leaving it in as a red flag for 210 mutations that might be noise. representative: England/DHSC-CYBAB7G/2022 representativeBacktrack: 1 ranges: [ # 5' UTR @@ -98,31 +100,32 @@ BN.1.2.3: # Inherits from BA.2.75 representative: England/QEUH-326228D4/2022 sites: [ 337 # https://github.com/cov-lineages/pango-designation/issues/2016#issuecomment-1626159006 ] BA.2.86: # Inherits from BA.2 # @Over-There-Is requested 21610 - very messy indeed. # https://github.com/sars-cov-2-variants/lineage-proposals/issues/606#issuecomment-1801095482 # @aviczhl2 pointed out some recurring reversions: # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1072 representative: Denmark/DCGC-661170/2023 ranges: [ [ 21294, 21296 ], # run of muts, makes a mini-JN.1 [ 21539, 21542 ], # run of muts, France/...-HCL, makes a mini-JN.1 - [ 21765, 21770 ], # https://github.com/sars-cov-2-variants/lineage-proposals/issues/606 + [ 21765, 21769 ], # https://github.com/sars-cov-2-variants/lineage-proposals/issues/606 + # https://github.com/sars-cov-2-variants/lineage-proposals/issues/2194#issuecomment-2456087552 [ 21610, 21624 ], # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1347 [ 21625, 21626 ], # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1380 # 21627 taken back out 2024-05-26 by email request from FedeGueli [ 21628, 21631 ], # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1380 [ 22194, 22196 ] ] # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1380 sites: [ 58, 59, # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1089 13427, # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1313 21302, 21304, 21305, # https://github.com/sars-cov-2-variants/lineage-proposals/issues/1190 ] reversions: [ T21711C, C22032T, A22033C, G22034A, A22770G, A23012G, G26610A, # Added 2024-03-01 because they're causing reversion branches with >= 100 samples. # Unfortunately 6183 and 9142 will be incorrect in XDD, XDR, XDS. T2790C, T4321C, G6183A, T9142C, C13339T, A22353C, G22556A, C22577G, T22674C, T22686C, G22688A, T22813G, C22895G, A22896T, A22898G, T22916C, G22917T, A22942T, A23005T, C23075T, G23599T, G23604C, T24378C, T26858C,