abdea7a81b3d511adaee6300277721a804f5581f
angie
  Tue Mar 30 11:57:47 2021 -0700
Ongoing fixes for odd characters in sequence names and other pipeline tweaks.

diff --git src/hg/utils/otto/sarscov2phylo/util.sh src/hg/utils/otto/sarscov2phylo/util.sh
index e64b80d..1373dbb 100755
--- src/hg/utils/otto/sarscov2phylo/util.sh
+++ src/hg/utils/otto/sarscov2phylo/util.sh
@@ -34,30 +34,30 @@
     | sed -re '/^[A-Z]+$/bx; s@[A-Za-z0-9]+ [a-z]*protein.*@@; :x;' \
     | sed -re 's@(( genomic)? RNA)?, ((nearly )?complete|partial) genome$@@;' \
     | sed -re 's@genome assembly(, complete genome)?: monopartite$@@;' \
     | sed -re 's@ (1 |nasopharyngeal )?genome assembly, chromosome: .*$@@;' \
     | sed -re 's@, complete sequence@@;' \
     | sed -re 's@humans, [A-Za-z]+,( [0-9]+ Years old)?( Adult)?/@@' \
     | sed -re 's@hCo[vV]-19/@@;' \
     | sed -re 's@SARS?-CoV-?2/([Hh]umai?ns?|[Hh]o[mw]o ?sapiens?)/@@;' \
     | sed -re 's@SARS-CoV-2/(environment|ENV)/@env/@;' \
     | sed -re 's@SARS-CoV-2/Felis catus/@cat/@;' \
     | sed -re 's@SARS-CoV-2/Panthera leo/@lion/@;' \
     | sed -re 's@SARS-CoV-2/Panthera tigris/@tiger/@;' \
     | sed -re 's@SARS-CoV-2/@@;' \
     | sed -re 's@BetaCoV/@@;' \
     | sed -re 's@Homo sapines/@@;' \
-    | sed -re 's@ \| @ \|@; s@ $@@; s@  @ @;' \
+    | sed -re 's@ \| @ \|@; s@ $@@; s@[:,]@ @g; s@  @ @g; s@[()]@@g;' \
     | sed -re 's@ \|@\t@;'
 # Got rid of this:   s/ ([^|])/_\1/g;
 }
 export -f cleanGenbank
 
 cleanCncb () {
     sed -re "s@^BetaCoV/@@;
              s@^hCoV-19/@@;
              s@^SARS-CoV-2/@@;
              s@^human/@@;
              s@ *\| *@\t@;"
 }
 export -f cleanCncb