generates subproblems/subproblems-scaffold.tre and subproblems/subproblems-scaffold-only.tre for an Open Tree synth. tree build

generate-subproblem-scaffold.bash

#!/bin/bash
# This needs to be made part of the propinquity process.
# 	MTH ran steps that made up the basis of this before the
#	Jan 2020 SSB workshop. So the resulting file will be in
#	the https://files.opentreeoflife.org/synthesis/opentree12.3/opentree12.3/subproblems/
#	folder, but (perversely enough) not in the tar archive at https://files.opentreeoflife.org/synthesis/opentree12.3/opentree12.3.tgz
# If all goes as planned, we'll start adding this to the tree build process so that it will be in 
#	builds and archives made after 12.3

# This is to be run with the working directory being the propinquity
#	output directory and with otcetera tools on the PATH
set -x
# Make a tree that is a polytomy with a leaf-set of all of the subproblem roots ID
cat subproblems/subproblem-ids.txt | sed -E 's/\.tre/,/' > idswithoutdottre.txt || exit
echo '(' > x.tre || exit
cat idswithoutdottre.txt >> x.tre || exit
echo ');' >> x.tre || exit

# remove the extra , by replacing ,\n) with )
perl -0777 -i -pe 's/,\n[)]/)/' x.tre || exit

# produce the induced tree for the taxonomy:
otc-induced-subtree exemplified_phylo/taxonomy.tre x.tre > subproblems/subproblems-scaffold.tre || exit
rm x.tre || exit

# Suppress monotypic taxa. This may eliminate some trivial subproblems, but gives
#	but gives an easier tree to look at.
python suppress-non-listed-ids-or-unnamed.py subproblems/subproblems-scaffold.tre idswithoutdottre.txt >subproblems/subproblems-scaffold-only.tre  || exit
rm idswithoutdottre.txt || exit