Exclude PAT strains and outliers from phylogenetic analysis

Exclude several PAT strains that did not have the is_lab_host metadata field set to True.
Exclude several strains that were either putative recombinants or were below the PAT FV537222 cluster.

phylogenetic/defaults/config.yaml

@@ -65,7 +65,7 @@ input_sequences: "data/sequences.fasta"
 # This command excludes all strains by default and then forces the inclusion of
 # the strains selected by the subsampling logic defined above.
 subsampling:
-  region: --query "is_lab_host != 'true'" --query-columns is_lab_host:str --min-length '9800' --group-by region year --subsample-max-sequences 3000
+  region: --query "is_lab_host != 'true'" --query-columns is_lab_host:str --min-length '9800' --group-by region year --subsample-max-sequences 3000 --exclude defaults/exclude.txt
   force_include: --exclude-all --include defaults/include.txt
 
 traits:

phylogenetic/defaults/exclude.txt

@@ -0,0 +1,55 @@
+HW816192 # 11029 bp PAT 27-MAY-2015
+CS543188 # 11029 bp PAT 20-APR-2007
+CS568914 # 11029 bp PAT 18-MAY-2007
+CS568916 # 11029 bp PAT 18-MAY-2007
+CS568917 # 11029 bp PAT 18-MAY-2007
+CS568918 # 11029 bp PAT 18-MAY-2007
+CS568919 # 11029 bp PAT 18-MAY-2007
+FV537222 # 10962 bp PAT 18-MAR-2010
+FV537223 # 10962 bp PAT 18-MAR-2010
+FV537224 # 10962 bp PAT 18-MAR-2010
+FV537225 # 10962 bp PAT 18-MAR-2010
+LQ460608 #  8839 bp PAT 06-OCT-2016
+LQ564350 #  8839 bp PAT 06-OCT-2016
+LY683288 # 11062 bp PAT 04-DEC-2019
+MA388207 #  8839 bp PAT 30-OCT-2018
+HC467807 # 11029 bp PAT 21-APR-2010
+HH961658 # 10975 bp PAT 31-OCT-2010
+HH961659 # 11029 bp PAT 31-OCT-2010
+HV572312 # 11029 bp PAT 31-MAY-2012
+OP846974 # Suspected recombinant sequences from Mencattelli et al, 2023 https://www.nature.com/articles/s41467-023-42185-7
+OK239667 # Suspected recombinant sequences from Mencattelli et al, 2023 https://www.nature.com/articles/s41467-023-42185-7
+OM202920 # Clusters below PAT FV537222
+OM202936 # Clusters below PAT FV537222
+OM202914 # Clusters below PAT FV537222
+OM202933 # Clusters below PAT FV537222
+OM202907 # Clusters below PAT FV537222
+OK573263 # Clusters below PAT FV537222
+FV537224 # Clusters below PAT FV537222
+OK573278 # Clusters below PAT FV537222
+OM202917 # Clusters below PAT FV537222
+OM202919 # Clusters below PAT FV537222
+OM202910 # Clusters below PAT FV537222
+OM202911 # Clusters below PAT FV537222
+OM202922 # Clusters below PAT FV537222
+OK573272 # Clusters below PAT FV537222
+OK573262 # Clusters below PAT FV537222
+OK573279 # Clusters below PAT FV537222
+OK573269 # Clusters below PAT FV537222
+OM202923 # Clusters below PAT FV537222
+OM202906 # Clusters below PAT FV537222
+OM202909 # Clusters below PAT FV537222
+OM202930 # Clusters below PAT FV537222
+OM202929 # Clusters below PAT FV537222
+OM202904 # Clusters below PAT FV537222
+OM202913 # Clusters below PAT FV537222
+OM202908 # Clusters below PAT FV537222
+OM202915 # Clusters below PAT FV537222
+OM202912 # Clusters below PAT FV537222
+OK572999 # Clusters below PAT FV537222
+OK573277 # Clusters below PAT FV537222
+FV537225 # Clusters below PAT FV537222
+OM202905 # Clusters below PAT FV537222
+OM202932 # Clusters below PAT FV537222
+FV537223 # Clusters below PAT FV537222
+FV537222 # Clusters below PAT FV537222