From ee349d5b7f5599c2975e1ef40e532cb7824a612d Mon Sep 17 00:00:00 2001
From: Lee Katz <gzu2@cdc.gov>
Date: Wed, 5 Jun 2024 14:09:31 -0400
Subject: [PATCH] Esearch input (#47)

* Add genomes (#45) (#46)

* Corynebacterium diphtheriae

* added Bifidobacterium adolenscentis

* replaced S. enterica IIIa; Added hops (Humulus lupulus)

* added a Citrobacter species

* m

* replaced repressed genome accession for B. faecium

* remove random single quotes

* bump version

* helpful log messages

* v5.6.3

* make symlink to avoid naming mistakes

* check whether taxonkit is loaded

* use efetch -input

* fix tr bug
---
 bin/buildKraken1.sh     |  8 ++++++++
 bin/downloadKalamari.pl | 26 ++++++++++++--------------
 bin/filterTaxonomy.sh   |  3 +++
 src/plasmids.tsv        |  4 ++--
 4 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/bin/buildKraken1.sh b/bin/buildKraken1.sh
index d51f638..851ff75 100755
--- a/bin/buildKraken1.sh
+++ b/bin/buildKraken1.sh
@@ -22,11 +22,15 @@ cp -rv $TAXDIR $DB/taxonomy
 
 # Make --add-to-library more efficient with
 # concatenated fasta files
+export nl=$'\n'
 find $SRC -name '*.fasta.gz' | \
   xargs -n 100 -P 1 bash -c '
     for i in "$@"; do
       gzip -cd $i
     done > $tmpfile
+    echo -ne "ADDING to library:\n  "
+    zgrep "^>" $tmpfile | sed "s/^>//" | tr "$nl" " "
+    echo "^^ contents of $tmpfile ^^"
     kraken-build --db $DB --add-to-library $tmpfile
   '
 
@@ -35,3 +39,7 @@ kraken-build --db $DB --build --threads 1
 # Reduce the size of the database
 kraken-build --db $DB --clean
 
+
+if [ ! -e "$sharedir/kalamari-kraken1" ]; then
+  ln -sv kalamari-kraken "$sharedir/kalamari-kraken1"
+fi
diff --git a/bin/downloadKalamari.pl b/bin/downloadKalamari.pl
index 314a3de..34526a5 100755
--- a/bin/downloadKalamari.pl
+++ b/bin/downloadKalamari.pl
@@ -11,7 +11,7 @@
 use IO::Compress::Gzip;
 use version 0.77;
 
-our $VERSION = version->parse("5.6.0");
+our $VERSION = version->parse("5.7.0");
 
 use threads;
 
@@ -167,27 +167,25 @@ sub downloadEntries{
   my $numEntries = scalar(@$entries);
   my @acc = map{$$_{nuccoreAcc}} @$entries;
   logmsg "Downloading ".scalar(@acc)." accessions";
-  my $queryArg = join("[accession] OR ", sort(@acc))."[accession]";
   my $dir = tempdir("download.XXXXXX", DIR=>$$settings{tempdir});
 
+  # Make the input file for efetch
+  my $inputAcc = "$dir/input.acc";
+  open(my $fh, ">", $inputAcc) or die "ERROR: could not write to $inputAcc: $!";
+  print $fh join("\n", @acc)."\n";
+  close $fh;
+
   # Accessions that had errors
   my @err;
 
-  # Get the esearch xml in place for at least one downstream query
-  my $esearchXml = "$dir/esearch.xml";
-  my $esearchCmd = "esearch -db nuccore -query '$queryArg' > $esearchXml";
-  command($esearchCmd);
+  # Get started on the comprehensive assembly file
+  my $outfile = "$dir/all.fasta";
+  logmsg "Downloading all accessions to $outfile using input accessions in $inputAcc";
+  command("efetch -db nuccore -input $inputAcc -format fasta > $dir/all.fasta");
   if($?){
-    die "ERROR running: $esearchCmd: $!";
+    die "ERROR: could not download all accessions";
   }
 
-  # Get started on the assembly file
-  my $outfile = "$dir/all.fasta";
-
-  # Main query: efetch
-  my $efetchCmd = "cat $esearchXml | efetch -format fasta > $outfile";
-  system($efetchCmd);
-
   my $seqsWithVersion = readSeqs($outfile);
   my $seqs = {};
   while(my($acc, $seq) = each(%$seqsWithVersion)){
diff --git a/bin/filterTaxonomy.sh b/bin/filterTaxonomy.sh
index 48fbb3f..1af4912 100755
--- a/bin/filterTaxonomy.sh
+++ b/bin/filterTaxonomy.sh
@@ -2,6 +2,9 @@
 
 set -eu
 
+# Check for dependencies
+which taxonkit
+
 thisdir=$(dirname $0)
 thisfile=$(basename $0)
 KALAMARI_VER=$(downloadKalamari.pl --version)
diff --git a/src/plasmids.tsv b/src/plasmids.tsv
index e9656a5..c2dafa6 100644
--- a/src/plasmids.tsv
+++ b/src/plasmids.tsv
@@ -2964,7 +2964,7 @@ Rickettsia	CP015014	780	33988
 Rickettsia	CP010970	780	33988
 Onion yellows phytoplasma	AB480166	100379	85620
 Onion yellows phytoplasma	AB479509	100379	85620
-'Brassica napus' phytoplasma	HQ637382	469009	85620
+Brassica napus phytoplasma	HQ637382	469009	85620
 Candidatus Phytoplasma	FJ905104	33926	2146
 Candidatus Phytoplasma	KF801472	33926	2146
 Onion yellows phytoplasma	AB479513	100379	2146
@@ -2986,7 +2986,7 @@ Paulownia witches'-broom phytoplasma	EF426472	39647	85620
 Paulownia witches'-broom phytoplasma	EF426473	39647	85620
 Periwinkle little leaf phytoplasma	JN835187	137854	85635
 Rice orange leaf phytoplasma	KY086101	146897	85635
-'Catharanthus roseus' aster yellows phytoplasma	CP035950	1193712	85620
+Catharanthus roseus aster yellows phytoplasma	CP035950	1193712	85620
 Bacillus thuringiensis	CP016196	1428	85620
 Bacillus sp. BS98	CP043831	2608254	185979
 Bacillus	CP009595	1386	185979