From fa9f6a78646d2f8a3aaea8971e663cc3375019b1 Mon Sep 17 00:00:00 2001
From: marieBvr <lefebvre.m2@gmail.com>
Date: Mon, 5 Jul 2021 16:11:34 +0200
Subject: [PATCH] Fix #1 update taxonomy db creation

---
 db/loadTaxonomy.pl           | 45 +++++++++++++++++++-----------------
 docs/source/prerequisite.rst |  8 ++++---
 2 files changed, 29 insertions(+), 24 deletions(-)

diff --git a/db/loadTaxonomy.pl b/db/loadTaxonomy.pl
index 67648a3..f1ed40a 100755
--- a/db/loadTaxonomy.pl
+++ b/db/loadTaxonomy.pl
@@ -28,6 +28,8 @@
   "acc_prot=s" => \$data_acc_prot,
   "acc_wgs=s"=> \$data_acc_wgs,
   "acc_nucl=s"=> \$data_acc_nucl,
+  "dead_prot=s"=> \$data_dead_acc_prot,
+  "dead_nucl=s"=> \$data_dead_acc_nucl,
   # "gi_nucl=s" => \$gi_nucl,
   "gi_prot=s" => \$gi_prot,
   "names=s"  => \$data_names,
@@ -246,27 +248,28 @@ sub _set_options {
 }
 
 
-sub help {
-my $prog = basename($0);
-print STDERR <<EOF ;
-#### $prog ####
-#
-# AUTHOR:     Sebastien THEIL and Marie LEFEBVRE
-# LAST MODIF: 07/02/2020
-# PURPOSE:    This script is used to load NCBI taxonomy file into a SQLite database.
+  sub help {
+    my $prog = basename($0);
+    print STDERR <<EOF ;
+    #### $prog ####
+    #
+    # AUTHOR:     Sebastien THEIL and Marie LEFEBVRE
+    # LAST MODIF: 07/02/2020
+    # PURPOSE:    This script is used to load NCBI taxonomy file into a SQLite database.
 
-USAGE:
-      $prog -struct taxonomyStructure.sql -index taxonomyIndex.sql -acc_prot acc2taxid.prot -acc_nucl acc2taxid.nucl -names names.dmp -nodes nodes.dmp -gi_nucl gi_taxid_nucl.dmp -gi_prot gi_taxid_prot.dmp
+    USAGE:
+          $prog -struct taxonomyStructure.sql -index taxonomyIndex.sql -acc_prot acc2taxid.prot -acc_nucl acc2taxid.nucl -names names.dmp -nodes nodes.dmp -gi_nucl gi_taxid_nucl.dmp -gi_prot gi_taxid_prot.dmp
 
-      ### OPTIONS ###
-      -struct     <path>   taxonomyStructure.sql path. (Default: $taxo_struct_dmp)
-      -index      <path>   taxonomyIndex.sql path. (Default: $taxo_index_dmp)
-      -acc_prot   <path>   prot.accession2taxid. (Default: $data_acc_prot)
-      -acc_nucl   <path>   nucl.accession2taxid. (Default: $data_acc_wgs)
-      -names      <path>   names.dmp file. (Default: $data_names)
-      -nodes      <path>   nodes.dmp file. (Default: $data_nodes)
-      -gi_prot    <path>   gi_taxid_prot.dmp file (Default: $gi_prot)
-      -v          <int>      Verbosity level. (0 -> 4).
-EOF
-exit(1);
+          ### OPTIONS ###
+          -struct     <path>   taxonomyStructure.sql path. (Default: $taxo_struct_dmp)
+          -index      <path>   taxonomyIndex.sql path. (Default: $taxo_index_dmp)
+          -acc_prot   <path>   prot.accession2taxid. (Default: $data_acc_prot)
+          -acc_nucl   <path>   nucl.accession2taxid. (Default: $data_acc_wgs)
+          -names      <path>   names.dmp file. (Default: $data_names)
+          -nodes      <path>   nodes.dmp file. (Default: $data_nodes)
+          -gi_prot    <path>   gi_taxid_prot.dmp file (Default: $gi_prot)
+          -v          <int>      Verbosity level. (0 -> 4).
+    EOF
+    exit(1);
+  }
 }
diff --git a/docs/source/prerequisite.rst b/docs/source/prerequisite.rst
index 875abac..194822e 100644
--- a/docs/source/prerequisite.rst
+++ b/docs/source/prerequisite.rst
@@ -44,6 +44,8 @@ Perl external libraries
 * String::Random
 * Bio::SearchIO:blastxml
 * Bio::SeqIO
+* Expect
+* GD:Simple
 
 
 Perl included libraries
@@ -116,7 +118,7 @@ NCBI Taxonomy
  wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/accession2taxid/dead_wgs.accession2taxid.gz ; gunzip dead_wgs.accession2taxid.gz
  cat nucl_wgs.accession2taxid nucl_gb.accession2taxid dead_wgs.accession2taxid > acc2taxid.nucl
  wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/accession2taxid/dead_nucl.accession2taxid.gz; gunzip dead_nucl.accession2taxid.gz;
- wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/gi_taxid_prot.dmp.gz; gunzip gi_taxid_prot.dmp.gz;
+ wget ftp://ftp.ncbi.nih.gov/pub/taxonomy/obsolete/gi_taxid_prot.dmp.gz; gunzip gi_taxid_prot.dmp.gz;
 
 Optionally you can combine multiple accession2taxid file with a simple cat. But keep separated nucl and prot accessions as they will be loaded in two different tables.
 
@@ -124,7 +126,7 @@ Launch the loadTaxonomy.pl script that will create the sqlite database. The scri
 
 .. code-block:: bash
 
- ./loadTaxonomy.pl -struct taxonomyStructure.sql -index taxonomyIndex.sql -acc_prot acc2taxid.prot -acc_nucl acc2taxid.nucl -names names.dmp -nodes nodes.dmp -gi_prot gi_taxid_prot.dmp
+ ./loadTaxonomy.pl -struct taxonomyStructure.sql -index taxonomyIndex.sql -acc_prot acc2taxid.prot -acc_nucl acc2taxid.nucl -names names.dmp -nodes nodes.dmp -gi_prot gi_taxid_prot.dmp -acc_wgs acc2taxid.nucl
 
 
 PFAM taxonomy
@@ -140,7 +142,7 @@ Be carefull, the files you will download have a size of ~900Mo.
 
  ftp://ftp.ncbi.nih.gov/pub/mmdb/cdd/fasta.tar.gz
  tar -xzf fasta.tar.gz;
- mkdir pfam
+ mkdir fasta
  mv pfam*.FASTA fasta/
  cd pfam/