Fix #1 update taxonomy db creation

marieBvr · Jul 5, 2021 · fa9f6a7 · fa9f6a7
1 parent 070640d
commit fa9f6a7
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 24 deletions.
diff --git 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
@@ -44,6 +44,8 @@ Perl external libraries
 * String::Random
 * Bio::SearchIO:blastxml
 * Bio::SeqIO
+* Expect
+* GD:Simple
 
 
 Perl included libraries
@@ -116,15 +118,15 @@ 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.
 
 Launch the loadTaxonomy.pl script that will create the sqlite database. The script needs two provided sqlite files: ``taxonomyIndex.sql`` and ``taxonomyStructure.sql`` that describe the database struture. All these files are in virAnnot/db/.
 
 .. 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/