bacterial-annotator 0.6.1 → 0.6.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 110718bf7fe99545dd5418522eb463b51e6b483f
-  data.tar.gz: 631d8765e3ecdcdd04497bbbccb589d6ab6688c5
+  metadata.gz: 713193368d710e1a3f78b0279657fab96ded5586
+  data.tar.gz: 82a924362e32d116b029429a00e55a45aa3f8dc7
 SHA512:
-  metadata.gz: cd532e9139c817b75d835bab7cd3124574d311b6484289f8c642c5f823411cdca5427c6088f93f0ed01c291a782ad0100b40f8bfe15d3a75234b6deb7a21ffa6
-  data.tar.gz: 0187bc5c3faa8e52184b00a12496e06ca6cc36b51d995a273a76f4728707e589cd011532f7060ac10146a78f8b466e28dcfd0ebf8552819d3c78a349083c32a6
+  metadata.gz: 9d853a09c8cfbb5e9bfc4525acf4d222ed8c15d601c7b40c0f68d21c724419f773dbe354e161940a04138a59c75c49743165f290f0f4acc1e4a7b15a7d5b9680
+  data.tar.gz: 3772047f7326e06f3cafd73f8776318001b3e53b446a92e144ec30725dd22fc41cb13c08a5f4cb4cc638bbc6b728f4c7af8b8375755f58b44ec42940f589cd6c

data/bin/ba_raxml

@@ -10,17 +10,18 @@
 require 'open-uri'
 
 ROOT_path = File.dirname(__FILE__)
-# raxml_url = https://github.com/stamatak/standard-RAxML/archive/master.zip
+# raxml_url = https://github.com/stamatak/standard-RAxML/archive/v8.2.11.zip
 # Install RAXML on the user system
 def installRaxml
 
   begin
-    resp = open("https://github.com/stamatak/standard-RAxML/archive/master.zip")
+    resp = open("https://github.com/stamatak/standard-RAxML/archive/v8.2.11.zip")
     open("#{ROOT_path}/master.zip", "wb") do |file|
       file.write(resp.read)
     end
     Dir.chdir("#{ROOT_path}/")
     `unzip master.zip && rm master.zip`
+    `mv standard-RAxML-8.2.11 standard-RAxML-master`
     Dir.chdir("#{ROOT_path}/standard-RAxML-master")
     `make -f Makefile.PTHREADS.gcc`
     `rm *.o`

data/bin/bacterial-annotator

@@ -11,6 +11,21 @@
 require 'bacterial-annotator'
 require 'bacterial-comparator'
 
+VERSION = "0.6.1"
+
+def print_version
+  version = "Bacterial Annotator - Version #{VERSION}\n\n"
+  version += "Packaged with : \n"
+  version += "  -- Prodigal v2.6.2\n"
+  version += "  -- BLAT standalone version\n"
+  version += "  -- MAFFT v7.222\n"
+  version += "  -- fasta36  v36.3.8d\n"
+  version += "  -- RAxML v8.2.11\n"
+  version += "  -- FastTree v2.1.10\n"
+  puts version
+end
+
+
 
 # Usage message to print to CLI
 def usage
@@ -29,6 +44,8 @@ bacterial-annotator [annotate | compare] [OPTIONS]
 
   --help/-h		Print this !
 
+  --version/-v  Version of the Bacterial-Annotator
+
 OEM
 
 end
@@ -47,7 +64,7 @@ annotate [OPTIONS]
     --name/-n     <name> Sample name
 
   // MERGEM-based Annotation (Recommended)
-    --db          MERGEM database directory
+    --db/-d          <directory> MERGEM database directory
 
   // Reference-Based Annotation
     --refgenome/-g	<GBK_ID> 	Provide a Genbank file or a Gbk Accession ID.
@@ -56,8 +73,8 @@ annotate [OPTIONS]
 			  Fasta headers need to look similar to NCBI or EBI fasta headers, ex.:
 			  >gi|385721352|gb|AFI72857.1| NDM-1 [Escherichia coli]
 			  >sp|C7C422|BLAN1_KLEPN Beta-lactamase NDM-1 OS=Klebsiella pneumoniae..
-    --pidentity		<% identity> Minimum percentage identity to incorporate a CDS annotation [default=0.7]
-    --pcoverage		<% identity> Minimum percentage of coverage over protein alignment to incorporate a CDS annotation [default=0.7]
+    --pidentity		<% identity> Minimum percentage identity to incorporate a CDS annotation [default=0.8]
+    --pcoverage		<% identity> Minimum percentage of coverage over protein alignment to incorporate a CDS annotation [default=0.8]
 			             .. otherwise hint for a non-functional protein
     --minlength		<length> Minimum contig length for annotation [default=500]
 
@@ -74,8 +91,8 @@ def parseOptions_annotate
 
   # default options
   options[:outdir] = "BAnnotation"
-  options[:pidentity] = 70
-  options[:pcoverage] = 70
+  options[:pidentity] = 80
+  options[:pcoverage] = 80
   options[:minlength] = 500
   options[:meta] = 0
 
@@ -84,6 +101,10 @@ def parseOptions_annotate
     case x.downcase
     when "--input", "-i"
       options[:input] = ARGV.shift
+    when "--name", "-n"
+      options[:name] = ARGV.shift
+    when "--db", "-d"
+      options[:mergem] = ARGV.shift
     when "--refgenome", "-g"
       options[:refgenome] = ARGV.shift
     when "--outdir", "-o"
@@ -101,8 +122,12 @@ def parseOptions_annotate
     when "--externaldb"
       options[:external_db] = ARGV.shift
     when "--help", "-h"
+
       usage_annotate
       abort
+    when "--version", "-v"
+      print_version
+      abort
     end
 
   end
@@ -188,12 +213,11 @@ def parseOptions_compare
 
 end
 
-
 ########
 # MAIN #
 ########
 
-if ARGV.size > 1
+if ARGV.size >= 1
 
   ROOT = File.dirname(__FILE__)
 
@@ -242,11 +266,13 @@ if ARGV.size > 1
     bcomp.mafft_aln aln_opt
     bcomp.raxml_tree aln_opt, options[:bootstrap] if options[:phylogeny] == 1
 
-  else
+  elsif ARGV[0] == "--version" or ARGV[0] == "-v"
 
-    usage
+    print_version
     abort
 
+  else
+    usage
   end
 
 

data/lib/bacterial-annotator.rb

@@ -30,6 +30,10 @@ class BacterialAnnotator
     @options[:pcoverage] = @options[:pcoverage].to_f
     @options[:pcoverage] = @options[:pcoverage] / 100 if @options[:pcoverage] > 1.00
 
+    if ! @options.has_key? :name
+      @options[:name] = @options[:input].gsub(/.fasta|.fa|.fna/,"")
+    end
+
     if File.exists? (@options[:outdir])
       if ! options.has_key? :force
         abort "Output directory already exist ! Choose another one or use -f to overwrite"

data/lib/bacterial-annotator/sequence-synteny.rb

@@ -39,7 +39,6 @@ class SequenceSynteny
       partial = false
       if properties.length >= 2 and properties[1].include? "partial"
         partial = (properties[1].gsub("partial=","")=='01')
-        puts "partial:" + partial.to_s
       end
       sequences[s_name][:partial] = partial
       sequences[s_name][:length] = s.seq.length
@@ -54,9 +53,10 @@ class SequenceSynteny
   # run blat on proteins
   def run_blat root, outdir
     base_cmd = "#{root}/blat.linux -out=blast8 -minIdentity=#{@pidentity}"
-    system("#{base_cmd} #{@subject_file} #{@query_file} #{outdir}/#{@name}.blat8.tsv")
     if @type == "prot"
       system("#{base_cmd} -prot #{@subject_file} #{@query_file} #{outdir}/#{@name}.blat8.tsv")
+    else
+      system("#{base_cmd} #{@subject_file} #{@query_file} #{outdir}/#{@name}.blat8.tsv")
     end
     @aln_file = "#{outdir}/#{@name}.blat8.tsv"
     # extract_hits
@@ -153,57 +153,6 @@ class SequenceSynteny
   end                           # end of method
 
 
-  # Extract Hit from blast8 file and save it in hash
-  # contig-0_1      ABJ71957.1      96.92   65      2       0       1       65      1       65      9.2e-31 131.0
-  def extract_hits_prodigal mode
-
-    @aln_hits = {}
-    feature = ""
-    File.open(@aln_file,"r") do |fread|
-      while l = fread.gets
-        lA = l.chomp!.split("\t")
-        key = lA[0]
-        if mode == :refgenome
-          hit = lA[1]
-          feature = "cds"
-        elsif mode == :externaldb
-          hit = lA[1].chomp.split("|")[3]
-          feature = "cds"
-        end
-        next if lA[2].to_f < @pidentity
-        if ! @aln_hits.has_key? key
-          @aln_hits[key] = {
-            pId: lA[2].to_f.round(2),
-            evalue: lA[10],
-            score: lA[11].to_f,
-            hits: [hit],
-            length: [lA[3].to_i],
-            query_location: [[lA[6].to_i,lA[7].to_i]],
-            subject_location: [[lA[8].to_i,lA[9].to_i]],
-            feature: feature
-          }
-        elsif lA[11].to_f > @aln_hits[key][:score]
-          @aln_hits[key] = {
-            pId: lA[2].to_f.round(2),
-            evalue: lA[10],
-            score: lA[11].to_f,
-            hits: [hit],
-            length: [lA[3].to_i],
-            query_location: [[lA[6].to_i,lA[7].to_i]],
-            subject_location: [[lA[8].to_i,lA[9].to_i]],
-            feature: feature
-          }
-        elsif lA[11].to_f == @aln_hits[key][:score]
-          @aln_hits[key][:hits] << hit
-          @aln_hits[key][:length] << lA[3].to_i
-          @aln_hits[key][:query_location] << [lA[6].to_i,lA[7].to_i]
-          @aln_hits[key][:subject_location] << [lA[8].to_i,lA[9].to_i]
-        end
-      end
-    end
-
-  end                           # end of method
-
   # Extract Hit from blast8 file and save it in hash
   # prpa    PA0668.4|rRNA|23S       99.97   2891    1       0       705042  707932  1       2891    0.0e+00 5671.0
   def extract_hits_dna mode

data/lib/bacterial-comparator.rb

@@ -247,7 +247,7 @@ class BacterialComparator
       puts "..Prot alignment files already exists, skipping."
     end
 
-    # ugly hack to find out the reference genome
+    # FIXME ugly hack to find out the reference genome
     ref_id = Dir["#{ori_dir}/#{@genomes_list[0]}/*.pep"][0].split('/')[-1].gsub(".pep","")
 
     concat_alignments "align-genes-pep.all.fasta", ref_id

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bacterial-annotator
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.6.2
 platform: ruby
 authors:
 - Maxime Deraspe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-18 00:00:00.000000000 Z
+date: 2017-10-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio