bacterial-annotator 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4dbc3b5e016a3f24ba82ab525a0c8daa9617afec
-  data.tar.gz: 7c8ba281632d84d7131cf1a27e143f596e76f414
+  metadata.gz: 34d344cebc006441522c54fa91a021c43c180299
+  data.tar.gz: e3902d68c0e931a4054dddd4d36ac08b5c57ec98
 SHA512:
-  metadata.gz: 73f72513dc9964c46c73ef39477a9b5148b010d68449ff270f5b15f556a5e56e027a9ddb80149b2ce44e12c09466ac11267c118c97c8ea8892eb582d220588cf
-  data.tar.gz: 0a92c0ceec70a12500a8dcf4433d76eff7edf2e4fe7ca180151efc016ee81a3e7a6279cc633a6adaaec5936425908c3a4299742ae1571bc1970017a058a8dedb
+  metadata.gz: e6104a764e106f3740410bd7e9a11f5d49e345b32797c854013dcc9a91fbd2540072f32fb85020896e8534eb2427fbdb6853ece60a123cd77a4f1c085fc34272
+  data.tar.gz: 1fc359b7523c87f66dcfd020092fc21b1691e8029bfa4684b35515f98b8f72c3160e2ef9d7aefc541f1eb91a803b1db839c02c24744d5e992fd6a2720b685b87

data/bin/ba_mafft

@@ -0,0 +1,48 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8 -*-
+# author:  	maxime déraspe
+# email:	maxime@deraspe.net
+# review:  	
+# date:    	15-02-24
+# version: 	0.01
+# licence:  	
+
+require 'open-uri'
+
+ROOT_path = File.dirname(__FILE__)
+# mafft_url = http://mafft.cbrc.jp/alignment/software/mafft-7.222-without-extensions-src.tgz
+# Install MAFFT on the user system
+def installMafft
+
+  begin
+    resp = open("http://mafft.cbrc.jp/alignment/software/mafft-7.222-without-extensions-src.tgz")
+    open("#{ROOT_path}/mafft-7.222-without-extensions-src.tgz", "wb") do |file|
+      file.write(resp.read)
+    end
+    Dir.chdir("#{ROOT_path}/")
+    `tar xvf mafft-7.222-without-extensions-src.tgz`
+    Dir.chdir("#{ROOT_path}/mafft-7.222-without-extensions/core")
+    `make`
+    `make install PREFIX=$(pwd -P)/../`
+    `echo '#! /bin/sh' > #{ROOT_path}/mafft.linux`
+    `echo export MAFFT_BINARIES=$(pwd -P)/../binaries >> #{ROOT_path}/mafft.linux`
+    `tail -n +2 #{ROOT_path}/mafft-7.222-without-extensions/bin/mafft >> #{ROOT_path}/mafft.linux`
+    File.chmod(0755, "#{ROOT_path}/mafft.linux")
+  rescue
+    abort "Problem in stalling MAFFT, aborting"
+  end
+
+end
+
+
+# Install prodigal if not already install
+if ! File.exists? "#{ROOT_path}/mafft.linux"
+
+  puts "Installing MAFFT 7.222 the aligner.."
+  puts "See http://mafft.cbrc.jp/alignment/software/"
+  puts "License BSD : http://mafft.cbrc.jp/alignment/software/license.txt"
+  installMafft
+  puts "MAFFT successfully installed in #{ROOT_path}/mafft-7.222-without-extensions"
+  puts ""
+
+end

data/bin/bacterial-annotator

@@ -9,6 +9,7 @@
 
 
 require 'bacterial-annotator'
+require 'bacterial-comparator'
 
 
 # Usage message to print to CLI
@@ -16,46 +17,61 @@ def usage
 
   print <<OEM
 
-bacterial-annotator [OPTIONS]
+bacterial-annotator [annotate | compare] [OPTIONS]
 
-[OPTIONS]
+# Choose either to annotate a genome or compare several genome annotations
 
-// IO
+  annotate  [OPTIONS]
+            .. see annotate -h for OPTIONS
 
-  --input/-i		<fasta_file>	Provide the fasta file to annotate
-  --outdir/-o		<outdir>	Output directory [default=BAnnotation]
-  --force/-f		Force to overwrite the output directory
+  compare   [OPTIONS] [all annotation directories]*
+            .. see compare -h for OPTIONS
+
+  --help/-h		Print this !
+
+OEM
+
+end
 
-// Dataset
 
-  --refgenome/-g        <GBK_ID> 	Provide a Genbank file or a Gbk Accession ID.
-  --guessref		Will guess the best reference genome to use for the annotation.
+def usage_annotate
 
-  --remotedb		<remote_database> [nr|refseq|swissprot]
-			Complete the annotation of remaining CDS with a remote NCBI BLAST
-			Can be very slow, better to use an external database !
+  print <<OEM
 
-  --externaldb		<proteins fasta_file>
-			Complete or do the annotation of remaining CDS with this database (a protein fasta file).
-			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..
+annotate [OPTIONS]
 
-// Other options
+  // IO
+    --input/-i		<fasta_file>	Provide the fasta file to annotate
+    --outdir/-o		<outdir>	Output directory [default=BAnnotation]
+    --force/-f		Force to overwrite the output directory
 
-  --pidentity		Minimum percentage identity to incorporate a CDS annotation [default=0.7]
-  --minlength		Minimum contig length for annotation [default=500]
+  // Dataset
+    --refgenome/-g        <GBK_ID> 	Provide a Genbank file or a Gbk Accession ID.
+    --guessref		Will guess the best reference genome to use for the annotation.
 
-  --meta		Better for metagenome and plasmid annotations because of disparate codon usage [default=off]
-  --gff			Will also generate gff annotation files [off by default]
+    --remotedb		<remote_database> [nr|refseq|swissprot]
+			  Complete the annotation of remaining CDS with a remote NCBI BLAST
+			  Can be very slow, better to use an external database !
+
+    --externaldb		<proteins fasta_file>
+			  Complete or do the annotation of remaining CDS with this database (a protein fasta file).
+			  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..
+
+  // Other options
+    --pidentity		Minimum percentage identity to incorporate a CDS annotation [default=0.7]
+    --minlength		Minimum contig length for annotation [default=500]
+
+    --meta		Better for metagenome and plasmid annotations because of disparate codon usage [default=off]
+    --gff			Will also generate gff annotation files [off by default]
 
-  --help/-h		Print this !
 OEM
 
 end
 
 # Parse the Options given on the CLI
-def parseOptions
+def parseOptions_annotate
 
   options = {}
 
@@ -89,7 +105,73 @@ def parseOptions
     when "--externaldb"
       options[:external_db] = ARGV.shift
     when "--help", "-h"
-      usage
+      usage_annotate
+      abort
+    end
+
+  end
+
+  options
+
+end
+
+
+def usage_compare
+
+  print <<OEM
+
+compare [OPTIONS]
+
+  //IO
+    --outdir/-o    <output directory>
+    --proc         <nb of process> Number of process to run the comparison
+
+  //Synteny
+    --pidentity    <default 0.80> Minimal percentage identity to call a syntenic protein
+    --min_cov      <default 0.80> Minimal coverage for the alignment of the protein / gene
+
+  //Alignment (MAFFT)
+    --align        [dna|prot|both] by default align only proteins
+    --concat       <nb of genes | all>  by default all
+
+  //Phylo (RAXML)
+
+OEM
+
+end
+
+
+# Parse the Options given on the CLI
+def parseOptions_compare
+
+  options = {}
+
+  # default options
+  options[:outdir] = "phylogenomics"
+  options[:pidentity] = 0.8
+  options[:min_cov] = 0.8
+  options[:proc] = 2
+  options[:align] = "prot"
+  options[:genomes_list] = []
+
+  while x = ARGV.shift
+
+    case x.downcase
+    when "--outdir", "-o"
+      options[:outdir] = ARGV.shift
+    when "--pidentity"
+      options[:pidentity] = ARGV.shift
+    when "--min_cov"
+      options[:min_cov] = ARGV.shift
+    when "--proc", "-p"
+      options[:proc] = ARGV.shift
+    when "--align"
+      options[:align] = ARGV.shift
+    when "--help", "-h"
+      usage_compare
+      abort
+    else
+      options[:genomes_list] << x if File.exists? "#{x}"
     end
 
   end
@@ -103,28 +185,60 @@ end
 if ARGV.size > 1
 
   ROOT = File.dirname(__FILE__)
-  options = parseOptions
 
-  # Check for 3rd party dependencies : Prodigal and Blat
+  # Check for 3rd party dependencies : Prodigal, Blat, MAFFT
   system("ba_prodigal")
   system("ba_blat")
+  system("ba_mafft")
 
-  if ! File.exist? ("#{ROOT}/blat.linux")
-    abort "exiting blat is missing"
-  end
+  options = {}
+  genomes_list = []
+
+  if ARGV[0] == "annotate"
+
+    ARGV.shift
+    options = parseOptions_annotate
+
+    if ! File.exist? ("#{ROOT}/blat.linux")
+      abort "#exiting blat is missing"
+    end
+
+    # Check Options
+    if ! options.has_key? :refgenome and
+       ! options.has_key? :remote_db and
+       ! options.has_key? :external_db
+      puts "You didn't provide a reference genome or a database for the annotation !"
+    elsif ! options.has_key? :input
+      puts "You didn't provide a fasta file to annotate !"
+    elsif
+      puts ""
+    end
+
+    bannot = BacterialAnnotator.new(options, ROOT)
+    bannot.prepare_files_for_annotation
+    bannot.run_annotation
+
+  elsif ARGV[0] == "compare"
+
+    ARGV.shift
+    options = parseOptions_compare
+    bcomp = BacterialComparator.new(options, ROOT)
+    if options[:align].downcase == "both"
+      bcomp.mafft_align_all_pep
+      bcomp.mafft_align_all_dna
+    elsif options[:align].downcase == "prot"
+      bcomp.mafft_align_all_pep
+    elsif options[:align].downcase == "dna"
+      bcomp.mafft_align_all_dna
+    end
+
+  else
+
+    usage
+    abort
 
-  # Check Options
-  if ! options.has_key? :refgenome and ! options.has_key? :remote_db and ! options.has_key? :external_db
-    puts "You didn't provide a reference genome or a database for the annotation !"
-  elsif ! options.has_key? :input
-    puts "You didn't provide a fasta file to annotate !"
-  elsif
-    puts ""
   end
 
-  bannot = BacterialAnnotator.new(options, ROOT)
-  bannot.prepare_files_for_annotation
-  bannot.run_annotation
 
 else
   usage

data/lib/bacterial-annotator/genbank-manip.rb

@@ -57,14 +57,18 @@ class GenbankManip
         product = ftH["product"] if !ftH["product"].nil?
         protId = ftH["protein_id"][0] if !ftH["protein_id"].nil?
         locustag = ftH["locus_tag"][0] if !ftH["locus_tag"].nil?
-        if ftH.has_key? "translation"
-          pep = ftH["translation"][0] if !ftH["translation"].nil?
-        else
-          dna = get_DNA(ft,@bioseq)
-          pep = dna.translate
-        end
 
+        # if ftH.has_key? "translation"
+        #   pep = ftH["translation"][0] if !ftH["translation"].nil?
+        # else
+        #   dna = get_DNA(ft,@bioseq)
+        #   pep = dna.translate
+        # end
+
+        dna = get_DNA(ft,@bioseq)
+        pep = dna.translate
         pepBioSeq = Bio::Sequence.auto(pep)
+        dnaBioSeq = Bio::Sequence.auto(dna)
 
         if protId.strip == ""
           protId = locustag
@@ -75,7 +79,8 @@ class GenbankManip
                                locustag: locustag,
                                gene: gene[0],
                                product: product[0],
-                               bioseq: pepBioSeq }
+                               bioseq: pepBioSeq,
+                               bioseq_gene: dnaBioSeq}
       end
 
     end
@@ -90,16 +95,22 @@ class GenbankManip
   def write_cds_to_file outdir
 
     cds_file = "#{@gbk.accession}.pep"
+    dna_file = "#{@gbk.accession}.dna"
+
     if @coding_seq == nil
       get_cds
     end
 
+    dna_out = File.open("#{outdir}/#{dna_file}", "w")
     File.open("#{outdir}/#{cds_file}", "w") do |fwrite|
       @coding_seq.each_key do |k|
         seqout = @coding_seq[k][:bioseq].output_fasta("#{k}",60)
+        seqout_dna = @coding_seq[k][:bioseq_gene].output_fasta("#{k}",60)
         fwrite.write(seqout)
+        dna_out.write(seqout_dna)
       end
     end
+    dna_out.close
 
     @cds_file = "#{outdir}/" + cds_file
 
@@ -202,7 +213,7 @@ class GenbankManip
     Bio::NCBI.default_email = 'default@default.com'
     ncbi = Bio::NCBI::REST.new
     genbankstring = ncbi.efetch(refgenome_id, {"db"=>'nucleotide', "rettype"=>'gb'})
-    File.open("#{outdir}/#{refgenome_id}.gbk", "w") do |f| 
+    File.open("#{outdir}/#{refgenome_id}.gbk", "w") do |f|
       f.write(genbankstring)
     end
   end

data/lib/bacterial-comparator.rb

@@ -0,0 +1,221 @@
+# -*- coding: utf-8 -*-
+# author:  	maxime déraspe
+# email:	maxime@deraspe.net
+# review:  	
+# date:    	15-02-24
+# version: 	0.0.1
+# licence:  	
+
+require 'bio'
+require 'fileutils'
+require 'parallel'
+
+class BacterialComparator
+
+  attr_reader :genomes_list, :stats
+
+  # Initialize BacterialAnnotator
+  # options[:input], options[:refgenome], ROOT, options[:outdir], options)
+  def initialize options, root
+
+    @root = root
+    @outdir = options[:outdir]
+    Dir.mkdir(@outdir) if ! Dir.exists? @outdir
+    @genomes_list = options[:genomes_list]
+    @proc = options[:proc].to_i
+
+    min_cov = options[:min_cov].to_f
+    min_pid = options[:pidentity].to_f
+    if min_cov > 1
+      min_cov = min_cov/100
+    end
+    if min_pid > 1
+      min_pid = min_pid/100
+    end
+
+    @ref_prot = get_ref_prot
+    @synteny = read_prot_synteny
+    @stats = extract_syntenic_fasta min_cov, min_pid
+
+  end
+
+  def read_prot_synteny
+    synteny = {}
+    @genomes_list.each do |g|
+      puts "#{g}/Prot-Synteny.tsv"
+      file = File.open("#{g}/Prot-Synteny.tsv", "r")
+      l = file.gets             # skip header
+      while l = file.gets
+        # AAK98805.1      spr0001 453     1.0     100.0   ABAC01000005_14 453     1.0
+        lA = l.chomp.split("\t")
+        synteny[lA[0]] =  [] if ! synteny.has_key? lA[0]
+        synteny[lA[0]] << {ref_cov: lA[3].to_f, pId: lA[4].to_f, query_prot: lA[5], query_cov: lA[7].to_f}
+      end
+      file.close
+    end
+    synteny
+  end
+
+  def get_ref_prot
+    ref_prot = []
+    pep_file = Dir["#{@genomes_list[0]}/*.pep"]
+    flatfile = Bio::FlatFile.auto("#{pep_file[0]}")
+    flatfile.each_entry do |entry|
+      ref_prot << entry.definition.split(" ")[0]
+    end
+    ref_prot
+  end
+
+
+  def get_sequence_from_flatfile flatfile, name
+
+    out = ""
+    flatfile.each_entry do |entry|
+      if entry.definition.split(" ")[0] == name
+        bioseq = Bio::Sequence.auto(entry.seq)
+        out = bioseq.output_fasta("#{name}",60)
+      end
+    end
+    out
+
+  end
+
+
+  def build_multifasta ref_prot, synteny
+
+    pep_out_dir = "./#{@outdir}/genes-align-pep"
+    dna_out_dir = "./#{@outdir}/genes-align-dna"
+
+    # create multifasta by syntenic proteins (pep)
+    if ! File.exists? pep_out_dir+"/#{ref_prot}.pep"
+      pep_out = File.open(pep_out_dir+"/#{ref_prot}.pep", "w")
+      pep_file = Dir["#{@genomes_list[0]}/*.pep"]
+      flatfile = Bio::FlatFile.auto("#{pep_file[0]}")
+      pep_out.write(get_sequence_from_flatfile flatfile, ref_prot)
+      @genomes_list.each_with_index do |g,i|
+        flatfile = Bio::FlatFile.auto("#{g}/Proteins.fa")
+        pep_out.write(get_sequence_from_flatfile flatfile, synteny[i][:query_prot])
+      end
+      pep_out.close
+    end
+
+    # create multifasta by syntenic genes (dna)
+    if ! File.exists? dna_out_dir+"/#{ref_prot}.dna"
+      dna_out = File.open(dna_out_dir+"/#{ref_prot}.dna", "w")
+      # create multifasta by syntenic proteins
+      dna_file = Dir["#{@genomes_list[0]}/*.dna"]
+      flatfile = Bio::FlatFile.auto("#{dna_file[0]}")
+      dna_out.write(get_sequence_from_flatfile flatfile, ref_prot)
+      @genomes_list.each_with_index do |g,i|
+        flatfile = Bio::FlatFile.auto("#{g}/Genes.fa")
+        dna_out.write(get_sequence_from_flatfile flatfile, synteny[i][:query_prot])
+      end
+      dna_out.close
+    end
+
+  end
+
+
+  def extract_syntenic_fasta min_cov, min_pid
+
+    "# Extracting Proteins and Genes multifasta.."
+    nb_of_syntenic = 0
+    stats = {}
+    stats[:syntenic] = []
+    fout = File.open("#{@outdir}/cds-synteny.tsv", "w")
+    fout.write("Gene\t"+@genomes_list.join("\t")+"\n")
+
+    to_build_multifasta = []
+
+    @synteny.each do |k,v|
+      is_syntenic = 1
+      v.each do |v_|
+        if v_[:query_cov].nil?
+          is_syntenic = 0
+          break
+        elsif v_[:query_cov] > min_cov and
+             v_[:ref_cov] > min_cov and
+             v_[:pId] > min_pid
+        # synteny -> great !
+        else
+          is_syntenic = 0
+          break
+        end
+      end
+
+      if is_syntenic == 1
+        nb_of_syntenic += 1
+        # build_multifasta k, v
+        to_build_multifasta << [k,v]
+        fout.write("#{k}")
+        v.each do |x|
+          fout.write("\t#{x[:query_prot]}|#{x[:query_cov]}|#{x[:ref_cov]}")
+          stats[:syntenic] << k
+        end
+        fout.write("\n")
+      end
+
+    end
+
+    fout.close
+
+    pep_out_dir = "./#{@outdir}/genes-align-pep"
+    dna_out_dir = "./#{@outdir}/genes-align-dna"
+    Dir.mkdir(pep_out_dir) if ! Dir.exists? pep_out_dir
+    Dir.mkdir(dna_out_dir) if ! Dir.exists? dna_out_dir
+
+    Parallel.map(to_build_multifasta, in_processes: @proc) { |k,v|
+      build_multifasta k, v
+    }
+
+    stats[:nb_of_syntenic] = nb_of_syntenic
+    puts "Syntenic genes : " + nb_of_syntenic.to_s + " / " + @ref_prot.length.to_s
+
+  end
+
+
+  def mafft_align f
+
+    trying = 0
+    begin
+      cmd = system("#{@root}/mafft.linux --quiet #{f} > #{f}.aln")
+      if File.size("#{f}.aln") == 0
+        puts "File size of 0.. --#{f}--"
+        puts "Command used : #{@root}/mafft.linux --quiet #{f} > #{f}.aln"
+        fail
+      else
+        status = "OK"
+        status = "FAILED" if cmd != true
+        puts "Alignment #{f} : #{status}"
+      end
+    rescue
+      if trying < 3
+        trying += 1
+        retry
+      end
+      status = "FAILED"
+      puts "Alignment #{f} : #{status}"
+    end
+
+  end
+
+  def mafft_align_all_pep
+    puts "# MAFFT multialign all protein sequences.."
+    Dir.chdir("#{@outdir}/genes-align-pep/")
+    Parallel.map(Dir["*.pep"], in_processes: @proc) { |f|
+      mafft_align f
+    }
+  end
+
+  def mafft_align_all_dna
+    puts "# MAFFT multialign all gene sequences.."
+    puts "# MAFFT multialign all protein sequences.."
+    Dir.chdir("#{@outdir}/genes-align-dna/")
+    Parallel.map(Dir["*.dna"], in_processes: @proc) { |f|
+      mafft_align f
+    }
+  end
+
+
+
+end                             # end of Class

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bacterial-annotator
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Maxime Deraspe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-09-21 00:00:00.000000000 Z
+date: 2016-10-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio
@@ -50,6 +50,26 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 2.7.3
+- !ruby/object:Gem::Dependency
+  name: parallel
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.9.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.9.0
 description: GEM to annotate bacterial genome sequence based on a reference genome
   and complete the annotation with an external database or a remote database.
 email: maxime@deraspe.net
@@ -57,10 +77,12 @@ executables:
 - bacterial-annotator
 - ba_prodigal
 - ba_blat
+- ba_mafft
 extensions: []
 extra_rdoc_files: []
 files:
 - bin/ba_blat
+- bin/ba_mafft
 - bin/ba_prodigal
 - bin/bacterial-annotator
 - lib/bacterial-annotator.rb
@@ -68,6 +90,7 @@ files:
 - lib/bacterial-annotator/genbank-manip.rb
 - lib/bacterial-annotator/remote-ncbi.rb
 - lib/bacterial-annotator/synteny-manip.rb
+- lib/bacterial-comparator.rb
 homepage: http://rubygems.org/gems/bacterial-annotator
 licenses:
 - GPL-3.0