bacterial-annotator 0.6.2 → 0.6.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 713193368d710e1a3f78b0279657fab96ded5586
-  data.tar.gz: 82a924362e32d116b029429a00e55a45aa3f8dc7
+  metadata.gz: bc9bbbe5d2c03c4019290cf077f7ac21c6b0d687
+  data.tar.gz: 746d312f4891d7a561d00b1c6299cb57750daa7f
 SHA512:
-  metadata.gz: 9d853a09c8cfbb5e9bfc4525acf4d222ed8c15d601c7b40c0f68d21c724419f773dbe354e161940a04138a59c75c49743165f290f0f4acc1e4a7b15a7d5b9680
-  data.tar.gz: 3772047f7326e06f3cafd73f8776318001b3e53b446a92e144ec30725dd22fc41cb13c08a5f4cb4cc638bbc6b728f4c7af8b8375755f58b44ec42940f589cd6c
+  metadata.gz: 1dbde919ea570e01223a48ec6f357d77d88ce62502ad0d09a9ba465a5bc4becb11a4caa5f6e8accf721e5c21780118f46c427b99abe1512bfce8e2a27c329a59
+  data.tar.gz: 708a2a03d84dcc46f10a921deaca1705fdd0091b00cd096971bf5436d443d244d31740d5012caf916a045b56b7c35ad73c45abefdee6a59d29abc9f7a8664c1d

data/bin/bacterial-annotator

@@ -11,7 +11,7 @@
 require 'bacterial-annotator'
 require 'bacterial-comparator'
 
-VERSION = "0.6.1"
+VERSION = "0.6.2"
 
 def print_version
   version = "Bacterial Annotator - Version #{VERSION}\n\n"
@@ -61,7 +61,7 @@ annotate [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
-    --name/-n     <name> Sample name
+    --name/-n		<name> Sample name
 
   // MERGEM-based Annotation (Recommended)
     --db/-d          <directory> MERGEM database directory
@@ -249,8 +249,6 @@ if ARGV.size >= 1
       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)

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

@@ -38,7 +38,7 @@ class SequenceSynteny
       properties = s.definition.chomp.split(";")
       partial = false
       if properties.length >= 2 and properties[1].include? "partial"
-        partial = (properties[1].gsub("partial=","")=='01')
+        partial = (properties[1].gsub("partial=","").include? '1')
       end
       sequences[s_name][:partial] = partial
       sequences[s_name][:length] = s.seq.length
@@ -52,7 +52,7 @@ class SequenceSynteny
 
   # run blat on proteins
   def run_blat root, outdir
-    base_cmd = "#{root}/blat.linux -out=blast8 -minIdentity=#{@pidentity}"
+    base_cmd = "#{root}/blat.linux -out=blast8 -minIdentity=#{@pidentity} > /dev/null 2>&1"
     if @type == "prot"
       system("#{base_cmd} -prot #{@subject_file} #{@query_file} #{outdir}/#{@name}.blat8.tsv")
     else

data/lib/bacterial-annotator.rb

@@ -12,7 +12,7 @@ require 'fileutils'
 require 'bacterial-annotator/sequence-fasta'
 require 'bacterial-annotator/sequence-annotation'
 require 'bacterial-annotator/sequence-synteny'
-
+require 'helper'
 
 class BacterialAnnotator
 
@@ -79,13 +79,16 @@ class BacterialAnnotator
   # Prepare files for the annotation
   # Will run prodigal on the query and prepare reference genome files
   def prepare_files_for_annotation
-    puts "\nRunning Prodigal on your genome.."
+    print "# Running Prodigal on your genome.."
+    start_time = Time.now
     @query_fasta.run_prodigal @root, @options[:outdir]
-    puts "Prodigal done."
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time - start_time)
+    print "done (#{c_time})\n"
     if @with_refence_genome
       @ref_genome.write_cds_to_file @options[:outdir]
       @ref_genome.write_rna_to_file @options[:outdir]
-      puts "Successfully loaded #{@ref_genome.gbk.definition}"
+      # puts "Successfully loaded #{@ref_genome.gbk.definition}"
     end
   end                           # end of method
 
@@ -95,7 +98,12 @@ class BacterialAnnotator
     ref_synteny_prot = SequenceSynteny.new(@query_fasta.annotation_files[:proteins], @ref_genome.cds_file,
                                            "Prot-Ref", @options[:pidentity], @options[:pcoverage], "prot")
 
+    print "# Running alignment with Reference Genome CDS (blat).."
+    start_time = Time.now
     ref_synteny_prot.run_blat @root, @options[:outdir]
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time - start_time)
+    print "done (#{c_time})\n"
 
     ref_synteny_prot.extract_hits :refgenome
 
@@ -145,10 +153,14 @@ class BacterialAnnotator
       dump_ref_synteny_to_file
 
       # run RNA annotation
-      puts "\nRunning BLAT alignment with Reference Genome RNA.."
       @rna_synteny = SequenceSynteny.new(@query_fasta.fasta_file, @ref_genome.rna_file,
                                          "RNA-Ref", @options[:pidentity], @options[:pcoverage], "dna")
+      print "# Running alignment with Reference Genome RNA (blat).."
+      start_time = Time.now
       @rna_synteny.run_blat @root, @options[:outdir]
+      end_time = Time.now
+      c_time = Helper.sec2str(end_time-start_time)
+      print "done (#{c_time})\n"
       @rna_synteny.extract_hits_dna :rna
       @contig_annotations_rna = {}
       @query_fasta.annotation_files[:contigs].each_with_index do |contig, contig_index|
@@ -168,9 +180,9 @@ class BacterialAnnotator
     # Parse annotations to genbank files
     parse_genbank_files
 
-    puts "\nPrinting Statistics.."
+    print "# Printing Statistics.."
     print_stats "#{@options[:outdir]}"
-
+    print "done\n"
 
   end                           # end of method
 
@@ -188,7 +200,7 @@ class BacterialAnnotator
                                                 "Prot-ExternalDB", @options[:pidentity],
                                                 @options[:pcoverage], "prot")
 
-      puts "\nRunning BLAT alignment with External Database.."
+      puts "# Running BLAT alignment with External Database.."
       @externaldb_synteny.run_blat @root, @options[:outdir]
       @externaldb_synteny.extract_hits :externaldb
 
@@ -237,7 +249,8 @@ class BacterialAnnotator
   # parse all genbank files
   def parse_genbank_files
 
-    puts "\nParsing annotation into genbank files.."
+    print "# Parsing annotation into genbank files.."
+    start_time = Time.now
     @contig_annotations_cds.each do |contig, contig_prots|
 
       gbk_path = @query_fasta.annotation_files[:gbk_path]
@@ -265,7 +278,9 @@ class BacterialAnnotator
       gbk_to_annotate.save_genbank_to_file gbk_path
 
     end
-
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
   end                           # end of method
 
 
@@ -505,18 +520,21 @@ class BacterialAnnotator
 
     # Iterate over each Ref protein and print syntheny
     synteny_file = File.open("#{@options[:outdir]}/Prot-Synteny.tsv","w")
-    synteny_file.write("RefLocusTag\tRefProtID\tRefLength\tRefCoverage\tIdentity\tQueryGene\tQueryLength\tQueryCoverage\n")
+    synteny_file.write("RefLocusTag\tRefProtID\tRefLength\tRefCoverage\tIdentity\tQueryGene\tQueryLength\tQueryCoverage\tQueryPartial\n")
     ref_annotated = {}
 
     @prot_synteny_refgenome.query_sequences.each do |prot, syn_val|
       next if ! syn_val.has_key? :homology
+      next if syn_val[:homology][:assert_cutoff].inject(:+) < 3
+      next if ref_annotated.has_key? syn_val[:homology][:hits][0] and ref_annotated[syn_val[:homology][:hits][0]][:partial] == 0
       ref_annotated[syn_val[:homology][:hits][0]] = {
         key: prot,
         pId: syn_val[:homology][:pId],
         cov_query: syn_val[:homology][:cov_query],
         cov_subject: syn_val[:homology][:cov_subject],
         assert_cutoff: syn_val[:homology][:assert_cutoff],
-        length: syn_val[:homology][:length][0]
+        length: syn_val[:homology][:length][0],
+        partial: (syn_val[:partial] ? 1 : 0)
       }
     end
 
@@ -539,6 +557,7 @@ class BacterialAnnotator
         query_length = @query_fasta.annotation_files[:prot_ids_length][gene]
         coverage_query = ref_annotated[ref_v[:protId]][:cov_query]
         pId = ref_annotated[ref_v[:protId]][:pId]
+        partial = ref_annotated[ref_v[:protId]][:partial]
       end
 
       synteny_file.write(ref_v[:protId])
@@ -549,6 +568,7 @@ class BacterialAnnotator
       synteny_file.write("\t"+gene)
       synteny_file.write("\t"+query_length.to_s)
       synteny_file.write("\t"+coverage_query.to_s)
+      synteny_file.write("\t"+partial.to_s)
       synteny_file.write("\n")
 
     end

data/lib/bacterial-comparator.rb

@@ -9,6 +9,7 @@
 require 'bio'
 require 'fileutils'
 require 'parallel'
+require 'helper'
 
 class BacterialComparator
 
@@ -40,15 +41,16 @@ class BacterialComparator
   end
 
   def read_prot_synteny
-    puts "# Reading genomes synteny files (from genome annotations) .."
+
+    print "# Reading genome synteny files - from genome annotations.."
+    start_time = Time.now
     synteny = {}
     @genomes_list.each do |g|
-      puts "   #{g}/Prot-Synteny.tsv"
       genome_synteny = []
       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
+        # AAK98805.1      spr0001 453     1.0     100.0   ABAC01000005_14 453     1.0	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}
@@ -61,7 +63,12 @@ class BacterialComparator
       end
       file.close
     end
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
+
     synteny
+
   end
 
   def get_ref_prot
@@ -76,62 +83,72 @@ class BacterialComparator
   end
 
 
-  def get_sequence_from_flatfile flatfile, name
+  # load all id => sequences from multifasta
+  def load_genome_cds file
 
-    out = ""
+    proteins = {}
+    flatfile = Bio::FlatFile.auto(file)
     flatfile.each_entry do |entry|
-      if entry.definition.split(" ")[0] == name
-        bioseq = Bio::Sequence.auto(entry.seq)
-        out = bioseq.output_fasta("#{name}",60)
-      end
+      name = entry.definition.split(" ")[0]
+      bioseq = Bio::Sequence.auto(entry.seq)
+      out = bioseq.output_fasta("#{name}",60)
+      proteins[name] = out
     end
-    out
+
+    proteins
 
   end
 
 
-  def build_multifasta ref_prot, synteny
+  def build_multifasta synteny_list
 
     pep_out_dir = "./#{@outdir}/align-genes-pep"
-    dna_out_dir = "./#{@outdir}/align-genes-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)
-      flatfile.close
-      @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])
-        flatfile.close
-      end
+    ref_proteins = load_genome_cds(Dir["#{@genomes_list[0]}/*.pep"][0])
+    synteny_list.each do |k,v|
+      pep_out = File.open(pep_out_dir+"/#{k}.pep", "w")
+      pep_out.write(ref_proteins[k])
       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)
-      flatfile.close
-      @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])
-        flatfile.close
+    @genomes_list.each_with_index do |g,i|
+
+      genome_proteins = load_genome_cds("#{g}/Proteins.fa")
+      synteny_list.each do |k,v|
+        pep_out = File.open(pep_out_dir+"/#{k}.pep", "a")
+        pep_out.write(genome_proteins[v[i][:query_prot]])
+        pep_out.close
       end
+
+    end
+
+    dna_out_dir = "./#{@outdir}/align-genes-dna"
+    ref_genes = load_genome_cds(Dir["#{@genomes_list[0]}/*.dna"][0])
+    synteny_list.each do |k,v|
+      dna_out = File.open(dna_out_dir+"/#{k}.dna", "w")
+      dna_out.write(ref_genes[k])
       dna_out.close
     end
 
-  end
+    @genomes_list.each_with_index do |g,i|
+
+      genome_genes = load_genome_cds("#{g}/Genes.fa")
+      synteny_list.each do |k,v|
+        dna_out = File.open(dna_out_dir+"/#{k}.dna", "a")
+        dna_out.write(genome_genes[v[i][:query_prot]])
+        dna_out.close
+      end
+
+    end
 
+  end
 
+  # extract and dump multifasta for syntenic genes and proteins
   def extract_syntenic_fasta min_cov, min_pid
 
-    puts "# Extracting Proteins and Genes multifasta.."
+    print "# Extracting Proteins and Genes multifasta.."
+    start_time = Time.now
+
     nb_of_syntenic = 0
     stats = {}
     stats[:syntenic] = []
@@ -141,6 +158,7 @@ class BacterialComparator
     to_build_multifasta = []
 
     @synteny.each do |k,v|
+
       is_syntenic = 1
       v.each do |v_|
         if v_[:query_cov] == "-"
@@ -186,12 +204,18 @@ class BacterialComparator
     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
+    synteny_list = to_build_multifasta.each_slice((to_build_multifasta.length/@proc)+1).to_a
+
+    Parallel.map(synteny_list, in_processes: @proc) { |list|
+      build_multifasta list
     }
 
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
+
     stats[:nb_of_syntenic] = nb_of_syntenic
-    puts "Syntenic genes : " + nb_of_syntenic.to_s + " / " + @ref_prot.length.to_s
+    #puts "   Syntenic genes : " + nb_of_syntenic.to_s + " / " + @ref_prot.length.to_s
 
   end
 
@@ -224,7 +248,9 @@ class BacterialComparator
 
   def mafft_align_all_pep
 
-    puts "# MAFFT multialign all protein sequences.."
+    print "# Sequence alignments - conserved single proteins a.a. (MAFFT).."
+    start_time = Time.now
+
     ori_dir = Dir.pwd
     Dir.chdir("#{@outdir}/align-genes-pep/")
 
@@ -243,10 +269,12 @@ class BacterialComparator
       Parallel.map(Dir["*.pep"], in_processes: @proc) { |f|
         mafft_align f
       }
-    else
-      puts "..Prot alignment files already exists, skipping."
     end
 
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
+
     # FIXME ugly hack to find out the reference genome
     ref_id = Dir["#{ori_dir}/#{@genomes_list[0]}/*.pep"][0].split('/')[-1].gsub(".pep","")
 
@@ -257,7 +285,10 @@ class BacterialComparator
   end
 
   def mafft_align_all_dna
-    puts "# MAFFT multialign all gene sequences.."
+
+    print "# Sequence alignments - conserved single genes dna (MAFFT).."
+    start_time = Time.now
+
     ori_dir = Dir.pwd
     Dir.chdir("#{@outdir}/align-genes-dna/")
 
@@ -276,13 +307,15 @@ class BacterialComparator
       Parallel.map(Dir["*.dna"], in_processes: @proc) { |f|
         mafft_align f
       }
-    else
-      puts "..Gene alignment files already exists, skipping."
     end
 
     # ugly hack to find out the reference genome
     ref_id = Dir["#{ori_dir}/#{@genomes_list[0]}/*.pep"][0].split('/')[-1].gsub(".pep","")
 
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
+
     concat_alignments "align-genes-dna.all.fasta", ref_id
 
     Dir.chdir(ori_dir)
@@ -355,36 +388,39 @@ class BacterialComparator
 
 
   def raxml_tree_dna bt
-
-    # DNA tree
-    puts "# RAXML DNA tree creation.. "
+    print "# Genes DNA tree creation (RAXML).."
+    start_time = Time.now
     ori_dir = Dir.pwd
     Dir.chdir(@outdir)
     Dir.mkdir("tree-genes-dna") if ! Dir.exists?("tree-genes-dna")
     current_dir = Dir.pwd
     tree_dir = "#{current_dir}/tree-genes-dna"
-    cmd = system("#{@root}/raxml.linux -T #{@proc} -f d -N #{bt} -s align-genes-dna.all.fasta  -m GTRGAMMA -p 123454321 -n DnaTree -w #{tree_dir}")
+    cmd = system("#{@root}/raxml.linux -T #{@proc} -f d -N #{bt} -s align-genes-dna.all.fasta  -m GTRGAMMA -p 123454321 -n DnaTree -w #{tree_dir} > /dev/null 2>&1")
     cmd = system("cat #{tree_dir}/RAxML_result.DnaTree.RUN.* >> #{tree_dir}/RAxML_result.BS")
-    cmd = system("#{@root}/raxml.linux -T #{@proc} -f b -z #{tree_dir}/RAxML_result.BS -t #{tree_dir}/RAxML_bestTree.DnaTree -m GTRGAMMA -n DNA_BS_TREE -w #{tree_dir}")
-    cmd = system("ln -s #{tree_dir}/RAxML_bipartitionsBranchLabels.DNA_BS_TREE #{tree_dir}/../")
+    cmd = system("#{@root}/raxml.linux -T #{@proc} -f b -z #{tree_dir}/RAxML_result.BS -t #{tree_dir}/RAxML_bestTree.DnaTree -m GTRGAMMA -n DNA_BS_TREE -w #{tree_dir} > /dev/null 2>&1")
+    cmd = system("ln -s #{tree_dir}/RAxML_bipartitionsBranchLabels.DNA_BS_TREE #{tree_dir}/../tree-genes-dna.nwk")
     Dir.chdir(ori_dir)
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
   end
 
   def raxml_tree_pep bt
-
-    # Prot tree
-    puts "# RAXML Protein tree creation.. "
+    print "# Proteins AA tree creation (RAXML).."
+    start_time = Time.now
     ori_dir = Dir.pwd
     Dir.chdir(@outdir)
     Dir.mkdir("tree-genes-pep") if ! Dir.exists?("tree-genes-pep")
     current_dir = Dir.pwd
     tree_dir = "#{current_dir}/tree-genes-pep"
-    cmd = system("#{@root}/raxml.linux -T #{@proc} -f d -N #{bt} -s align-genes-pep.all.fasta  -m PROTGAMMAAUTO -p 123454321 -n PepTree -w #{tree_dir}")
+    cmd = system("#{@root}/raxml.linux -T #{@proc} -f d -N #{bt} -s align-genes-pep.all.fasta  -m PROTGAMMAAUTO -p 123454321 -n PepTree -w #{tree_dir} > /dev/null 2>&1")
     cmd = system("cat #{tree_dir}/RAxML_result.PepTree.RUN.* >> #{tree_dir}/RAxML_result.BS")
-    cmd = system("#{@root}/raxml.linux -T #{@proc} -f b -z #{tree_dir}/RAxML_result.BS -t #{tree_dir}/RAxML_bestTree.PepTree -m PROTGAMMAAUTO -n PEP_BS_TREE -w #{tree_dir}")
-    cmd = system("ln -s #{tree_dir}/RAxML_bipartitionsBranchLabels.PEP_BS_TREE #{tree_dir}/../")
+    cmd = system("#{@root}/raxml.linux -T #{@proc} -f b -z #{tree_dir}/RAxML_result.BS -t #{tree_dir}/RAxML_bestTree.PepTree -m PROTGAMMAAUTO -n PEP_BS_TREE -w #{tree_dir} > /dev/null 2>&1")
+    cmd = system("ln -s #{tree_dir}/RAxML_bipartitionsBranchLabels.PEP_BS_TREE #{tree_dir}/../tree-proteins-aa.nwk")
     Dir.chdir(ori_dir)
-
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time-start_time)
+    print "done (#{c_time})\n"
   end
 
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bacterial-annotator
 version: !ruby/object:Gem::Version
-  version: 0.6.2
+  version: 0.6.3
 platform: ruby
 authors:
 - Maxime Deraspe
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-10-03 00:00:00.000000000 Z
+date: 2017-10-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio