bacterial-annotator 0.7.0 → 0.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0228aafd97af13b8756df42db362e4a53a30f4f0
-  data.tar.gz: 858942624597354dd0f52ad98ea1e94373289174
+  metadata.gz: 10f3d2469fb3aaf64e6b84076e05ab9e1ae41cd6
+  data.tar.gz: f08a5465ce584dd888074c7d0146c1450386598e
 SHA512:
-  metadata.gz: 82c36c4fba00b437e721991c739517b7cfeb5edaa7e1ac49849e59d3ffac2165f1ef39f9961aa756ff8ad691fec36a8b3424cf8ce4d0e1125d486fa2e2a38593
-  data.tar.gz: e8b569f61f2dcb7309c6587ce619f7432e2588a717f3017053adcb693327ac2f21850785883eae4477226d057dde18a308a88d85d2a0558561d567865d1348cc
+  metadata.gz: bd006cf021f0a74f1e98fa6367ca4aca0abb36004f375654ec552b68e1ac8ebc5c1f65e38a480473551848d25ac6be904c5d1841cc60657a47384169d368a18c
+  data.tar.gz: b5a8cb5c74c028e813bbc585e70b6dcb420b8c8f4ad659e8e4c985bce868009a7f5d6015c4e396768a6146c918943e4586a638c084d844cc91be6ac927c993b6

data/bin/bacterial-annotator

@@ -63,27 +63,28 @@ def usage_annotate
 annotate [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
-    --name/-n		<name> Sample name
+    --input/-i      <fasta_file>         Provide the fasta file to annotate
+    --outdir/-o     <outdir>             Output directory [default=BAnnotation]
+    --name/-n       <name>               Sample name
+    --force/-f                           Force to overwrite the output directory
 
   // MERGEM-based Annotation (Recommended)
-    --db/-d		<directory> MERGEM database directory
+    --db/-d         <species_dir>        From MERGEM database (include CDS and RNAs fasta)
+                                         // see bacteriapps.genome.ulaval.ca/mergem
 
   // Reference-Based Annotation
-    --refgenome/-g	<GBK_ID> 	Provide a Genbank file or a Gbk Accession ID.
-    --externaldb	<proteins fasta_file>
-			  Finish or do a complete annotation with this sequence 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..
-    --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]
-
-    --meta		Better for metagenome and plasmid annotations because of disparate codon usage [default=off]
+    --refgenome/-g  <GBK_ID>             Provide a Genbank file or a Gbk Accession ID.
+    --externaldb    <fasta_file>         Finish or do a complete annotation with this sequence database (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..
+
+  // Options
+    --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]
+    --meta                                Better for metagenome and plasmid annotations because of disparate codon usage [default=off]
 
 OEM
 
@@ -101,6 +102,11 @@ def parseOptions_annotate
   options[:minlength] = 500
   options[:meta] = 0
 
+  if ARGV.length == 0
+    usage_annotate
+    abort
+  end
+
   while x = ARGV.shift
 
     case x.downcase
@@ -224,12 +230,14 @@ def usage_identify
 
 identify [OPTIONS] genome_1.fasta genome_2.fasta genome_x.fasta
 
-  //MERGEM Database
-    --db/-d        <database directory>
+  //Mash Sketch
+    --mash/-m      <mash sketch file>
 
   //IO
     --proc         <nb of process> Number of process to run the comparison
 
+    --output       [csv,tsv|json]
+
 OEM
 
 end
@@ -238,21 +246,24 @@ def parseOptions_identify
 
   options = {}
   options[:proc] = 2
-  options[:genomes_list] = []
+  options[:genome_list] = []
+  options[:output] = "tsv"
 
   while x = ARGV.shift
 
     case x.downcase
-    when "--db", "-d"
-      options[:database] = ARGV.shift
+    when "--mash", "-m"
+      options[:mash_file] = ARGV.shift
     when "--proc", "-p"
       options[:proc] = ARGV.shift
+    when "--output", "-o"
+      options[:output] = ARGV.shift
     when "--help", "-h"
       usage_identify
       abort
     else
       if File.exists? "#{x}"
-        options[:genomes_list] << x
+        options[:genome_list] << x
       else
         puts "#{x} file doesn't exist"
         usage_identify
@@ -302,14 +313,14 @@ if ARGV.size >= 1
 
     # Check Options
     if ! options.has_key? :refgenome and
-       ! options.has_key? :external_db
+       ! options.has_key? :external_db and
+       ! options.has_key? :mergem
       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 !"
     end
 
     bannot = BacterialAnnotator.new(options, ROOT)
-    bannot.prepare_files_for_annotation
     bannot.run_annotation
 
   elsif ARGV[0] == "compare"
@@ -317,20 +328,19 @@ if ARGV.size >= 1
     ARGV.shift
     options = parseOptions_compare
     bcomp = BacterialComparator.new(options, ROOT)
-    aln_opt = options[:align].downcase
-    bcomp.mafft_aln aln_opt
-    bcomp.raxml_tree aln_opt, options[:bootstrap] if options[:phylogeny] == 1
+    bcomp.run_comparison
 
   elsif ARGV[0] == "identify"
 
     ARGV.shift
     options = parseOptions_identify
-    if options[:genomes_list].empty?
+    if options[:genome_list].empty?
       puts "You need at least 1 genome fasta to identify !!"
       usage_identify
       abort
     end
     bident = BacterialIdentificator.new(options, ROOT)
+    bident.run_identification
 
   elsif ARGV[0] == "--version" or ARGV[0] == "-v"
 

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

@@ -5,27 +5,208 @@
 # version: 	0.0.1
 # licence:  	
 
+require 'json'
+require 'zlib'
 
 
 class SequenceAnnotation
 
-  attr_accessor :gbk, :coding_seq, :cds_file, :rna_file
+  attr_accessor :gbk, :coding_seq, :rna_seq, :cds_file, :rna_file
 
   # Initialize then genbank file
-  def initialize gbk_file, outdir
+  def initialize root, outdir, file_ref, type
+
+    @root = root
+    @outdir = outdir
+    @coding_seq = {}
+    @rna_seq = {}
+
+    case type
+    when "refGbk"
+      # reference genome use for annotation
+      reference_gbk file_ref
+    when "db"
+      # reference database use for annotation
+      reference_db file_ref
+    when "fasta"
+      # single fasta database for annotation (completion)
+      single_fasta file_ref
+    when "newGbk"
+      # new genbank holder to be annotated
+      new_gbk file_ref
+    end
+
+  end
+
+
+  # Use a MERGEM database to get annotation from it
+  def reference_db dir
+
+    abort "Aborting: Can't find MERGEM db direcotry" if ! File.exists? dir
+
+    @cds_file = "#{dir}/cds.dmnd"
+    @rna_file = "#{dir}/rnas.fasta"
+
+    json_genes = {}
+    Zlib::GzipReader.open("#{dir}/cds.json.gz") {|gz|
+      json_genes = JSON.parse(gz.read)
+    }
+
+    json_genes.each do |gene|
 
-    @gbk_file = gbk_file
-    if ! File.exists? @gbk_file
-      fetch_ncbi_genome(@gbk_file, outdir)
-      @gbk_file = "#{outdir}/#{gbk_file}.gbk"
-      # @gbk_file += ".gbk"
+      prot_id = gene["cluster_id"]
+      @coding_seq[prot_id] = {
+        protId: prot_id,
+        location: nil,
+        product: gene["consensus_name"],
+        length: gene["consensus_length"]
+      }
+
+    end
+
+    # File.open("#{dir}/cds.txt") do |f|
+    #   while l = f.gets
+    #     lA = l.chomp.split(" ")
+    #     @coding_seq[lA[0].gsub(">","")] = {
+    #       protId: lA[0].gsub(">",""),
+    #       location: nil,
+    #       product: lA[1..-1].join(' '),
+    #     }
+    #   end
+    # end
+
+    File.open("#{dir}/rnas.txt") do |f|
+      while l = f.gets
+        lA = l.chomp.split(" ")
+        @rna_seq[lA[0].gsub(">","")] = {
+          protId: lA[0].gsub(">",""),
+          location: nil,
+          product: lA[1..-1].join(' '),
+        }
+      end
     end
 
-    flat_gbk = Bio::FlatFile.auto(@gbk_file)
+  end
+
+  # Use a Genbank Reference and read annotation from it
+  def reference_gbk gbk_file
+
+    puts "# Preparing reference genome files.."
+    if ! File.exists? gbk_file
+      fetch_ncbi_genome(gbk_file)
+      gbk_file = "#{@outdir}/#{gbk_file}.gbk"
+      # gbk_file += ".gbk"
+    end
+
+    flat_gbk = Bio::FlatFile.auto(gbk_file)
 
     # Check if gbk is valid
     if flat_gbk.dbclass != Bio::GenBank
-      abort "Aborting : The input #{@gbk_file} is not a valid genbank file !"
+      abort "Aborting : The input #{gbk_file} is not a valid genbank file !"
+    else
+      @gbk = flat_gbk.next_entry
+    end
+
+    @bioseq = @gbk.to_biosequence
+
+    write_cds_to_file
+    write_rna_to_file
+
+  end
+
+  # Use a Genbank Reference and read annotation from it
+  def single_fasta fasta_file
+
+    return "" if ! File.exists? fasta_file
+
+    File.open(fasta_file, "r") do |dbfile|
+
+      while l=dbfile.gets
+
+        if l[0] == ">"
+
+          lA = l.chomp.split("|")
+
+          if lA.length > 1      # refseq, ncbi, trembl, swissprot
+
+            key_gi = l.split(" ")[0][1..-1]
+            product_long = lA[-1]
+
+            organism = ""
+            product = ""
+            db_source = "[DBSource]"
+
+            if product_long.scan(/|/).count >= 5 # FROM BIORUBY SCRIPTS
+              product = product_long
+              db_source = "RefSeq"
+            elsif product_long.include? " [" and product_long.include? "]" # NCBI
+              organism = product_long[/\[.*?\]/]
+              product = product_long.split(" [")[0].strip
+            elsif product_long.include? "OS=" # Swissprot / TrEMBL
+              product_tmp = product.split("OS=")
+              organism = product_tmp[1].split(/[A-Z][A-Z]=/)[0].strip
+              product = product_tmp[0].strip
+            elsif product_long.include? "[A-Z][A-Z]=" # NCBI
+              product = product_long.split(/[A-Z][A-Z]=/)[0].strip
+            else
+              product = product_long
+            end
+
+            org = organism.gsub("[","").gsub("]","")
+
+            product.lstrip!
+            prot_id = nil
+
+            if key_gi.count("|") == 4
+              if lA[2] == "ref"
+                db_source = "RefSeq"
+              end
+              prot_id = lA[3]
+            elsif key_gi.count("|") == 2
+              if lA[0].include? == "sp" or
+                lA[0].include? == "tr"
+                db_source = "UniProtKB"
+              end
+              prot_id = lA[1]
+            elsif key_gi.count("|") == 5
+              db_source = "RefSeq"
+              prot_id = lA[2]
+            end
+
+
+          else                  # mergem
+
+
+          end
+
+          @coding_seq[key_gi] = { product: product,
+                                  org: org,
+                                  prot_id: prot_id,
+                                  db_source: db_source }
+
+        end
+
+      end
+
+    end
+
+  end
+
+
+  # New Genbank Holder to add annotation to it
+  def new_gbk gbk_file
+
+    if ! File.exists? gbk_file
+      fetch_ncbi_genome(gbk_file)
+      gbk_file = "#{@outdir}/#{gbk_file}.gbk"
+      # gbk_file += ".gbk"
+    end
+
+    flat_gbk = Bio::FlatFile.auto(gbk_file)
+
+    # Check if gbk is valid
+    if flat_gbk.dbclass != Bio::GenBank
+      abort "Aborting : The input #{gbk_file} is not a valid genbank file !"
     else
       @gbk = flat_gbk.next_entry
     end
@@ -38,9 +219,7 @@ class SequenceAnnotation
   # Prepare CDS/proteins
   def get_cds
 
-    if @coding_seq == nil
-
-      @coding_seq = {}
+    if @coding_seq.empty?
 
       # Iterate over each CDS
       @gbk.each_cds do |ft|
@@ -74,7 +253,7 @@ class SequenceAnnotation
           product: product[0],
           bioseq: pepBioSeq,
           bioseq_gene: dnaBioSeq,
-          bioseq_len: pepBioSeq.length
+          length: pepBioSeq.length
         }
 
       end
@@ -88,12 +267,12 @@ class SequenceAnnotation
   # Prepare rRNA tRNA
   def get_rna
 
-    if @rna_seq == nil
+    if @rna_seq.empty?
 
       @rna_seq = {}
       @gbk.features do |ft|
 
-        next if ! ft.feature.to_s.include? "RNA"
+        next if ! ft.feature.to_s.include? "rRNA"
 
         ftH = ft.to_hash
         loc = ft.locations
@@ -129,20 +308,19 @@ class SequenceAnnotation
 
   end
 
-
   # Print CDS to files
   # RETURN : cds_file path
-  def write_cds_to_file outdir
+  def write_cds_to_file
 
     cds_file = "#{@gbk.accession}.pep"
     dna_file = "#{@gbk.accession}.dna"
 
-    if @coding_seq == nil
+    if @coding_seq.empty?
       get_cds
     end
 
-    dna_out = File.open("#{outdir}/#{dna_file}", "w")
-    File.open("#{outdir}/#{cds_file}", "w") do |fwrite|
+    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)
@@ -152,28 +330,28 @@ class SequenceAnnotation
     end
     dna_out.close
 
-    @cds_file = "#{outdir}/" + cds_file
+    @cds_file = "#{@outdir}/" + cds_file
 
   end
 
   # Print RNA to files
   # RETURN : rna_file path
-  def write_rna_to_file outdir
+  def write_rna_to_file
 
     rna_file = "#{@gbk.accession}.rna"
 
-    if @rna_seq == nil
+    if @rna_seq.empty?
       get_rna
     end
 
-    File.open("#{outdir}/#{rna_file}", "w") do |fwrite|
+    File.open("#{@outdir}/#{rna_file}", "w") do |fwrite|
       @rna_seq.each_key do |k|
         seqout_dna = @rna_seq[k][:bioseq_gene].output_fasta("#{k}|#{@rna_seq[k][:type]}|#{@rna_seq[k][:product]}",60)
         fwrite.write(seqout_dna)
       end
     end
 
-    @rna_file = "#{outdir}/" + rna_file
+    @rna_file = "#{@outdir}/" + rna_file
 
   end
 
@@ -247,6 +425,7 @@ class SequenceAnnotation
 
           # check if there is a reference genome.. reference_locus shouldn't be nil in that case
           if locus != nil
+
             qNote = Bio::Feature::Qualifier.new('note', "corresponds to #{locus} locus (AA identity: #{pId}%; coverage(q,s): #{cov_query}%,#{cov_subject}%) from #{ref_genome}")
             ftArray.push(qNote)
 
@@ -390,9 +569,9 @@ class SequenceAnnotation
   end
 
 
-  def save_genbank_to_file outdir
+  def save_genbank_to_file
 
-    File.open("#{outdir}/#{@gbk.definition}.gbk", "w") do |f|
+    File.open("#{@outdir}/#{@gbk.definition}.gbk", "w") do |f|
       f.write(@gbk.to_biosequence.output(:genbank))
     end
 
@@ -403,7 +582,7 @@ class SequenceAnnotation
   ###################
 
   # Fct: Get dna sequence
-  def get_DNA (cds, seq)
+  def get_DNA cds, seq
     loc = cds.locations
     sbeg = loc[0].from.to_i
     send = loc[0].to.to_i
@@ -418,11 +597,11 @@ class SequenceAnnotation
 
 
   # Fetch genbank genome from NCBI
-  def fetch_ncbi_genome refgenome_id, outdir
+  def fetch_ncbi_genome refgenome_id
     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-annotator/sequence-fasta.rb

@@ -13,8 +13,10 @@ class SequenceFasta
   attr_reader :fasta_flat, :fasta_file, :annotation_files
 
   # Initialize fasta holder
-  def initialize fasta_file, meta
+  def initialize root, outdir, fasta_file, meta
 
+    @root = root
+    @outdir = outdir
     @fasta_file = fasta_file
     @fasta_flat = Bio::FlatFile.auto(@fasta_file)
 
@@ -32,29 +34,29 @@ class SequenceFasta
 
 
   # Run prodigal on the genome to annotate
-  def run_prodigal root, outdir
+  def run_prodigal
 
     @annotation_files = {}
-    Dir.mkdir "#{outdir}" if ! Dir.exists? "#{outdir}"
+    Dir.mkdir "#{@outdir}" if ! Dir.exists? "#{@outdir}"
     if @meta==1
-      system("#{root}/prodigal.linux -p meta -i #{@fasta_file} -a #{outdir}/Proteins.fa -d #{outdir}/Genes.fa -o #{outdir}/Genbanks.gbk -q")
+      system("#{@root}/prodigal.linux -p meta -i #{@fasta_file} -a #{@outdir}/Proteins.fa -d #{@outdir}/Genes.fa -o #{@outdir}/Genbanks.gbk -q")
     else
-      system("#{root}/prodigal.linux -i #{@fasta_file} -a #{outdir}/Proteins.fa -d #{outdir}/Genes.fa -o #{outdir}/Genbanks.gbk -q")
+      system("#{@root}/prodigal.linux -i #{@fasta_file} -a #{@outdir}/Proteins.fa -d #{@outdir}/Genes.fa -o #{@outdir}/Genbanks.gbk -q")
     end
 
     @annotation_files = {
-      multiGBK: "#{outdir}/Genbanks.gbk",
+      multiGBK: "#{@outdir}/Genbanks.gbk",
       contigs: [],
       contigs_length: [],
-      genes: "#{outdir}/Genes.fa",
-      proteins: "#{outdir}/Proteins.fa",
+      genes: "#{@outdir}/Genes.fa",
+      proteins: "#{@outdir}/Proteins.fa",
       prot_ids_by_contig: {},
-      fasta_path: "#{outdir}/single-fasta/",
-      gbk_path: "#{outdir}/single-genbank/"
+      fasta_path: "#{@outdir}/single-fasta/",
+      gbk_path: "#{@outdir}/single-genbank/"
     }
 
-    split_fasta outdir
-    split_genbank outdir, "#{outdir}/Genbanks.gbk"
+    split_fasta
+    split_genbank
     extract_cds_names
     @annotation_files
 
@@ -63,14 +65,14 @@ class SequenceFasta
 
   # Split Multi Fasta file
   # RETURN : array of fasta files
-  def split_fasta outdir
+  def split_fasta
     @single_fasta = {}
-    Dir.mkdir("#{outdir}/single-fasta") if ! Dir.exists?("#{outdir}/single-fasta")
+    Dir.mkdir("#{@outdir}/single-fasta") if ! Dir.exists?("#{@outdir}/single-fasta")
     @fasta_flat.each_entry do |seq|
       file_name = seq.definition.chomp.split(" ")[0]
       @annotation_files[:contigs] << "#{file_name}"
       @annotation_files[:contigs_length] << seq.seq.length
-      File.open("#{outdir}/single-fasta/#{file_name}.fasta", "w") do |fwrite|
+      File.open("#{@outdir}/single-fasta/#{file_name}.fasta", "w") do |fwrite|
         fwrite.write(seq)
       end
       @single_fasta[file_name] = seq
@@ -80,9 +82,10 @@ class SequenceFasta
 
   # Split Multi Genbanks file
   # RETURN : array of genbank files
-  def split_genbank outdir, multigbk
+  def split_genbank
 
-    Dir.mkdir("#{outdir}/single-genbank")if ! Dir.exists?("#{outdir}/single-genbank")
+    multigbk = "#{@outdir}/Genbanks.gbk"
+    Dir.mkdir("#{@outdir}/single-genbank")if ! Dir.exists?("#{@outdir}/single-genbank")
     File.open(multigbk,"r") do |f|
       fopen = nil
       while l = f.gets
@@ -96,7 +99,7 @@ class SequenceFasta
           year = date.year
           locus = "LOCUS       #{file_name}#{spacer}#{seq_length.to_s} bp    DNA     linear   BCT #{day}-#{month}-#{year}\n"
           locus += "DEFINITION  #{file_name}\n"
-          fopen = File.open("#{outdir}/single-genbank/#{file_name}.gbk", "w")
+          fopen = File.open("#{@outdir}/single-genbank/#{file_name}.gbk", "w")
           fopen.write(locus)
         elsif l[0..1] == "//"
           fopen.write(outseq)