bacterial-annotator 0.8.8 → 0.9.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b629352a56f96c69564434da84bf58732e519ec6e064551e7cf7a0871a7050a1
-  data.tar.gz: 1659b196791b259db68053ef83ae74acd453f92814ffba807a1b2af87026acb3
+  metadata.gz: c3f04aa6e41b8214a3f3d46b77afc21f8c4471326721cf29aae3c810d798b553
+  data.tar.gz: 959c216c280eb6c62f4b27bc01b03f59f00efef9e393d036cc04519ab7f6c54a
 SHA512:
-  metadata.gz: 0cecffe0d0f8ac6cf1c41783927594cdcf952d90b35e5d115efad0a0e87a2d89f6b573397973bcdfd2c390d3f6e08172b3f94c9352e68d0c1d33ecbbfdd19f0f
-  data.tar.gz: bcbddbdf09266cbda5529b60c952afa7e3d92f3b4f14eec1c878ebb2b6a66130f2f0857d54a5f0680fbab3f47dc12bdfc8872387cbe08a085ec793f166c8f6cf
+  metadata.gz: ef78d609d9c3bb1a0af64d4f662206038683c67cb3a55386e5dcde0e3200cbc4ecdf6d5844bb361fb5841e247b1d2e19fc4e1d68c7db963fa8cdcf6e564c9453
+  data.tar.gz: b58553928bf63cbbf845a84ddb30765ebb04ec83e73494bf8caaf2784b3c29a5bf17f9c587c99feb7bf80f24eb041f331618705d61d04bf4191628dd8d48af73

data/bin/bacterial-annotator

@@ -2,10 +2,10 @@
 # -*- coding: utf-8 -*-
 # author:  	maxime déraspe
 # email:	maximilien1er@gmail.com
-# review:  	
+# review:
 # date:    	15-02-24
 # version: 	0.01
-# licence:  	
+# licence:
 
 
 require 'bacterial-annotator'
@@ -160,6 +160,7 @@ compare [OPTIONS]
     --proc         <nb of process> Number of process to run the comparison
 
   //Synteny
+    --refgenome    genbank ref genome if you want to provide complete genomes not previously annotated with bacterial-annotator
     --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
 
@@ -193,6 +194,12 @@ def parseOptions_compare
   options[:phylogeny] = 0
   options[:software] = "fasttree"
   options[:bootstrap] = 100
+  options[:refgenome] = ""
+
+  if ARGV.length == 0
+    usage_compare
+    abort
+  end
 
   while x = ARGV.shift
 
@@ -207,6 +214,8 @@ def parseOptions_compare
       options[:proc] = ARGV.shift
     when "--align"
       options[:align] = ARGV.shift
+    when "--refgenome", "-g"
+      options[:refgenome] = ARGV.shift
     when "--concat"
       options[:concat] = ARGV.shift
     when "--phylogeny"
@@ -254,6 +263,11 @@ def parseOptions_identify
   options[:genome_list] = []
   options[:output] = "tsv"
 
+  if ARGV.length == 0
+    usage_identify
+    abort
+  end
+
   while x = ARGV.shift
 
     case x.downcase

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

@@ -7,7 +7,7 @@
 
 require 'json'
 require 'zlib'
-
+require 'pp'
 
 class SequenceAnnotation
 
@@ -272,7 +272,7 @@ class SequenceAnnotation
       @rna_seq = {}
       @gbk.features do |ft|
 
-        next if ! ft.feature.to_s.include? "rRNA"
+        next if ! ft.feature.to_s.include? "RNA"
 
         ftH = ft.to_hash
         loc = ft.locations
@@ -285,7 +285,12 @@ class SequenceAnnotation
         # gene = ftH["gene"] if !ftH["gene"].nil?
         # protId = ftH["protein_id"][0] if !ftH["protein_id"].nil?
         product = ""
-        product = ftH["product"][0] if !ftH["product"].nil?
+
+        if !ftH["product"].nil?
+          product = ftH["product"][0]
+          # puts ftH["product"].join(",") + "---" + ftH["product"][0]
+        end
+
         locustag = ftH["locus_tag"][0] if !ftH["locus_tag"].nil?
 
         # puts "#{@accession}\t#{seqBeg}\t#{seqEnd}\t#{strand}\t#{protId}\t#{locustag}\t#{gene[0]}\t#{product[0]}"
@@ -533,6 +538,7 @@ class SequenceAnnotation
 
       new_features = {}
       annotations_done = {}
+      gbk_features_len = @gbk.features.length
 
       @gbk.features.each_with_index do |ft, ft_index|
 
@@ -540,8 +546,9 @@ class SequenceAnnotation
 
           next if annotations_done.has_key? k
 
-          if v[:query_location][0][0] < ft.locations[0].from
+          if v[:query_location][0][0] < ft.locations[0].from or ft_index == gbk_features_len-1
 
+            pp v
             if v[:subject_location][0][0] > v[:subject_location][0][1]
               location = "complement(#{v[:query_location][0][0]}..#{v[:query_location][0][1]})"
             else
@@ -550,7 +557,12 @@ class SequenceAnnotation
 
             feature = Bio::Feature.new(v[:feature][0],location)
             feature.qualifiers.push(Bio::Feature::Qualifier.new('product',v[:product][0])) if ! v[:product][0].nil? or v[:product][0] != ""
-            new_features[ft_index] = feature
+            if ft_index == gbk_features_len-1
+              new_features[gbk_features_len] = feature
+            else
+              new_features[ft_index] = feature
+            end
+
             annotations_done[k] = 1
             break
 

data/lib/bacterial-annotator.rb

@@ -1,10 +1,10 @@
 # -*- coding: utf-8 -*-
 # author:  	maxime déraspe
 # email:	maximilien1er@gmail.com
-# review:  	
+# review:
 # date:    	15-02-24
 # version: 	0.0.1
-# licence:  	
+# licence:
 
 require 'bio'
 require 'fileutils'
@@ -324,11 +324,19 @@ class BacterialAnnotator
                                                 @options[:pcoverage],
                                                 "prot")
 
-      print "# Running BLAT alignment with External Database.."
+      # print "# Running BLAT alignment with External Database.."
+      # start_time = Time.now
+      # @externaldb_synteny.run_blat
+      # end_time = Time.now
+      # c_time = Helper.sec2str(end_time-start_time)
+      # print "done (#{c_time})\n"
+      # @externaldb_synteny.extract_hits :externaldb
+
+      print "# Running alignment with External DB"
       start_time = Time.now
-      @externaldb_synteny.run_blat
+      @externaldb_synteny.run_diamond
       end_time = Time.now
-      c_time = Helper.sec2str(end_time-start_time)
+      c_time = Helper.sec2str(end_time - start_time)
       print "done (#{c_time})\n"
       @externaldb_synteny.extract_hits :externaldb
 
@@ -369,6 +377,20 @@ class BacterialAnnotator
           inference: inference
         }
 
+        @annotation_stats[:flagged_cds].each do |flag|
+          if flag.include? "#{k}"
+            if v[:homology][:assert_cutoff].inject(:+) > 2
+              flag.replace("#{flag}\tAnnotated by externaldb (#{v[:homology][:hits][0]}|#{v[:homology][:pId]}|#{cov_query}|#{cov_subject}))")
+            elsif v[:homology][:assert_cutoff] == [1,1,0]
+              flag.replace("#{flag}\tPossible pseudogene (coverage subject = #{cov_subject} with #{v[:homology][:hits][0]}))")
+            elsif v[:homology][:assert_cutoff] == [1,0,1]
+              flag.replace("#{flag}\tPossible pseudogene (coverage query = #{cov_query} with #{v[:homology][:hits][0]}))")
+            elsif v[:homology][:assert_cutoff] == [0,1,1]
+              flag.replace("#{flag}\tLow similarity (percent identity = #{v[:homology][:pId]} with #{v[:homology][:hits][0]}))")
+            end
+          end
+        end
+
       end
 
     end
@@ -463,6 +485,7 @@ class BacterialAnnotator
             flag += "\t#{(@prot_synteny_refgenome.query_sequences[prot][:homology][:cov_query]*100).round(2)}"
             flag += "\t#{(@prot_synteny_refgenome.query_sequences[prot][:homology][:cov_subject]*100).round(2)}"
             @annotation_stats[:flagged_cds] << flag
+            remaining_cds << prot
           end
 
         else
@@ -515,7 +538,7 @@ class BacterialAnnotator
 
     file_flagged_cds = file_dir + "/Prot-flagged.tsv"
     File.open(file_flagged_cds, "w") do |fopen|
-      fopen.write("CDS locus\tAssertion-CutOff\tAA Identity\tCovQuery(%)\tCovSubject(%)\n")
+      fopen.write("CDS locus\tAssertion-CutOff\tAA Identity\tCovQuery(%)\tCovSubject(%)\tNote\n")
       @annotation_stats[:flagged_cds].each do |fcds|
         fopen.write("#{fcds}\n")
       end

data/lib/bacterial-comparator.rb

@@ -1,16 +1,18 @@
 # -*- coding: utf-8 -*-
 # author:  	maxime déraspe
 # email:	maximilien1er@gmail.com
-# review:  	
+# review:
 # date:    	15-02-24
 # version: 	0.0.1
-# licence:  	
+# licence:
 
 require 'bio'
 require 'fileutils'
 require 'parallel'
 require 'helper'
 
+require 'bacterial-annotator/sequence-annotation'
+
 class BacterialComparator
 
   attr_reader :genomes_list, :stats
@@ -25,6 +27,9 @@ class BacterialComparator
     @genomes_list = options[:genomes_list]
     @proc = options[:proc].to_i
     @phylo_nb_genes = options[:phylo_nb_genes]
+    @refgenome_file = options[:refgenome]
+    @refgenome = ""
+
     if ["fasttree","raxml"].include? options[:software]
       @software = options[:software]
     else
@@ -62,14 +67,39 @@ class BacterialComparator
 
   end
 
-
   def read_prot_synteny
 
     puts "# Reading genome synteny files START.."
     start_time = Time.now
     synteny = {}
-    @genomes_list.each do |g|
+
+    # If genome is genbank (.gbk or .gb) then do syntheny first
+
+    @genomes_list.each_with_index do |g,i|
+
       genome_synteny = []
+
+      if g =~ /.gbk/i
+        new_genomes_dir = @outdir+"/new-genomes/"
+        Dir.mkdir(new_genomes_dir) if ! Dir.exists? new_genomes_dir
+        genome_dir = new_genomes_dir + "/" + File.basename(g).gsub(".gbk","")
+        Dir.mkdir(genome_dir) if ! Dir.exists? genome_dir
+        genome_to_annotate = SequenceAnnotation.new(@root,
+                                                    genome_dir,
+                                                    g,
+                                                    "refGbk")
+        query_prot_file = Dir["#{genome_dir}/*.pep"][0]
+        query_gene_file = Dir["#{genome_dir}/*.dna"][0]
+
+        File.symlink(query_prot_file, File.dirname(query_prot_file)+"/Proteins.fa")
+        File.symlink(query_gene_file, File.dirname(query_gene_file)+"/Genes.fa")
+
+        run_synteny_prot @root, genome_dir, @ref_prot_file, query_prot_file
+
+        g = genome_dir
+        @genomes_list[i] = genome_dir
+      end
+
       file = File.open("#{g}/Prot-Synteny.tsv", "r")
       l = file.gets             # skip header
       while l = file.gets
@@ -79,6 +109,7 @@ class BacterialComparator
         synteny[lA[0]] << {ref_cov: lA[3].to_f, pId: lA[4].to_f, query_prot: lA[5], query_cov: lA[7].to_f}
         genome_synteny << lA[0]
       end
+
       @ref_prot.each do |ref_prot|
         if ! genome_synteny.include? ref_prot
           synteny[lA[0]] << {ref_cov: "-", pId: "-", query_prot: "-", query_cov: "-"}
@@ -96,16 +127,45 @@ class BacterialComparator
   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]
+    if File.exist?("#{@genomes_list[0]}/*.pep")
+      pep_file = Dir["#{@genomes_list[0]}/*.pep"]
+      @ref_prot_file = pep_file[0]
+      flatfile = Bio::FlatFile.auto("#{@ref_prot_file}")
+      flatfile.each_entry do |entry|
+        ref_prot << entry.definition.split(" ")[0]
+      end
+      flatfile.close
+      dna_file = Dir["#{@genomes_list[0]}/*.dna"]
+      @ref_dna_file = dna_file[0]
+    else
+      if @refgenome_file == ""
+        abort "You need to provide a reference genome to add a non-annotated genome"
+      elsif @refgenome == ""
+        new_genomes_dir = @outdir+"/new-genomes/"
+        Dir.mkdir(new_genomes_dir) if ! Dir.exists? new_genomes_dir
+        refgenome_dir = new_genomes_dir + "/" + File.basename(@refgenome_file).gsub(".gbk","")
+        Dir.mkdir(refgenome_dir) if ! Dir.exists? refgenome_dir
+        @refgenome = SequenceAnnotation.new(@root,
+                                            refgenome_dir,
+                                            @refgenome_file,
+                                            "refGbk")
+        pep_file = Dir["#{refgenome_dir}/*.pep"]
+        @ref_prot_file = pep_file[0]
+        flatfile = Bio::FlatFile.auto("#{@ref_prot_file}")
+        flatfile.each_entry do |entry|
+          ref_prot << entry.definition.split(" ")[0]
+        end
+        flatfile.close
+        dna_file = Dir["#{refgenome_dir}/*.dna"]
+        @ref_dna_file = dna_file[0]
+      end
     end
-    flatfile.close
+
     ref_prot
-  end
 
+  end
 
   # load all id => sequences from multifasta
   def load_genome_cds file
@@ -128,7 +188,7 @@ class BacterialComparator
 
     pep_out_dir = "#{@outdir}/align-genes-pep"
 
-    ref_proteins = load_genome_cds(Dir["#{@genomes_list[0]}/*.pep"][0])
+    ref_proteins = load_genome_cds(@ref_prot_file)
     synteny_list.each do |k,v|
       pep_out = File.open(pep_out_dir+"/#{k}.pep", "w")
       pep_out.write(ref_proteins[k])
@@ -147,7 +207,7 @@ class BacterialComparator
     end
 
     dna_out_dir = "#{@outdir}/align-genes-dna"
-    ref_genes = load_genome_cds(Dir["#{@genomes_list[0]}/*.dna"][0])
+    ref_genes = load_genome_cds(@ref_dna_file)
     synteny_list.each do |k,v|
       dna_out = File.open(dna_out_dir+"/#{k}.dna", "w")
       dna_out.write(ref_genes[k])
@@ -304,7 +364,7 @@ class BacterialComparator
 
     # FIXME ugly hack to find out the reference genome
     Dir.chdir(ori_dir)
-    ref_id = Dir["#{@genomes_list[0]}/*.pep"][0].split('/')[-1].gsub(".pep","")
+    ref_id = @ref_prot_file.split('/')[-1].gsub(".pep","")
 
     concat_alignments "#{@outdir}/align-genes-pep.all.fasta", ref_id
 
@@ -339,7 +399,7 @@ class BacterialComparator
 
     # ugly hack to find out the reference genome FIXME
     Dir.chdir(ori_dir)
-    ref_id = Dir["#{@genomes_list[0]}/*.pep"][0].split('/')[-1].gsub(".pep","")
+    ref_id = @ref_prot_file.split('/')[-1].gsub(".pep","")
 
     end_time = Time.now
     c_time = Helper.sec2str(end_time-start_time)
@@ -508,4 +568,110 @@ class BacterialComparator
 
   end
 
+
+  def get_fasta_length fasta
+    flatfile = Bio::FlatFile.auto(fasta)
+    prot_lengths = {}
+    flatfile.each_entry do |entry|
+      prot_id = entry.definition.split(" ")[0]
+      prot_length = entry.length
+      prot_lengths[prot_id] = prot_length
+    end
+    flatfile.close
+    prot_lengths
+  end
+
+
+  def run_synteny_prot root, outdir, ref_prot_file, query_prot_file
+
+    puts query_prot_file
+    puts ref_prot_file
+
+    ref_synteny_prot = SequenceSynteny.new(root,
+                                           outdir,
+                                           query_prot_file,
+                                           ref_prot_file,
+                                           "Prot-Ref",
+                                           0.80,
+                                           0.80,
+                                           "prot")
+
+    print "# Running alignment with Reference Genome CDS (diamond).."
+    start_time = Time.now
+    ref_synteny_prot.run_diamond
+    end_time = Time.now
+    c_time = Helper.sec2str(end_time - start_time)
+    print "done (#{c_time})\n"
+
+    ref_synteny_prot.extract_hits :refgenome
+
+    synteny_file = File.open("#{outdir}/Prot-Synteny.tsv","w")
+    synteny_file.write("RefLocusTag\tRefProtID\tRefLength\tRefCoverage\tIdentity\tQueryGene\tQueryLength\tQueryCoverage\tQueryPartial\n")
+    ref_annotated = {}
+
+    ref_synteny_prot.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],
+        partial: (syn_val[:partial] ? 1 : 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],
+      #   partial: (syn_val[:partial] ? 1 : 0)
+      # }
+    end
+
+    # print ref_annotated
+    query_lengths = get_fasta_length query_prot_file
+
+    @refgenome.coding_seq.each do |ref_k, ref_v|
+      gene = ""
+      coverage_ref = ""
+      coverage_query = ""
+      query_length = ""
+      pId = ""
+      if ref_annotated[ref_v[:protId]] != nil
+        gene = ref_annotated[ref_v[:protId]][:key]
+        coverage_ref = ref_annotated[ref_v[:protId]][:cov_subject]
+        query_length = query_lengths[ref_annotated[ref_v[:protId]][:key]]
+        coverage_query = ref_annotated[ref_v[:protId]][:cov_query]
+        pId = ref_annotated[ref_v[:protId]][:pId]
+        partial = ref_annotated[ref_v[:protId]][:partial]
+      end
+
+      _locus_tag = ref_v[:locustag] || ""
+      _seq_len = "NA"
+      # _seq_len = ref_v[:bioseq].seq.length.to_s if ! ref_v[:bioseq].nil?
+      _seq_len = ref_v[:length].to_s if ! ref_v[:length].nil?
+
+      synteny_file.write(ref_v[:protId])
+      synteny_file.write("\t"+_locus_tag)
+      synteny_file.write("\t"+_seq_len)
+      synteny_file.write("\t"+coverage_ref.to_s)
+      synteny_file.write("\t"+pId.to_s)
+      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
+
+    synteny_file.close
+
+  end
+
+
 end                             # end of Class

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bacterial-annotator
 version: !ruby/object:Gem::Version
-  version: 0.8.8
+  version: 0.9.1
 platform: ruby
 authors:
 - Maxime Deraspe
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-08-02 00:00:00.000000000 Z
+date: 2022-09-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio
@@ -110,7 +110,7 @@ homepage: http://rubygems.org/gems/bacterial-annotator
 licenses:
 - GPL-3.0
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -125,9 +125,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
-signing_key: 
+rubygems_version: 3.1.6
+signing_key:
 specification_version: 4
 summary: Bacterial Annotator
 test_files: []