bio-pangenome 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 67ff78e3e817086eb54e9f3c2a93bad8dfec84733d2e6db2a1ccb716543ae3cb
-  data.tar.gz: b9720ab3108dba2864a2f94762597c3cb89fd0837e5853d6f08215abe9f8fce8
+  metadata.gz: 8d1d196a63e35bb86d33ba74ed1465454ffa9d028f57f0603ff90f8708acc352
+  data.tar.gz: 5f00000897b7de9361eba0781d02b49da78dc3d9e0af75fc572283173826224e
 SHA512:
-  metadata.gz: b1643aecb2e252b8c1cc4fe3328d9b296d9ac0f63987544b954320a720346b7175234d6a83c9322baac25f057edc171e530e11181714016aeca73d0da791a650
-  data.tar.gz: d34eafed8d0080ecfbdc68dad5a39366fb18fec2666337e69a00f656f9c2d187b7b9aad062eb3197c24f881194343ce87b4730caafb51d729a80b77722883bd3
+  metadata.gz: 6f8eb3a8f1b10706cd193dc720b3138460ddd4ceb9c5cc1878779159da8064ec20975a032583f872effc19ac24ea1deab6adbd97186f7789a11fccd6d441f126
+  data.tar.gz: 11e2512016f4b5d36ee1c19f88f47dafe82f6e1995c673d39ca5efcfc836fc2cca4f2a03550fcbb0a0b8ee7ef02c1a52e859b4c4111664dfb0870b2197c009b9

data/VERSION

@@ -1 +1 @@
-0.1.1
+0.1.2

data/bin/pangenome_blast_flanking.rb

@@ -4,6 +4,13 @@
 # Author:: homonecloco
 # Copyright:: 2019
 
+class String
+    def integer?
+        Integer(self) != nil rescue false
+    end
+end
+
+
 USAGE = "panggenome_blast_flanking.rb [options]"
 
 gempath = File.dirname(File.dirname(__FILE__))
@@ -83,19 +90,31 @@ lines = BioPangenome.load_lines(options[:lines])
 
 projected_genes = BioPangenome.load_projected_genes options[:transcript_mapping], genes: genes
 
-variety_coordinates = BioPangenome.load_mapping_hash(
-  varieties:lines, 
-  genes: projected_genes ,
-  prefix: options[:basepath],
-  distance: options[:distance]
-  )
-
-seqs = BioPangenome.load_sequences_from_hash(
-  coordinates:variety_coordinates,
-  prefix: options[:basepath],
-  distance: options[:distance],
-  projected_genes: projected_genes
-  )
+
+seqs = nil 
+
+if options[:distance].integer?
+  variety_coordinates = BioPangenome.load_mapping_hash(
+    varieties:lines, 
+    genes: projected_genes ,
+    prefix: options[:basepath],
+    distance: options[:distance]
+    )
+  seqs = BioPangenome.load_sequences_from_hash(
+    coordinates:variety_coordinates,
+    prefix: options[:basepath],
+    distance: options[:distance],
+    projected_genes: projected_genes
+    )
+else 
+  seqs = BioPangenome.load_cds_sequences( varieties: lines,
+    prefix: "#{options[:basepath]}/#{options[:distance]}/",
+    suffix: ".#{options[:distance]}.fa.gz",
+    set_id: options[:distance], 
+    genes:projected_genes )
+end
+
+puts "Loaded squence set for #{seqs.size} genes"
 
 output = options[:output].to_s
 output = output + "_" + options[:window].to_s if options[:no_windows] > 0

data/bin/pangenome_gene_bed_files.rb

@@ -0,0 +1,125 @@
+#!/usr/bin/env ruby
+#
+# BioRuby bio-pangenome Plugin BioPangenome
+# Author:: homonecloco
+# Copyright:: 2019
+
+USAGE = "pangenome_gene_bed_files.rb [options]"
+
+gempath = File.dirname(File.dirname(__FILE__))
+$: << File.join(gempath,'lib')
+
+VERSION_FILENAME=File.join(gempath,'VERSION')
+version = File.new(VERSION_FILENAME).read.chomp
+
+# print banner
+print "pangenome_gene_bed_files #{version} by Ricardo H. Ramirez-Gonzalez 2020\n"
+
+if ARGV.size == 0
+  print USAGE
+end
+
+path = gempath + '/lib/bio-pangenome.rb'
+require path
+#require 'bio-pangenome'
+require 'optparse'
+require 'tmpdir'
+
+require 'csv'
+require 'zlib'
+require 'bio'
+require 'bio-svgenes'
+
+
+options = {
+    lines:     "lines.txt",
+    distances: [0,1000,2000,5000],
+    path: "./gff/",
+    is_gz: true
+}
+
+opts = OptionParser.new do |o|
+
+    o.on("-l", "--lines PATH", "File containing the lines to be analysed") do |arg|
+        options[:lines] = arg
+    end
+
+    o.on("-d", "--distances 0,1000,2000", "File containing the distances to be analysed") do |arg|
+        options[:distances] = arg.split(",").map { |e|  e.to_i }
+    end
+
+    o.on("-p", "--gff_path DIR", "The directory where the gff files are") do |arg|
+        options[:path ] = arg
+    end
+
+    o.separator ""
+    o.on_tail('-h', '--help', 'display this help and exit') do
+        options[:show_help] = true
+    end
+
+end
+
+opts.parse!(ARGV)
+
+puts options.inspect
+
+lines = File.foreach(options[:lines]).map { |line| line.chomp }
+distances = options[:distances]
+puts lines
+
+
+
+gffs = MultipleGFFs.new(folder: options[:path], lines:lines, suffix:".gff.gz", 
+    is_gz:options[:is_gz] )
+
+distances.each do |d|
+    gffs.bedAround(distance: d, prefix: options[:path], suffix: ".bed" )
+end
+
+
+ def bedAroundToRegions(lines:[], distance: 1000, prefix: "../flanking/filtered/", suffix: ".RefSeqv1.1.reg" , suffix_in: ".RefSeqv1.1.bed" )
+     lines.each do |k|
+         path="#{prefix}#{k}_#{distance}bp_#{suffix_in}"
+         path2="#{prefix}#{k}_#{distance}bp_#{suffix}"
+         path3="#{prefix}#{k}_#{distance}bp_#{suffix}.map"
+         puts path
+         out=File.open(path2, "w")
+         out2=File.open(path3, "w")
+         File.foreach(path) do |line|
+            # puts line
+             arr = line.chomp!.split "\t"
+             first=arr[1]
+             last=arr[2]
+             name=arr[0]
+             #if(arr[5] == "-")
+             #    first=arr[2]
+             #    last=arr[1]
+             #end
+           
+             reg =  "#{name}:#{first}-#{last}"
+             out.puts reg
+             out2.puts [reg,arr[3]].join "\t"
+             #puts reg
+             #v.bedAroundGene(distance:distance, out:out)
+             #break
+         end
+         out.close
+         out2.close
+     end
+ end
+
+
+
+ distances.each do |d|
+     bedAroundToRegions(lines:lines,
+         distance: d,
+         prefix: options[:path],
+         suffix_in: ".bed", 
+         suffix: ".reg")
+ end
+
+
+
+
+
+

data/lib/bio-pangenome.rb

@@ -9,4 +9,5 @@
 # In this file only require other files. Avoid other source code.
 
 require 'bio-pangenome/pangenome.rb'
-
+require 'bio-pangenome/gff3_extensions.rb'
+require	'bio-pangenome/MultipleGFF3.rb'

data/lib/bio-pangenome/MultipleGFF3.rb

@@ -0,0 +1,77 @@
+class MultipleGFFs
+    attr_reader :lines_gffs
+
+    def initialize(folder: "../mapping/", lines:[], suffix:".SM1.cds.sorted.gff", is_gz:false )
+        @folder = folder
+        @lines = lines
+        @suffix = suffix
+        @lines_gffs = Hash.new
+        @lines.each do |l|
+            path ="#{folder}/#{l}#{suffix}"
+            @lines_gffs[l] = GFF3.new(file: path, is_gz: is_gz)
+        end
+    end
+    
+    def each_gff
+        @lines_gffs.each_pair{|k,v| yield k, v }
+    end
+
+    def bedAround(distance: 1000, prefix: "../flanking/releasePGSBV1/", suffix: ".RefSeqv1.1.bed" )
+        each_gff do |k, v|
+            path="#{prefix}#{k}_#{distance}bp_#{suffix}"
+            puts path
+            out=File.open(path, "w")
+            v.bedAroundGene(distance:distance, out:out)
+            out.close
+        end
+    end
+
+    def summary
+        ret = []
+        each_gff do |k,v|
+            v.each_mrna do |record|
+                tmp = {}
+                tmp[:line] = k
+                tmp[:id] = record.get_attribute "Name"
+                tmp[:chr] = record.seqid
+                tmp[:start] = record.start
+                tmp[:end] = record.end
+                tmp[:strand] = record.strand
+                tmp[:genomic_length] = record.end - record.start
+                tmp[:coverage] = record.get_attribute "coverage"
+                tmp[:identity] = record.get_attribute "identity"
+                tmp[:matches]  = record.get_attribute "matches"
+                tmp[:mismatches]  = record.get_attribute "mismatches"
+                tmp[:indels] = record.get_attribute "indels"
+                tmp[:unknowns] = record.get_attribute "unknowns"
+                mrna_stats = @lines_gffs[k].mrna_info(record.id)
+                tmp[:cds_count]   = mrna_stats.cds_count
+                tmp[:cds_max_gap] = mrna_stats.cds_max_gap
+                ret << tmp
+            end
+        end
+        ret
+    end
+
+    def to_svg(mrna: "Sm1_CDS.mrna1", positions: false, out: nil)
+        p = Bio::Graphics::Page.new(width: 800,
+         height: 1000, 
+         number_of_intervals:10,
+         background_color: "white"
+         )
+        each_gff do |k,v|
+            generic_track = p.add_track(:glyph => :generic, 
+                :name => k, 
+                :label => true  )
+            v.cds_to_print(mrna).each do |cds|
+
+                f_id = positions ? cds.offset_start : nil
+                feature = Bio::Graphics::MiniFeature.new(start: cds.start, 
+            end: cds.end,
+            fill_color: cds.color, 
+            id: f_id)
+                generic_track.add(feature) 
+            end 
+        end
+    end
+end

data/lib/bio-pangenome/gff3_extensions.rb

@@ -0,0 +1,121 @@
+require 'bio-gff3'
+
+module Bio::GFFbrowser::FastLineParser
+	module_function :parse_line_fast
+end
+
+MrnaStats = Struct.new(:cds_count, :cds_max_gap)
+
+class GFF3
+	CDS_feature = Struct.new(:start, :end, :color, :ref_chr,:ref_start, :ref_end, :offset_start)
+
+	def initialize(file: "", is_gz: true)
+		@file = file
+		@is_gz = is_gz
+	end
+
+	def each
+		return enum_for(:each) unless block_given? 
+		io = nil
+		if @is_gz
+			infile = open(@file)
+			io = Zlib::GzipReader.new(infile) 
+		else
+			io =  File.open(@file)
+		end
+		parser = Bio::GFFbrowser::FastLineParser
+		io.each_line do |line|  
+			line.encode!('UTF-8', 'UTF-8', :invalid => :replace)
+			line.strip!
+			break if line == '##FASTA'
+			next if line.length == 0 or line =~ /^#/
+			begin
+				record = Bio::GFFbrowser::FastLineRecord.new(parser.parse_line_fast(line))
+				yield record
+			rescue Exception => e
+				$stderr.puts "Unable to parse '#{line}'\n#{e}" 
+				throw e
+			end
+		end
+	end
+
+	def each_gene
+		return enum_for(:each_gene) unless block_given? 
+		self.each do |record|
+			next unless record.feature == "gene"
+			yield record
+		end 
+	end
+
+	def each_mrna
+		return enum_for(:each_mrna) unless block_given? 
+		self.each do |record|
+			next unless record.feature == "mRNA"
+			yield record
+		end 
+	end
+
+	def each_cds
+		return enum_for(:each_mrna) unless block_given? 
+		self.each do |record|
+			next unless record.feature == "CDS"
+			yield record
+		end 
+	end
+
+	def calculate_mrna_stats
+		return if @mrna_stats
+		@mrna_stats = Hash.new {|h,k| h[k] = MrnaStats.new(0,0) }
+		last_mrna = ""
+		last_record = nil
+		each_cds do |record|
+			parent = record.get_attribute "Parent"
+			mrna = @mrna_stats[parent]
+			mrna.cds_count += 1
+			if last_mrna == parent
+				distance =  record.start - last_record.end 
+				mrna.cds_max_gap = distance if distance > mrna.cds_max_gap
+			end
+			last_record = record
+			last_mrna   = parent
+		end
+		return
+	end
+
+	def mrna_info(id)
+		calculate_mrna_stats
+		@mrna_stats[id] 
+	end
+
+	def bedAroundGene(distance:1000, out:$stdout)
+		each_gene do |record|
+			start = record.start-distance
+			start = 1 if start < 1
+			reg_end=record.end + distance
+			out.puts [record.seqid, start, reg_end, "#{record.id}_#{record.source}_#{distance}bp", ".", record.strand].join "\t"
+		end
+	end
+
+
+	def cds_to_print(mrna,cannonical_exons:[], colors:["#a6cee3", "#1f78b4", "#b2df8a" , "#33a02c", "#fb9a99",  "#e31a1c", "#fdbf6f", "#ff7f00", "#cab2d6", "#6a3d9a"])
+
+		cds_features = [] 
+		i = 0
+		offset=0
+		offset_start=0
+		each_cds do |record|
+			target = record.get_attribute "Target"
+			arr = target.split(" ")
+			col = colors[i % colors.size ]
+			start = arr[1].to_i + offset
+			ends = arr[2].to_i + offset
+			offset_start = record.start  if offset_start == 0
+			tmp = CDS_feature.new(start, ends, col, 
+				record.seqid, record.start,record.end, record.start - offset_start )
+			cds_features << tmp
+			i += 1
+		end
+		cds_features
+	end
+
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bio-pangenome
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Ricardo H. Ramirez-Gonzalez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-11-27 00:00:00.000000000 Z
+date: 2020-04-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio
@@ -112,6 +112,7 @@ description: Tools to find similarity between pangenomes.
 email: ricardo.ramirez-gonzalez@jic.ac.uk
 executables:
 - pangenome_blast_flanking.rb
+- pangenome_gene_bed_files.rb
 extensions: []
 extra_rdoc_files:
 - LICENSE.txt
@@ -127,7 +128,10 @@ files:
 - Rakefile
 - VERSION
 - bin/pangenome_blast_flanking.rb
+- bin/pangenome_gene_bed_files.rb
 - lib/bio-pangenome.rb
+- lib/bio-pangenome/MultipleGFF3.rb
+- lib/bio-pangenome/gff3_extensions.rb
 - lib/bio-pangenome/pangenome.rb
 - test/helper.rb
 - test/test_bio-pangenome.rb
@@ -150,7 +154,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.6
+rubyforge_project: 
+rubygems_version: 2.7.7
 signing_key: 
 specification_version: 4
 summary: Scripts to analyse pangenomes.