bio-ngs 0.3.2.alpha.01

data/lib/bio/ngs/converter.rb

@@ -0,0 +1,100 @@
+#
+#  converter.rb - convert qseq format to fastq
+#
+# Copyright:: Copyright (C) 2011
+#     Raoul Bonnal <r@bioruby.org>,
+#     Ranzani Valeria <ranzani@ingm.it>
+# License:: The Ruby License
+#
+#
+
+
+module Bio
+  module Ngs
+    module Converter
+      class Qseq
+
+        # Source buffer:
+        # String with \n as line separator
+        # File (reading)
+        attr_accessor :buffer
+        attr_reader :type
+        attr_reader :stats #keep statistics about total reads, passed filter or not.
+
+        def initialize(default_type=nil)
+          @type=default_type if [:pe, :se].include?(default_type)
+          @stats = {}
+        end
+
+        def type=(data)
+          if [:pe, :se].include?(data)
+            @type = data
+          else
+            @type = nil
+          end
+        end
+
+        # Return each line converted in fastq, is a line is not valid
+        # because is not good enough that line will return a nil
+        # rember to remove the nil values if you are building an array    
+        # TODO: benchmark the performances, I suspect this is not ooptimized 
+        def to_fastq(stats=false)
+          if (type.nil?)            
+            raise "Type of qseq not specifed."
+          else
+            total = 0
+            passed = 0
+            rejected = 0
+            bases_passed_b_quality = 0
+            bases_rejected_b_quality = 0
+            bases_passed_total = 0
+            bases_rejected_total  = 0
+            bases_passed_N = 0
+            bases_rejected_N = 0
+            @buffer.lines do |line|
+              qseq_line_array = line.split
+              read  = (send "qseq2fastq_#{type}", qseq_line_array)
+              total += 1
+              if read
+                passed+=1
+                bases_passed_b_quality += qseq_line_array[9].scan("B").size
+                bases_passed_N += qseq_line_array[9].scan("N").size
+                bases_passed_total += qseq_line_array[9].size                
+              else
+                rejected+=1
+                bases_rejected_b_quality += qseq_line_array[9].scan("B").size
+                bases_rejected_N += qseq_line_array[9].scan("N").size
+                bases_rejected_total += qseq_line_array[9].size
+              end
+              yield read
+            end
+            @stats={:reads_total=>total,
+              :reads_passed=>passed,
+              :reads_rejected=>rejected,
+              :bases_passed_total => bases_passed_total,
+              :bases_rejected_total => bases_rejected_total,
+              :bases_passed_with_b_quality => bases_passed_b_quality,
+              :bases_rejected_with_b_quality => bases_rejected_b_quality,
+              :bases_passed_with_n => bases_passed_N,
+              :bases_rejected_with_n => bases_rejected_N}
+            end
+          end
+
+          # Return the reads in fastq from a paired-end read dataset
+          # qseq_line is an Array  of strings generated from raw line of qseq file.
+          def qseq2fastq_pe(qseq)
+            #          qseq = qseq_line.split #logic here
+            "@#{qseq[0]}:#{qseq[2]}:#{qseq[3]}:#{qseq[4]}:#{qseq[5]}#0/#{qseq[7]}\n#{qseq[8].gsub(/\./,'N')}\n+\n#{qseq[9]}" if qseq[10]=="1"
+          end
+
+          # Return the reads in fastq from a single read dataset
+          # qseq_line is an Array  of strings generated from raw line of qseq file.
+          def qseq2fastq_se(qseq)
+            #         qseq = qseq_line.split #logic here
+            "@#{qseq[0]}:#{qseq[2]}:#{qseq[3]}:#{qseq[4]}:#{qseq[5]}#0/\n#{qseq[8].gsub(/\./,'N')}\n+\n#{qseq[9]}" if qseq[10]=="1"
+          end
+
+        end #Qseq
+      end #Converter
+    end #Ngs
+  end #Bio

data/lib/bio/ngs/core_ext.rb

@@ -0,0 +1,12 @@
+class Thor
+  module CoreExt #:nodoc:
+    class HashWithIndifferentAccess
+      def symbolize_keys
+        self.inject({}) do |hash, item|
+          hash[item[0].to_sym] = item[1]
+          hash
+        end
+      end
+    end #HashWithIndifferentAccess
+  end # CoreExt
+end #Thor

data/lib/bio/ngs/db.rb

@@ -0,0 +1,66 @@
+#
+#
+# Copyright:: Copyright (C) 2011
+#     Francesco Strozzi <francesco.strozzi@gmail.com>
+# License:: The Ruby License
+#
+#
+
+module Bio
+  module Ngs
+    class Db
+      
+      require 'active_support/inflector'
+      DB_TYPES = [:ontology, :homology]
+           
+      # Open a connection to a database using ActiveRecord
+      def initialize(*args)
+        @db_type = args[0]
+        if DB_TYPES.include? @db_type
+          yaml_file=(args[1]) ? args[1] : Dir.pwd+"/conf/#{@db_type}_db.yml"
+          @db = ActiveRecord::Base
+          @db.establish_connection YAML.load_file(yaml_file)
+          # ONLY FOR DEBUG
+          #require 'logger'
+          #ActiveRecord::Base.logger = Logger.new 'log/db.log'
+          require File.expand_path(File.dirname(__FILE__)+"/db/models/#{@db_type}.rb")
+        else
+          raise ArgumentError, "Invalid database type: #{@db_type}"
+        end
+      end
+    
+      # Runs AR migrations and create database tables
+      def create_tables(verbose=false)
+        ActiveRecord::Migration.verbose = verbose
+        ActiveRecord::Migrator.migrate(File.expand_path(File.dirname(__FILE__)+"/db/migrate/#{@db_type}"),nil)
+      end
+      
+      # Export a database table into a tab-separated file
+      def export(table,fileout)
+        klass = @db.const_get(table.singularize.camelize)
+        columns = klass.column_names
+        out = File.open(fileout,"w") 
+        out.write columns.join("\t")+"\n"
+        klass.find(:all).each do |output|
+          records = output.attributes
+          values = []
+          columns.each {|c| values << records[c]}
+          out.write values.join("\t")+"\n"
+        end
+      end
+      
+      # Wrapper for DB transaction to execute many INSERT queries into a single transaction
+      # This can speed up things particularly for SQLite databases.
+      def insert_many(table,query,values=[])
+        klass = @db.const_get(table.to_s.singularize.camelize)
+        klass.transaction do 
+          values.each do |v|
+            sql = @db.send(:sanitize_sql_array,[query]+v)
+            @db.connection.execute(sql)
+          end
+        end
+      end
+      
+    end
+  end
+end

data/lib/bio/ngs/db/migrate/homology/201105030707_create_blastout.rb

@@ -0,0 +1,22 @@
+class CreateBlastout < ActiveRecord::Migration
+
+ def self.up
+	create_table :blast_outputs do |t|
+		t.string :query_id
+		t.string :target_id
+		t.string :target_description
+		t.float :evalue, :precision => :double
+		t.float	:identity
+		t.float :positive
+	end
+	
+	add_index :blast_outputs, :query_id
+	
+ end
+
+ def self.down
+	drop_table :blast_outputs
+ end
+
+
+end

data/lib/bio/ngs/db/migrate/homology/201105030709_create_goannotation.rb

@@ -0,0 +1,29 @@
+class CreateGoannotation < ActiveRecord::Migration
+	
+	def self.up
+		create_table :go_annotations do |t|
+			t.string :db
+			t.string :entry_id
+			t.string :symbol
+			t.string :qualifier
+			t.string :go_id
+			t.string :db_ref
+			t.string :evidence
+			t.string :additional_identifier
+			t.string :aspect
+			t.string :name
+			t.string :synonym
+			t.string :molecule_type
+			t.string :taxon_id
+			t.string :date
+			t.string :assigned_by
+		end
+		
+		add_index :go_annotations, :entry_id
+	end
+	
+	def	self.down
+		drop_table :go_annotations
+	end
+
+end

data/lib/bio/ngs/db/migrate/ontology/201105030708_create_go.rb

@@ -0,0 +1,18 @@
+class CreateGo < ActiveRecord::Migration
+	
+	def self.up
+		create_table :go do |t|
+			t.string :go_id
+			t.string :name
+			t.string :namespace
+			t.string :is_a
+		end
+		
+		add_index :go, :go_id
+	end
+	
+	def	self.down
+		drop_table :go
+	end
+
+end

data/lib/bio/ngs/db/migrate/ontology/201105030710_create_gene_go.rb

@@ -0,0 +1,17 @@
+class CreateGeneGo < ActiveRecord::Migration
+
+	def self.up
+		create_table :gene_gos do |t|
+			t.integer :gene_id
+			t.integer :go_id
+		end
+		
+		add_index :gene_gos, :gene_id
+		add_index :gene_gos, :go_id
+	end
+	
+	def	self.down
+		drop_table :gene_gos
+	end
+
+end

data/lib/bio/ngs/db/migrate/ontology/201105030711_create_gene.rb

@@ -0,0 +1,16 @@
+class CreateGene < ActiveRecord::Migration
+
+	def self.up
+		create_table :genes do |t|
+			t.string :gene_id
+			t.string :library
+		end
+		
+		add_index :genes, :gene_id
+	end
+	
+	def	self.down
+		drop_table :genes
+	end
+
+end

data/lib/bio/ngs/db/models.rb

@@ -0,0 +1 @@
+

data/lib/bio/ngs/db/models/homology.rb

@@ -0,0 +1,8 @@
+
+class GoAnnotation < ActiveRecord::Base
+  belongs_to :blast_output
+end
+
+class BlastOutput < ActiveRecord::Base
+  has_many :go_annotations, :foreign_key => "entry_id", :primary_key => "target_id"
+end

data/lib/bio/ngs/db/models/ontology.rb

@@ -0,0 +1,16 @@
+class Go < ActiveRecord::Base
+  set_table_name "go"
+  has_many :genes, :through => :gene_gos
+  has_many :gene_gos
+  
+end
+
+class Gene < ActiveRecord::Base
+  has_many :go, :through => :gene_gos
+  has_many :gene_gos
+end
+
+class GeneGo < ActiveRecord::Base
+  belongs_to :gene
+  belongs_to :go
+end

data/lib/bio/ngs/ext/bin/common/fastq_coverage_graph.sh

@@ -0,0 +1,161 @@
+#!/usr/bin/env bash
+
+#    FASTX-toolkit - FASTA/FASTQ preprocessing tools.
+#    Copyright (C) 2009  A. Gordon (gordon@cshl.edu)
+#
+#   This program is free software: you can redistribute it and/or modify
+#   it under the terms of the GNU Affero General Public License as
+#   published by the Free Software Foundation, either version 3 of the
+#   License, or (at your option) any later version.
+#
+#   This program is distributed in the hope that it will be useful,
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#   GNU Affero General Public License for more details.
+#
+#    You should have received a copy of the GNU Affero General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+function usage()
+{
+	echo "Solexa-Quality BoxPlot plotter"
+	echo "Generates a solexa quality score box-plot graph "
+	echo
+	echo "Usage: $0 [-i INPUT.TXT] [-t TITLE] [-p] [-o OUTPUT]"
+	echo
+	echo "  [-p]           - Generate PostScript (.PS) file. Default is PNG image."
+	echo "  [-i INPUT.TXT] - Input file. Should be the output of \"solexa_quality_statistics\" program."
+	echo "  [-o OUTPUT]    - Output file name. default is STDOUT."
+	echo "  [-t TITLE]     - Title (usually the solexa file name) - will be plotted on the graph."
+	echo
+	exit 
+}
+
+#
+# Input Data columns: #pos	cnt	min	max	sum       	mean	Q1	med	Q3	IQR	lW	rW A_Count	C_Count	G_Count	T_Count	N_Count
+#  As produced by "solexa_quality_statistics" program
+
+TITLE=""					# default title is empty
+FILENAME=""
+OUTPUTTERM="set term png size 2048,768"		# default output terminal is "PNG"
+OUTPUTFILE="/dev/stdout"   			# Default output file is simply "stdout"
+while getopts ":t:i:o:ph" Option
+	do
+	case $Option in
+		# w ) CMD=$OPTARG; FILENAME="PIMSLogList.txt"; TARGET="logfiles"; ;;
+		t ) TITLE="for $OPTARG" ;;
+		i ) FILENAME=$OPTARG ;;
+		o ) OUTPUTFILE="$OPTARG" ;;
+		p ) OUTPUTTERM="set term postscript enhanced color \"Helvetica\" 8" ;;
+		h ) usage ;;
+		* ) echo "unrecognized argument. use '-h' for usage information."; exit -1 ;;
+	esac
+done
+shift $(($OPTIND - 1)) 
+
+
+if [ "$FILENAME" == "" ]; then
+	usage
+fi
+
+if [ ! -r "$FILENAME" ]; then
+	echo "Error: can't open input file ($1)." >&2
+	exit 1
+fi
+
+##
+## Input validation
+## Too many users (in galaxy) try to plot a FASTQ file
+## (without using the 'fastq statistics' tool first).
+##
+## gnuplot's error in that case is crypt, and support emails are annoying.
+##
+## try to detect FASTA/FASTQ input, and give a detailed, easy-to-understand warning.
+##
+##
+AWK_FASTX_DETECTION='
+NR==1 && $0 ~ /^>/ { fasta_id = 1 }
+NR==1 && $0 ~ /^@/ { fastq_id = 1 }
+NR==2 && $0 ~ /^[ACGT][ACGT]*$/ { nucleotides = 1 }
+NR>3 { exit }
+END { if ( fasta_id && nucleotides ) { print "FASTA" }
+      if ( fastq_id && nucleotides ) { print "FASTQ" }
+}'
+
+INPUT_TYPE=$(awk "$AWK_FASTX_DETECTION" "$FILENAME")
+
+if [ "x$INPUT_TYPE" = "xFASTA" ] ; then
+#this doesn't even make sense: FASTA files don't contain any quality scores
+cat>&2<<EOF
+Error: It looks like your input file is a FASTA file.
+
+FASTA files do not contain quality scores, and can not be used with this tool.
+EOF
+exit 1
+fi
+if [ "x$INPUT_TYPE" = "xFASTQ" ] ; then
+cat>&2<<EOF
+Error: It looks like your input file is a FASTQ file.
+
+This tool (fastq-quality-plot) can't use FASTQ files directly - it requires a tabular text file conaining summary statistic about your FASTQ file.
+
+In Galaxy,
+Please use the "Compute Quality Statistics" tool (in the "NGS: QC and Manipulation" category) to compute the quality statistics report, and then use this tool with the new statistics report.
+
+On the command line,
+Please use the "fastx_quality_stats" program to create the statistics report.
+EOF
+exit 1
+fi
+
+##
+## Even if this is not a FASTA/FASTQ file,
+## users can still use incompatible input files.
+## Try to detect it and abort with a warning.
+AWK_VALID_STAT='NR==1 && $1=="column" && $2=="count" && $3=="min" { exit 2 } NR>1 { exit }'
+
+awk "$AWK_VALID_STAT" "$FILENAME"
+if [ $? -ne 2 ] ; then
+cat>&2<<EOF
+Error: Input file is not a valid statistics report.
+
+This tool (fastq-quality-plot) requires a tabular text file conaining summary statistic about your FASTQ file.
+
+In Galaxy,
+Please use the "Compute Quality Statistics" tool (in the "NGS: QC and Manipulation" category) to compute the quality statistics report, and then use this tool with the new statistics report.
+
+On the command line,
+Please use the "fastx_quality_stats" program to create the statistics report.
+EOF
+exit 1
+fi
+
+
+#Read number of cycles from the stats file (each line is a cycle, minus the header line)
+#But for the graph, I want xrange to reach (num_cycles+1), so I don't subtract 1 now.
+NUM_CYCLES=$(cat "$FILENAME" | wc -l) 
+
+GNUPLOTCMD="
+$OUTPUTTERM
+set boxwidth 0.8 
+set size 1,1
+set key Left inside
+set xlabel \"read position\"
+set ylabel \"Coverage\"
+set title  \"Coverage $TITLE\"
+#set auto y
+#set bars 4.0
+set xrange [ 0: $NUM_CYCLES ]
+#set yrange [-15:45]
+#set y2range [-15:45]
+set xtics 1 
+set x2tics 1
+#set ytics 2
+#set y2tics 2
+set tics out
+set grid ytics
+set style fill empty
+plot '$FILENAME' using 1:2 with lines lt 1 lw 1 title 'Coverage'
+"
+
+echo "$GNUPLOTCMD" | gnuplot > "$OUTPUTFILE"