transrate 1.0.0.beta1 → 1.0.0.beta2

data/lib/transrate/express.rb

@@ -1,102 +0,0 @@
-
-module Transrate
-
-  class ExpressError < StandardError
-  end
-
-  class Express
-
-    require 'ostruct'
-
-    attr_reader :fin_output
-
-    # return an Express object
-    def initialize
-      which = Cmd.new('which express')
-      which.run
-      if !which.status.success?
-        raise ExpressError.new("could not find express in the path")
-      end
-      @express = which.stdout.split("\n").first
-    end
-
-    # return struct containing:
-    #   results_file => path to the express results TSV
-    #   expression   => a hash of target => effective_count
-    #   align_samp   => path to the sampled alignments file
-    def run assembly, bamfile
-      assembly = assembly.file if assembly.is_a? Assembly
-
-      ex_output = 'results.xprs'
-      @fin_output = "#{File.basename assembly}_#{ex_output}"
-
-      unless File.exists? @fin_output
-        runner = Cmd.new build_command(assembly, bamfile)
-        runner.run
-        unless runner.status.success?
-          logger.warn "express failed. cleaning sam file and trying again"
-          File.delete("hits.1.samp.bam")
-          fix_problem_snap_output bamfile
-          runner.run
-          unless runner.status.success?
-            abort "express failed on the cleaned sam file\n#{runner.stderr}"
-          end
-        end
-        File.rename(ex_output, @fin_output)
-      end
-      return 'hits.1.samp.bam'
-    end
-
-    # return the constructed eXpress command
-    def build_command assembly, bamfile
-      cmd = "#{@express}"
-      cmd << " --output-dir ."
-      cmd << " --output-align-samp"
-      cmd << " --no-update-check"
-      cmd << " --additional-online 1"
-      cmd << " #{File.expand_path assembly}"
-      cmd << " #{File.expand_path bamfile}"
-      cmd
-    end
-
-    # return a hash of target => effective_count created
-    # by parsing the results file
-    def load_expression file
-      expression = {}
-      first = true
-      File.open(file).each do |line|
-        if first # skip header line
-          first = false
-          next
-        end
-        line = line.chomp.split("\t")
-        target = line[1]
-        effective_length = line[3]
-        effective_count = line[7]
-        tpm = line[14]
-        expression[target] = {
-          :eff_len => effective_length.to_i,
-          :eff_count => effective_count.to_f,
-          :tpm => tpm.to_f
-        }
-      end
-      expression
-    end
-
-    def fix_problem_snap_output bam
-      # express failed, probably because of temporary snap error
-      # convert bam to sam
-      sam = "#{File.expand_path(File.basename(bam, File.extname(bam)))}.sam"
-      Samtools.run "view -h #{bam} > #{sam}"
-      # run sam fixer on sam
-      checker = SamChecker.new
-      fixed_sam = "#{File.expand_path(File.basename(sam, File.extname(sam)))}.fixed.sam"
-      checker.fix_sam(sam, fixed_sam)
-      # convert sam to bam
-      Samtools.run "view -bS #{fixed_sam} > #{bam}"
-      bam
-    end
-
-  end # Express
-
- end # Transrate

data/lib/transrate/sam_checker.rb

@@ -1,74 +0,0 @@
-module Transrate
-
-  class SamChecker
-
-    def initialize
-      @contigs = {}
-      @reference = ""
-      @count = 0
-      @percent = 0
-      @first = true
-    end
-
-    def check sam
-      cols = sam.split("\t")
-
-      reference = cols[2]
-      length = @contigs[reference]
-
-      seq_length = cols[9].length
-      position = cols[3].to_i
-      cigar = cols[5]
-      # this generates a list of pairs in the form [ ["10", "M"], ["1", "D"] ]
-      list = cigar.split(/[MDIS]/).zip(cigar.scan(/[MDIS]/))
-      list.each_with_index do |a, i|
-        c=a[0].to_i
-        t=a[1]
-        if t=="M" or t=="D"
-          position += c
-        elsif i==0 and t=="S"
-          position += c
-        end
-      end
-      if position > length + 1
-        return false
-      else
-        return true
-      end
-    end
-
-    def fix_sam input, output
-      sam1 = ""
-      File.open("#{output}", "wb") do |out|
-        File.open("#{input}").each_line do |sam|
-          if sam =~ /^@/
-            # header
-            # @SQ SN:Locus_1_Transcript_13/342_Confidence_1.000_Length_1605 LN:1605
-            if sam[0..2]=="@SQ"
-              cols = sam.split("\t")
-              name = cols[1][3..-1]
-              length = cols[2][3..-1].to_i
-              @contigs[name] = length
-            end
-            out.write sam
-          else
-            # alignment
-            if @first
-              sam1 = sam.dup
-              @first = false
-            else
-              if check(sam1) and check(sam)
-                out.write(sam1)
-                out.write(sam)
-              end
-              @first = true
-            end
-            @count+=1
-          end
-        end
-      end
-    end
-
-  end
-
-end

data/lib/transrate/samtools.rb

@@ -1,146 +0,0 @@
-module Transrate
-
-  class Samtools
-
-    class SamtoolsError < StandardError; end
-
-    # Get the path to the samtools binary built when bio-samtools
-    # was installed
-    def self.path
-      if !@path
-        which_samtools = Cmd.new("which samtools")
-        which_samtools.run
-        if !which_samtools.status.success?
-          raise SamtoolsError.new("could not find samtools in the path")
-        end
-        @path = which_samtools.stdout.split("\n").first
-      end
-      return @path
-    end
-
-    # Run a samtools command
-    def self.run cmd
-      runcmd = Cmd.new "#{Samtools.path} #{cmd}"
-      runcmd.run
-      if !runcmd.status.success?
-        raise SamtoolsError.new("Samtools command failed: #{runcmd}" +
-                                "\n#{runcmd.stderr}" +
-                                "\n#{runcmd.stdout}")
-      end
-      runcmd.stdout
-    end
-
-    # Convert a sam file to a bam file, returning the path to the bamfile
-    def self.sam_to_bam samfile
-      bamfile = File.basename(samfile, '.sam') + '.bam'
-      bamfile = File.expand_path bamfile
-      if !File.exist?(bamfile)
-        Samtools.run "view -bS #{File.expand_path samfile} > #{bamfile}"
-      end
-      bamfile
-    end
-
-    # Sort a bam file, returning the path to the sorted bamfile
-    def self.sort_bam bamfile, threads=4
-      # the sort command behaves inconsistently with the other commands:
-      # it takes an output prefix rather than a filename
-      # and automatically adds the .bam extension
-      sorted = File.basename(bamfile, '.bam') + '.sorted'
-      if !File.exist?("#{sorted}.bam")
-        cmd = "sort"
-        cmd << " -@ #{threads}"
-        cmd << " #{File.expand_path bamfile} #{sorted}"
-        Samtools.run cmd
-      end
-      File.expand_path(sorted + '.bam')
-    end
-
-    # Sort a bam file by readname only, returning the path to th
-    # sorted bamfile
-    def self.readsort_bam bamfile, threads=4
-      # the sort command behaves inconsistently with the other commands:
-      # it takes an output prefix rather than a filename
-      # and automatically adds the .bam extension
-      sorted = File.basename(bamfile, '.bam') + '.readsorted'
-      if !File.exist?("#{sorted}.bam")
-        cmd = "sort"
-        cmd << " -@ #{threads}"
-        cmd << " -n" # sort by read name only
-        cmd << " #{File.expand_path bamfile} #{sorted}"
-        Samtools.run cmd
-      end
-      File.expand_path(sorted + '.bam')
-    end
-
-
-    # Index a bamfile, returning the path to the index
-    def self.index_bam bamfile
-      index = File.basename(bamfile, '.bam') + '.bai'
-      index = File.expand_path index
-      Samtools.run "index #{File.expand_path bamfile} #{index}"
-      index
-    end
-
-    # Convert a sam file to bam, sort and index the bam, returning
-    # an array of paths to the bamfile, sorted bamfile and index respectively
-    def self.sam_to_sorted_indexed_bam samfile
-      bamfile = Samtools.sam_to_bam samfile
-      sorted = Samtools.sort_bam bamfile
-      index = Samtools.index_bam bamfile
-      [bamfile, sorted, index]
-    end
-
-    # Calculate per-base coverage from a sorted, indexed bam file
-    # return the path to the coverage file
-    def self.coverage bam
-      outfile = File.expand_path "#{File.basename(bam.fasta)}.coverage"
-      if !File.exist?(outfile)
-        cmd = "mpileup"
-        cmd += " -f #{File.expand_path bam.fasta}" # reference
-        cmd += " -B" # don't calculate BAQ quality scores
-        cmd += " -Q0" # include all reads ignoring quality
-        cmd += " -I" # don't do genotype calculations
-        cmd += " #{File.expand_path bam.bam}" # the bam file
-        cmd += " > #{outfile}"
-        Samtools.run cmd
-      end
-      outfile
-    end
-
-    # Calculate per-base coverage and mapQ score from a sorted, indexed
-    # bam file. Return the path to the coverage file.
-    def self.bam_to_bcf(bam, fasta)
-      outfile = File.expand_path "#{File.basename(fasta)}.bcf"
-      if !File.exist?(outfile)
-        cmd = "samtools mpileup"
-        cmd << " -f #{File.expand_path fasta}" # reference
-        cmd << " -B" # don't calculate BAQ quality scores
-        cmd << " -q0" # include all multimapping reads
-        cmd << " -Q0" # include all reads ignoring quality
-        cmd << " -I" # don't do genotype calculations
-        cmd << " -u" # output uncompressed bcf format
-        cmd << " #{File.expand_path bam}" # the bam file
-        cmd << " | bcftools view -cg - "
-        cmd << " > #{outfile}"
-        mpileup = Cmd.new cmd
-        mpileup.run
-        if !mpileup.status.success?
-          raise RuntimeError.new("samtools and bcftools failed")
-        end
-      end
-      outfile
-    end
-
-    def self.merge_bam left, right, out, threads=1
-      cmd = "merge"
-      cmd << " -@ #{threads}"
-      cmd << " #{out}"
-      cmd << " #{left}"
-      cmd << " #{right}"
-      Samtools.run cmd
-      out
-    end
-
-  end
-
-end

data/test/data/express_results.xprs

@@ -1,5 +0,0 @@
-bundle_id	target_id	length	eff_length	tot_counts	uniq_counts	est_counts	eff_counts	ambig_distr_alpha	ambig_distr_beta	fpkm	fpkm_conf_low	fpkm_conf_high	solvable	tpm
-1	C291600	261	54.369218	10	10	10.000000	48.005105	0.000000e+00	0.000000e+00	5.410108e+00	5.410108e+00	5.410108e+00	T	5.417487e+00
-2	C196710	138	0.000000	0	0	0.000000	0.000000	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	F	0.000000e+00
-3	C378763	1364	1096.889202	195	195	195.000000	242.485749	0.000000e+00	0.000000e+00	5.229148e+00	5.183800e+00	5.274496e+00	T	5.236279e+00
-4	C132376	100	0.000000	0	0	0.000000	0.000000	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	F	0.000000e+00

data/test/test_express.rb

@@ -1,22 +0,0 @@
-require 'helper'
-require 'tmpdir'
-
-class TestExpress < Test::Unit::TestCase
-
-  context "Express" do
-
-    should "load an expression file" do
-      file = File.join(File.dirname(__FILE__), 'data',
-                        'express_results.xprs')
-      e = Transrate::Express.new
-      results = e.load_expression file
-      assert_equal 4, results.size, "should be four results loaded"
-      assert_equal 54, results['C291600'][:eff_len], "eff length is wrong"
-      assert_equal 48.005105, results['C291600'][:eff_count],
-                   "eff count is wrong"
-      assert_equal 5.417487e+00, results['C291600'][:tpm], "tpm is wrong"
-    end
-
-  end
-
-end

data/test/test_samtools.rb

@@ -1,22 +0,0 @@
-require 'helper'
-
-class TestSamtools < Test::Unit::TestCase
-
-  context "samtools" do
-
-    should "know the path to samtools binary" do
-      msg = /Program: samtools/
-      path = Transrate::Samtools.path
-      res = `#{path} 2>&1`.split("\n").join
-      assert msg =~ res
-    end
-
-    should "run commands" do
-      sam = File.join(File.dirname(__FILE__), 'data', 'tiny.sam')
-      Transrate::Samtools.run "view -bS #{sam} > tiny.bam"
-      assert_equal 460, File.size('tiny.bam'), 'bam file should be created'
-      File.delete 'tiny.bam'
-    end
-
-  end
-end