transrate 1.0.0.alpha.8.bowtie → 1.0.0.beta1

data/lib/transrate/sam_checker.rb

@@ -31,36 +31,9 @@ module Transrate
         end
       end
       if position > length + 1
-        # `diff` is how much the cigar makes the read overlap the end
-        diff = position - (length + 1)
-        if list[-1][1] == "S" # the last item in the cigar is "S"
-          # increase the number in the last item in the cigar
-          list[-1][0] = (list[-1][0].to_i + diff).to_s
-          if list[-2][0].to_i > diff
-            # decrease the penultimate item in the cigar
-            list[-2][0] = (list[-2][0].to_i - diff).to_s
-          elsif list[-2][0].to_i == diff
-            # just delete the penultimate item if
-            list.delete_at(-2) # delete_at changes `list`
-          else
-            # this didn't happen in the rice/oases sam file, but it might
-          end
-        elsif list[-1][1] == "M"
-          if list[-1][0].to_i > diff
-            # decrease the number of the last item in the cigar
-            list[-1][0] = (list[-1][0].to_i - diff).to_s
-            # add a new soft mask item to the end of the cigar
-            list << [diff.to_s, "S"]
-          elsif list[-1][0].to_i == diff
-            # just change the last item to soft mask if it's the same length
-            # as the difference
-            list[-1][1] = "S"
-          end
-        end
-        cols[5] = list.join("")
-        return cols.join("\t")
+        return false
       else
-        return sam
+        return true
       end
     end
 
@@ -84,8 +57,10 @@ module Transrate
               sam1 = sam.dup
               @first = false
             else
-              out.write(check(sam1))
-              out.write(check(sam))
+              if check(sam1) and check(sam)
+                out.write(sam1)
+                out.write(sam)
+              end
               @first = true
             end
             @count+=1

data/lib/transrate/samtools.rb

@@ -61,7 +61,7 @@ module Transrate
       # 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'
+      sorted = File.basename(bamfile, '.bam') + '.readsorted'
       if !File.exist?("#{sorted}.bam")
         cmd = "sort"
         cmd << " -@ #{threads}"

data/lib/transrate/score_optimiser.rb

@@ -0,0 +1,31 @@
+module Transrate
+
+  # This class is currently only used to calculate the basic transrate score.
+  # In future it will be used to automatically optimised the score by
+  # taking the optimal subset of contigs.
+  class ScoreOptimiser
+
+    def initialize assembly, read_metrics
+      @assembly = assembly
+      read_stats = read_metrics.read_stats
+      @total = read_stats[:fragments]
+      @good = read_stats[:good_mappings]
+    end
+
+    def raw_score
+      scores = @assembly.assembly.values.map{ |c| c.score }
+      @contig_score = geomean scores
+      @contig_score * (@good / @total.to_f)
+    end
+
+    # Calculate the geometric mean of an array of numbers
+    def geomean x
+      sum = 0.0
+      x.each{ |v| sum += Math.log(v) }
+      sum /= x.size
+      Math.exp sum
+    end
+
+  end # ScoreOptimiser
+
+end

data/lib/transrate/snap.rb

@@ -6,6 +6,7 @@ module Transrate
   class Snap
 
     require 'fix-trinity-output'
+    require 'bio'
 
     attr_reader :index_name, :sam, :read_count
 
@@ -38,7 +39,6 @@ module Transrate
       cmd << " -t #{threads}"
       cmd << " -b" # bind threads to cores
       cmd << " -M"  # format cigar string
-      cmd << " -sa" # keep all alignments, don't discard 0x100
       cmd << " -D 5" # edit distance to search for mapq calculation
       cmd << " -om 5" # Output multiple alignments. extra edit distance
       cmd << " -omax 10" # max alignments per pair/read
@@ -102,8 +102,8 @@ module Transrate
     def save_readcount stdout
       stdout.split("\n").each do |line|
         cols = line.split(/\s+/)
-        if cols[0]=="2000" and cols[1]=="30"
-          @read_count = cols[8].to_i / 2
+        if cols.size > 5 and cols[0]=~/[0-9\,]+/
+          @read_count = cols[0].gsub(",", "").to_i / 2
           File.open("#{@read_count_file}", "wb") do |out|
             out.write("#{@read_count}\n")
           end
@@ -134,6 +134,7 @@ module Transrate
 
     def build_index file, threads
       @index_name = File.basename(file, File.extname(file))
+      file = check_ambiguous(file)
       unless Dir.exists?(@index_name)
         cmd = "#{@snap} index #{file} #{@index_name}"
         cmd << " -s 23"
@@ -150,6 +151,30 @@ module Transrate
       @index_built = true
     end
 
+    def check_ambiguous file
+
+      ref = Bio::FastaFormat.open(file)
+      ambiguous = false
+      fixed = ""
+      ref.each do |entry|
+        seq = entry.seq
+        if seq =~ /[RYSWKMBDHV]/
+          seq = seq.gsub(/[RYSWKMBDHV]/, "N")
+          ambiguous = true
+        end
+        fixed << ">#{entry.definition}\n#{seq}\n"
+      end
+      ref.close
+      if ambiguous
+        logger.warn "squelching ambiguous nucleotides"
+        file = "#{File.basename(file, File.extname(file))}.fixed.fasta"
+        File.open(file, "w") do |out|
+          out.write fixed
+        end
+      end
+      return file
+    end
+
   end # Snap
 
 end # Transrate

data/lib/transrate/transrater.rb

@@ -62,22 +62,16 @@ module Transrate
       comparative_metrics
     end
 
-    # Calculate the geometric mean of an array of numbers
-    def geomean(x)
-      sum = 0.0
-      x.each{ |v| sum += Math.log(v) }
-      sum /= x.size
-      Math.exp(sum)
-    end
-
     # Reduce all metrics for the assembly to a single quality score
     # by taking the geometric mean of the scores for all contigs
     # and multiplying it by the proportion of fragments whose most likely
     # mapping is consistent with the assembly
     # @return [Integer] the assembly score
     def assembly_score
-      @score = geomean assembly.assembly.values.map{ |contig| contig.score }
-      return @score * @read_metrics.p_good_mapping
+      if !@score_optimiser
+        @score_optimiser = ScoreOptimiser.new(@assembly, @read_metrics)
+      end
+      return @score_optimiser.raw_score
     end
 
     def assembly_metrics
@@ -89,6 +83,7 @@ module Transrate
       unless @read_metrics.has_run
         @read_metrics.run(left, right, threads: @threads)
       end
+      @assembly.classify_contigs
       @read_metrics
     end
 

data/lib/transrate/version.rb

@@ -11,7 +11,7 @@ module Transrate
     MAJOR = 1
     MINOR = 0
     PATCH = 0
-    BUILD = 'alpha.8.bowtie'
+    BUILD = 'beta1'
 
     STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.')
   end

data/test/data/express_results.xprs

@@ -0,0 +1,5 @@
+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_bin.rb

@@ -25,10 +25,8 @@ class TestTransrateBin < Test::Unit::TestCase
       "transrate_sorghum_transcript.fa_contigs.csv",
       "150uncovered.l.fq-150uncovered.r.fq-read_count.txt",
       "150uncovered.l.fq.150uncovered.r.fq.sorghum_transcript.merged.sorted.bam",
-      "150uncovered.l.fq.150uncovered.r.fq.sorghum_transcript.merged.valid.bam",
-      "150uncovered.l.fq.150uncovered.r.fq.sorghum_transcript.valid.bam",
-      "150uncovered.l.fq.150uncovered.r.fq.sorghum_transcript.valid.sorted.bam",
-      "150uncovered.l.fq.150uncovered.r.fq.sorghum_transcript.sam-read_count.txt"]
+      "bad.sorghum_transcript.fa", "chimeric.sorghum_transcript.fa",
+      "fragmented.sorghum_transcript.fa", "good.sorghum_transcript.fa"]
       files.each do |file|
         File.delete(file) if File.exist?(file)
       end
@@ -70,10 +68,6 @@ class TestTransrateBin < Test::Unit::TestCase
       assert File.exist?("transrate_sorghum_transcript.fa_contigs.csv"),
              "contig csv file doesn't exist"
       hash = {}
-      if !c.status.success?
-        puts c.stderr
-        puts c.stdout
-      end
       CSV.foreach("transrate_assemblies.csv", :headers => true,
                                    :header_converters => :symbol,
                                    :converters => :all) do |row|

data/test/test_express.rb

@@ -0,0 +1,22 @@
+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_read_metrics.rb

@@ -27,32 +27,19 @@ class TestReadMetrics < Test::Unit::TestCase
       left = File.join(File.dirname(__FILE__), 'data', '150uncovered.l.fq')
       right = File.join(File.dirname(__FILE__), 'data', '150uncovered.r.fq')
       Dir.mktmpdir do |tmpdir|
-      # tmpdir = Dir.mktmpdir
-      # puts tmpdir
         Dir.chdir tmpdir do
           @read_metrics.run(left, right)
           stats = @read_metrics.read_stats
           assert @read_metrics.has_run, "has run"
           assert_equal 223,     stats[:fragments], 'number of read pairs'
-          assert_equal 219,     stats[:fragments_mapped], 'number mapping'
-          assert_equal 0.9821,   stats[:p_fragments_mapped].round(4),
+          assert_equal 215,     stats[:fragments_mapped], 'number mapping'
+          assert_equal 0.9641,   stats[:p_fragments_mapped].round(4),
                        'proportion mapping'
-          assert_equal 184,     stats[:good_mappings], 'good mapping'
-          assert_equal 0.8251,   stats[:p_good_mapping].round(4),
+          assert_equal 182,     stats[:good_mappings], 'good mapping'
+          assert_equal 0.8161,   stats[:p_good_mapping].round(4),
                        'percent good mapping'
-          assert_equal 35,      stats[:bad_mappings], 'bad mapping'
-        end
-      end
-    end
-
-    should "calculate more read mapping statistics" do
-      left = File.join(File.dirname(__FILE__), 'data', '150uncovered.l.fq')
-      right = File.join(File.dirname(__FILE__), 'data', '150uncovered.r.fq')
-      Dir.mktmpdir do |tmpdir|
-        Dir.chdir tmpdir do
-          @read_metrics.run(left, right)
-          stats = @read_metrics.read_stats
-          assert_equal 0, stats[:potential_bridges], 'bridges'
+          assert_equal 33,      stats[:bad_mappings], 'bad mapping'
+          assert_equal 1, stats[:potential_bridges], 'bridges'
           assert_equal 2, stats[:contigs_uncovbase], 'uncovered base contig'
           assert_equal 0, stats[:contigs_uncovered], 'uncovered contig'
           assert_equal 0, stats[:contigs_lowcovered], 'lowcovered contig'
@@ -76,22 +63,23 @@ class TestReadMetrics < Test::Unit::TestCase
 
           edit_a = a[:p_seq_true].round(5)
           edit_b = b[:p_seq_true].round(5)
-          assert_equal 0.98618, edit_a, "edit distance 1"
-          assert_equal 0.9749, edit_b, "edit distance 2"
+          assert_equal 0.98414, edit_a, "edit distance 1"
+          assert_equal 0.974, edit_b, "edit distance 2"
 
-          assert_equal 0.83146, a[:p_good].round(5), "proportion of good mappings"
-          assert_equal 0.84615, b[:p_good].round(5), "proportion of good mappings"
+          assert_equal 0.8046, a[:p_good].round(5),
+                       "proportion of good mappings"
+          assert_equal 0.875, b[:p_good].round(5), "proportion of good mappings"
 
           # uncovered bases
           unc_a = contigs[0].uncovered_bases
           unc_b = contigs[1].uncovered_bases
-          assert_equal 12, unc_a, "uncovered bases"
-          assert_equal 4, unc_b, "uncovered bases"
+          assert_equal 11, unc_a, "uncovered bases"
+          assert_equal 3, unc_b, "uncovered bases"
 
           prop_unc_a = a[:p_bases_covered]
           prop_unc_b = b[:p_bases_covered]
-          assert_equal 0.98361, prop_unc_a.round(5), "proportion covered bases"
-          assert_equal 0.99514, prop_unc_b.round(5), "proportion covered bases"
+          assert_equal 0.98497, prop_unc_a.round(5), "proportion covered bases"
+          assert_equal 0.99635, prop_unc_b.round(5), "proportion covered bases"
 
         end
       end
@@ -112,8 +100,8 @@ class TestReadMetrics < Test::Unit::TestCase
 
           edit_a = a[:p_not_segmented].round(5)
           edit_b = b[:p_not_segmented].round(5)
-          assert_equal 0.47635, edit_a, "probability not segmented 1"
-          assert_equal 0.77451, edit_b, "probability not segmented 2"
+          assert_equal 0.23527, edit_a, "probability not segmented 1"
+          assert_equal 0.9341, edit_b, "probability not segmented 2"
 
         end
       end

data/test/test_transrater.rb

@@ -59,7 +59,7 @@ class TestTransrater < Test::Unit::TestCase
         Dir.chdir tmpdir do
           all = @rater.all_metrics(@left, @right)
           score = @rater.assembly_score
-          assert_equal 0.4078, score.round(5) # regression test
+          assert_equal 0.31136, score.round(5) # regression test
         end
       end
     end

data/test/vagrant/centos_6.5_64/Vagrantfile

@@ -0,0 +1,122 @@
+# -*- mode: ruby -*-
+# vi: set ft=ruby :
+
+# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
+VAGRANTFILE_API_VERSION = "2"
+
+Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
+  # All Vagrant configuration is done here. The most common configuration
+  # options are documented and commented below. For a complete reference,
+  # please see the online documentation at vagrantup.com.
+
+  # Every Vagrant virtual environment requires a box to build off of.
+  config.vm.box = "chef/centos-6.5"
+
+  # Disable automatic box update checking. If you disable this, then
+  # boxes will only be checked for updates when the user runs
+  # `vagrant box outdated`. This is not recommended.
+  # config.vm.box_check_update = false
+
+  # Create a forwarded port mapping which allows access to a specific port
+  # within the machine from a port on the host machine. In the example below,
+  # accessing "localhost:8080" will access port 80 on the guest machine.
+  # config.vm.network "forwarded_port", guest: 80, host: 8080
+
+  # Create a private network, which allows host-only access to the machine
+  # using a specific IP.
+  # config.vm.network "private_network", ip: "192.168.33.10"
+
+  # Create a public network, which generally matched to bridged network.
+  # Bridged networks make the machine appear as another physical device on
+  # your network.
+  # config.vm.network "public_network"
+
+  # If true, then any SSH connections made will enable agent forwarding.
+  # Default value: false
+  # config.ssh.forward_agent = true
+
+  # Share an additional folder to the guest VM. The first argument is
+  # the path on the host to the actual folder. The second argument is
+  # the path on the guest to mount the folder. And the optional third
+  # argument is a set of non-required options.
+  # config.vm.synced_folder "../data", "/vagrant_data"
+
+  # Provider-specific configuration so you can fine-tune various
+  # backing providers for Vagrant. These expose provider-specific options.
+  # Example for VirtualBox:
+  #
+  # config.vm.provider "virtualbox" do |vb|
+  #   # Don't boot with headless mode
+  #   vb.gui = true
+  #
+  #   # Use VBoxManage to customize the VM. For example to change memory:
+  #   vb.customize ["modifyvm", :id, "--memory", "1024"]
+  # end
+  #
+  # View the documentation for the provider you're using for more
+  # information on available options.
+
+  # Enable provisioning with CFEngine. CFEngine Community packages are
+  # automatically installed. For example, configure the host as a
+  # policy server and optionally a policy file to run:
+  #
+  # config.vm.provision "cfengine" do |cf|
+  #   cf.am_policy_hub = true
+  #   # cf.run_file = "motd.cf"
+  # end
+  #
+  # You can also configure and bootstrap a client to an existing
+  # policy server:
+  #
+  # config.vm.provision "cfengine" do |cf|
+  #   cf.policy_server_address = "10.0.2.15"
+  # end
+
+  # Enable provisioning with Puppet stand alone.  Puppet manifests
+  # are contained in a directory path relative to this Vagrantfile.
+  # You will need to create the manifests directory and a manifest in
+  # the file default.pp in the manifests_path directory.
+  #
+  # config.vm.provision "puppet" do |puppet|
+  #   puppet.manifests_path = "manifests"
+  #   puppet.manifest_file  = "site.pp"
+  # end
+
+  # Enable provisioning with chef solo, specifying a cookbooks path, roles
+  # path, and data_bags path (all relative to this Vagrantfile), and adding
+  # some recipes and/or roles.
+  #
+  # config.vm.provision "chef_solo" do |chef|
+  #   chef.cookbooks_path = "../my-recipes/cookbooks"
+  #   chef.roles_path = "../my-recipes/roles"
+  #   chef.data_bags_path = "../my-recipes/data_bags"
+  #   chef.add_recipe "mysql"
+  #   chef.add_role "web"
+  #
+  #   # You may also specify custom JSON attributes:
+  #   chef.json = { mysql_password: "foo" }
+  # end
+
+  # Enable provisioning with chef server, specifying the chef server URL,
+  # and the path to the validation key (relative to this Vagrantfile).
+  #
+  # The Opscode Platform uses HTTPS. Substitute your organization for
+  # ORGNAME in the URL and validation key.
+  #
+  # If you have your own Chef Server, use the appropriate URL, which may be
+  # HTTP instead of HTTPS depending on your configuration. Also change the
+  # validation key to validation.pem.
+  #
+  # config.vm.provision "chef_client" do |chef|
+  #   chef.chef_server_url = "https://api.opscode.com/organizations/ORGNAME"
+  #   chef.validation_key_path = "ORGNAME-validator.pem"
+  # end
+  #
+  # If you're using the Opscode platform, your validator client is
+  # ORGNAME-validator, replacing ORGNAME with your organization name.
+  #
+  # If you have your own Chef Server, the default validation client name is
+  # chef-validator, unless you changed the configuration.
+  #
+  #   chef.validation_client_name = "ORGNAME-validator"
+end