seqtrimnext 2.0.29

data/lib/seqtrimnext/templates/genomics_454_with_paired.txt

@@ -0,0 +1,5 @@
+# ======================================
+# General parameters GENOMICS WITH POSSIBLE LINKER
+# ======================================
+
+plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginContaminants,PluginLinker,PluginVectors,PluginLowQuality

data/lib/seqtrimnext/templates/low_quality.txt

@@ -0,0 +1,5 @@
+# ======================================
+# General parameters GENOMICS WITH POSSIBLE LINKER
+# ======================================
+
+plugin_list = PluginIndeterminations,PluginContaminants,PluginVectors,PluginLowQuality

data/lib/seqtrimnext/templates/low_quality_and_low_complexity.txt

@@ -0,0 +1,5 @@
+# ======================================
+# General parameters GENOMICS WITH POSSIBLE LINKER
+# ======================================
+
+plugin_list = PluginIndeterminations,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity

data/lib/seqtrimnext/templates/transcriptomics_454.txt

@@ -0,0 +1,8 @@
+# ======================================
+# General parameters
+# ======================================
+
+
+plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginFindPolyAt,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
+
+contaminants_db="contaminants.fasta cont_ribosome.fasta"

data/lib/seqtrimnext/templates/transcriptomics_plants.txt

@@ -0,0 +1,8 @@
+# ======================================
+# General parameters
+# ======================================
+
+
+plugin_list = PluginLowHighSize,PluginMids,PluginIndeterminations,PluginAbAdapters,PluginFindPolyAt,PluginContaminants,PluginVectors,PluginLowQuality,PluginLowComplexity
+
+contaminants_db="contaminants.fasta cont_ribosome.fasta cont_mitochondrias.fasta cont_plastids.fasta"

data/lib/seqtrimnext/utils/extract_samples.rb

@@ -0,0 +1,52 @@
+require "fasta_reader.rb"
+
+
+######################################
+# Author:: Almudena Bocinos Rioboo
+# Extract ramdom sequences until "num_seqs" 
+# Inherit:: FastaReader
+######################################
+
+class ExtractSamples < FastaReader
+  attr_accessor :num_seqs
+  def initialize(file_name)
+    @num_seqs = 0
+    super(file_name)
+  end
+
+       # override begin processing
+ def on_begin_process()
+    $LOG.info " Begin Extract Samples"
+    @fich = File.open("results/Sample.txt",'w') 
+    @max = 1000
+    
+ end
+ 
+    # override processing sequence
+  def on_process_sequence(seq_name,seq_fasta)
+      ra_seq = Kernel.rand
+     
+      if ((@num_seqs < @max) and (ra_seq>0.5)) #if cond is successful then, choose a part from this sequence
+        #calculate the part from the sequence
+        width = (Kernel.rand * 50 ) + 300
+        ra_part1 = Kernel.rand * (seq_fasta.length-width)
+        ra_part2 = ra_part1 + width
+        sub_seq_fasta = seq_fasta.slice(ra_part1,ra_part2)
+        
+        @fich.puts "#{seq_name} "
+        @fich.puts "#{sub_seq_fasta} "
+        @num_seqs += 1
+        
+      end
+      
+  end
+    
+    
+
+       #override end processing
+ def on_end_process()
+    $LOG.info "All Samples have been extracted"
+    @fich.close
+ end
+
+end

data/lib/seqtrimnext/utils/fasta2xml.rb

@@ -0,0 +1,69 @@
+#!/usr/bin/env ruby
+
+
+command_info="
+#================================================
+# Author: Almudena Bocinos Rioboo    
+#
+#
+# Usage: fasta2xml.rb <fasta_file>  [> <out_file.xml>]
+#
+# Converts a fasta file to xml format (used for cabog)
+#
+# Prints to stdout, can be redirected to file with >
+#
+#================================================
+\n";
+
+#require "utils/fasta_utils"
+require File.dirname(__FILE__) + "/utils/fasta_utils"
+
+#receive one argument or fail
+if ARGV.length != 1
+  puts command_info;
+  Process.exit(-1);
+end
+
+#get file name
+file_name=ARGV[0];
+
+#check if file exists
+if !File.exist?(file_name)
+  puts "File #{file_name} not found.\n";
+  puts command_info;
+  Process.exit(-1);
+end
+
+######################################
+# Define a subclass to override events
+######################################
+class FastaProcessor< FastaUtils::FastaReader
+
+  #override begin processing
+  def on_begin_process()
+      
+    # print XML header
+    puts "<?xml version=\"1.0\"?>\n<trace_volume>\n";
+    
+  end
+ 
+  #override sequence processing
+  def on_process_sequence(seq_name,seq_fasta)
+    
+    # prints the xml tags
+    puts "<trace>\n\t<trace_name>#{seq_name}</trace_name>\n\t<clip_vector_left>1</clip_vector_left>\n\t<clip_vector_right>#{seq_fasta.length.to_s}</clip_vector_right>\n</trace>\n";
+    
+  end
+  
+  #override end processing
+  def on_end_process()
+  
+    #print foot
+    puts "</trace_volume>\n";
+    
+  end
+   
+end
+
+#Create a new instance to process the file
+f=FastaProcessor.new(file_name);

data/lib/seqtrimnext/utils/global_match.rb

@@ -0,0 +1,65 @@
+class GMatch
+  
+  attr_accessor :offset
+  attr_accessor :match
+  
+  
+end
+
+class Regexp
+  def global_match(input_str,overlap_group_no = 0)
+    res = []
+    
+    str=input_str
+    
+    last_end = 0
+    
+    loop do
+      str = input_str.slice(last_end,input_str.length-last_end)
+      if str.nil? or str.empty?
+        break
+      end
+      
+      m = self.match(str)
+      # puts "find in: #{str}"
+      
+      if !m.nil?
+        # puts m.inspect
+        
+        
+        new_match=GMatch.new()
+        new_match.offset = last_end
+        new_match.match = m
+        
+        res.push new_match
+        
+        if overlap_group_no == 0
+          last_end += m.end(overlap_group_no)
+        else
+          last_end += m.begin(overlap_group_no)
+        end
+        
+      else
+        break
+      end
+      
+    end
+    
+    
+    return res
+  end
+    
+  
+  # def global_match(str, &proc)
+  #     retval = nil
+  #     loop do
+  #       res = str.sub(self) do |m|
+  #         proc.call($~) # pass MatchData obj
+  #         ''
+  #       end
+  #       break retval if res == str
+  #       str = res
+  #       retval ||= true
+  #     end
+  #   end
+end

data/lib/seqtrimnext/utils/hash_stats.rb

@@ -0,0 +1,29 @@
+
+class Hash
+
+#increments a hash with the stats defined in h_stats
+
+# three levels:
+# STATS->plugin_name->Property->count
+
+def add_stats(h_stats)
+	h=self
+
+	h_stats.each do |plugin_hash,add_stats|
+		h[plugin_hash]={} if h[plugin_hash].nil?	
+		
+		add_stats.each do |property,hash_value|
+			h[plugin_hash][property]={} if h[plugin_hash][property].nil?	
+		
+			hash_value.each do |value, count|
+				h[plugin_hash][property][value]=(h[plugin_hash][property][value]||0) + count
+			end
+		end
+	end
+
+end            
+                
+
+
+end
+

data/lib/seqtrimnext/utils/json_utils.rb

@@ -0,0 +1,50 @@
+#================================================
+# SCBI - dariogf <soporte@scbi.uma.es>
+#------------------------------------------------
+#
+# Version: 0.1 - 04/2009
+#
+# Usage: require "utils/json_utils"
+#
+# Fasta utilities
+#
+# 
+#
+#================================================
+
+module JsonUtils
+  
+  require 'json';
+  
+     
+  def to_pretty_json
+    return JSON.pretty_generate(self)
+  end
+
+
+  def from_json
+       return JSON.parse(self)
+  end
+  
+  # ===========================================
+  
+  #------------------------------------
+  # get json data
+  #------------------------------------
+  def self.get_json_data(file_path)
+    file1 = File.open(file_path)
+    text = file1.read
+    file1.close
+
+    # wipe text
+    text=text.grep(/^\s*[^#]/).to_s
+
+    # decode json
+    data = JSON.parse(text)
+
+    return data
+  end
+  
+end
+
+

data/lib/seqtrimnext/utils/load_fasta_names_in_hash.rb

@@ -0,0 +1,37 @@
+#================================================
+# SCBI - dariogf <soporte@scbi.uma.es>
+#------------------------------------------------
+#
+# Version: 0.1 - 04/2009
+#
+# Usage: require "utils/fasta_utils"
+#
+# Fasta utilities
+#
+# 
+#
+#================================================
+
+require File.dirname(__FILE__) +"/fasta_reader.rb"
+
+	######################################
+	# Define a subclass to override events
+	######################################
+class LoadFastaNamesInHash< FastaReader
+
+	attr_reader :names
+
+	#override begin processing
+	def on_begin_process()
+		@names = {}
+	end
+
+	def on_process_sequence(seq_name,seq_fasta)
+		@names[seq_name]=true
+	end
+
+	#override end processing
+	def on_end_process()
+	end
+
+end

data/lib/seqtrimnext/utils/load_qual_in_hash.rb

@@ -0,0 +1,37 @@
+#================================================
+# SCBI - dariogf <soporte@scbi.uma.es>
+#------------------------------------------------
+#
+# Version: 0.1 - 04/2009
+#
+# Usage: require "utils/fasta_utils"
+#
+# Fasta utilities
+#
+# 
+#
+#================================================
+
+require File.dirname(__FILE__) +"/qual_reader.rb"
+
+	######################################
+	# Define a subclass to override events
+	######################################
+class LoadQualInHash< QualReader
+
+	attr_reader :quals
+
+	#override begin processing
+	def on_begin_process()
+		@quals = {}
+	end
+
+	def on_process_sequence(seq_name,seq_qual)
+		@quals[seq_name]=seq_qual
+	end
+
+	#override end processing
+	def on_end_process()
+	end
+
+end

data/lib/seqtrimnext/utils/recover_mid.rb

@@ -0,0 +1,95 @@
+module RecoverMid
+
+  #receives hit of mid from blast, complete db_mid from DB and SEQ_fasta
+  def recover_mid(hit, db_mid, seq)
+  
+    mid_in_seq = seq[hit.q_beg..hit.q_end]  
+    mid_in_mid = db_mid[hit.s_beg..hit.s_end]
+
+		if hit.s_beg==0 # look right parts
+	
+			mid_part=db_mid[hit.s_end+1..db_mid.length]
+	 	  seq_part=seq[hit.q_end+1,mid_part.length+1]
+	 	  
+	 	  common=mid_part.lcs(seq_part)
+	 	  
+	 	  
+	 	  in_seq_pos=seq_part.index(common)
+			  
+        # puts "seq right part: #{seq_part}, mid right part #{mid_part} => Match: #{common}"
+		
+	 	  if in_seq_pos>1 #
+
+          # puts "NO VALE, comienza en #{in_seq_pos}"
+	 	    in_seq_pos=0
+		 	  	common=''
+		 	end
+
+			new_q_beg=hit.q_beg
+			new_q_end=hit.q_end+in_seq_pos+common.length
+			recovered_mid=seq[new_q_beg..new_q_end]
+
+			recovered_size=hit.q_end-hit.q_beg+1+common.length
+
+		
+		else hit.s_end == db_mid.length-1#look left parts
+			mid_part=db_mid[0..hit.s_beg-1]
+	 	  seq_part=seq[hit.q_beg-mid_part.length-1..hit.q_beg-1]
+	 	  
+	 	  common=mid_part.lcs(seq_part)
+	 	  
+	 	  in_seq_pos=hit.q_beg-mid_part.length-1+seq_part.index(common)
+			  
+        # puts "seq left part: #{seq_part}, mid right part #{mid_part} => Match: #{common} at #{in_seq_pos}"
+		
+	 	  if in_seq_pos+common.length<hit.q_beg-1 
+          # puts "NO VALE, comienza en #{in_seq_pos+common.length} < #{hit.q_beg}"
+	 	    in_seq_pos=hit.q_beg
+		 	  	common=''
+		 	end
+
+			new_q_beg=in_seq_pos
+			new_q_end=hit.q_end
+			recovered_mid=seq[new_q_beg..new_q_end]
+
+			recovered_size=hit.q_end-hit.q_beg+1+common.length
+	
+		end
+		
+		return [new_q_beg, new_q_end, recovered_size,recovered_mid]
+	
+	end
+
+end
+
+class String
+		def lcs(s2)
+			s1=self
+			res="" 
+			num=Array.new(s1.size){Array.new(s2.size)}
+			len,ans=0
+			lastsub=0
+			s1.scan(/./).each_with_index do |l1,i |
+				s2.scan(/./).each_with_index do |l2,j |
+				  unless l1==l2
+				    num[i][j]=0
+				  else
+				    (i==0 || j==0)? num[i][j]=1 : num[i][j]=1 + num[i-1][j-1]
+				    if num[i][j] > len
+				      len = ans = num[i][j]
+				      thissub = i
+				      thissub -= num[i-1][j-1] unless num[i-1][j-1].nil?  
+				      if lastsub==thissub
+				        res+=s1[i,1]
+				      else
+				        lastsub=thissub
+				        res=s1[lastsub, (i+1)-lastsub]
+				      end
+				    end
+				  end
+				end
+			end
+			res
+		end
+end
+

data/lib/seqtrimnext/utils/string_utils.rb

@@ -0,0 +1,56 @@
+
+class String
+  
+   def integer?
+                     
+     res = true
+      
+     begin
+       r=Integer(self)
+     rescue
+       res=false
+     end
+     
+     return res
+   end
+   
+   def decamelize 
+        self.to_s. 
+          gsub(/([A-Z\d]+)([A-Z][a-z])/, '\1_\2'). 
+          gsub(/([a-z]+)([A-Z\d])/, '\1_\2'). 
+          gsub(/([A-Z]{2,})(\d+)/i, '\1_\2'). 
+          gsub(/(\d+)([a-z])/i, '\1_\2'). 
+          gsub(/(.+?)\&(.+?)/, '\1_&_\2'). 
+          gsub(/\s/, '_').downcase 
+   end
+  
+end
+
+class File
+  
+  def self.is_zip?(file_path)
+    res=false
+    begin
+      f=File.open(file_path,'rb')
+      head=f.read(4)
+      f.close
+      res=(head=="PK\x03\x04")
+    rescue
+      res=false
+    end
+    
+    return res
+  end
+  
+  def self.unzip(file_path)
+    unzipped=`unzip "#{file_path}"`
+    file_list = unzipped.split("\n")
+    list=[]
+    
+    # select only the files, not folders
+    list=file_list.select{|e| e=~/inflating/}.map{|e| e.gsub('inflating:','').strip}
+    
+    return list
+  end
+  
+end

data/lib/seqtrimnext.rb

@@ -0,0 +1,37 @@
+$:.unshift(File.dirname(__FILE__)) unless
+  $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+
+
+# setup REQUIRE_PATH
+
+ROOT_PATH=File.join(File.dirname(__FILE__),'seqtrimnext')
+
+$: << File.expand_path(File.join(ROOT_PATH, 'classes'))
+
+#finds the classes that were in the folder 'plugins'
+$: << File.expand_path(File.join(ROOT_PATH, 'plugins'))
+
+
+#finds the classes that were in the folder 'plugins'
+$: << File.expand_path(File.join(ROOT_PATH, 'actions'))
+
+#finds the classes that were in the folder 'utils'
+$: << File.expand_path(File.join(ROOT_PATH, 'utils'))
+
+$: << File.expand_path(File.join(ROOT_PATH, 'classes','em_classes'))
+
+$: << File.expand_path(File.join(ROOT_PATH, 'latex','classes'))
+
+# puts $:
+
+module Seqtrimnext
+  
+  # SEQTRIM_VERSION_REVISION=27
+  # SEQTRIM_VERSION_STAGE = 'b'
+  # SEQTRIM_VERSION = "2.0.0#{SEQTRIM_VERSION_STAGE}#{SEQTRIM_VERSION_REVISION}"
+  
+  VERSION = '2.0.29'
+  
+  SEQTRIM_VERSION = VERSION
+  
+end

data/script/console

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+# File: script/console
+irb = RUBY_PLATFORM =~ /(:?mswin|mingw)/ ? 'irb.bat' : 'irb'
+
+libs =  " -r irb/completion"
+# Perhaps use a console_lib to store any extra methods I may want available in the cosole
+# libs << " -r #{File.dirname(__FILE__) + '/../lib/console_lib/console_logger.rb'}"
+libs <<  " -r #{File.dirname(__FILE__) + '/../lib/seqtrimnext.rb'}"
+puts "Loading seqtrimnext gem"
+exec "#{irb} #{libs} --simple-prompt"

data/script/destroy

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
+
+begin
+  require 'rubigen'
+rescue LoadError
+  require 'rubygems'
+  require 'rubigen'
+end
+require 'rubigen/scripts/destroy'
+
+ARGV.shift if ['--help', '-h'].include?(ARGV[0])
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
+RubiGen::Scripts::Destroy.new.run(ARGV)

data/script/generate

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
+
+begin
+  require 'rubigen'
+rescue LoadError
+  require 'rubygems'
+  require 'rubigen'
+end
+require 'rubigen/scripts/generate'
+
+ARGV.shift if ['--help', '-h'].include?(ARGV[0])
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
+RubiGen::Scripts::Generate.new.run(ARGV)

data/test/test_helper.rb

@@ -0,0 +1,3 @@
+require 'stringio'
+require 'test/unit'
+require File.dirname(__FILE__) + '/../lib/seqtrimnext'

data/test/test_seqtrimnext.rb

@@ -0,0 +1,11 @@
+require File.dirname(__FILE__) + '/test_helper.rb'
+
+class TestSeqtrimnext < Test::Unit::TestCase
+
+  def setup
+  end
+  
+  def test_truth
+    assert true
+  end
+end