protk 1.4.0 → 1.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 22d2c990e46bf29f08cbf00dc2ecd9a759fae457
-  data.tar.gz: 09dd0159d8b564d9d297a987c74e13833fabbc24
+  metadata.gz: 7329f51a45b5449ec979e76aca5727c6714a5bc8
+  data.tar.gz: e96f553b27c61c7ba1935d379e01086e9cb00725
 SHA512:
-  metadata.gz: 2b08c1086187da5755e4b0d98dcfebcff80893eb291e09291ea3853fa848ade7f464f83fc97a8fe362d2b9a96e915e2aa1945ddd6e0f39ada32d1a747a0c7d73
-  data.tar.gz: 767b474d9f0b890342f783bff0e8633434542cf151d34f239f9ed52dab43a1909b683fa285b25954af54856d68493ab67e4776d152830bc938e62a932c63e9b3
+  metadata.gz: fb933aa9ce0cc6fabb19b0a731bb8d74f23456937ec4d08973477f8f956eb733fcb44b26b66fc61242f5ea6c617d0c3a178b83f16dc568ad5f330db9dcd27c1d
+  data.tar.gz: 5b2b370cea53d3a3ec9eee9d5916df8f910ef12181c0bce9b660c1d82d042e00a5b66ce7fcba6a864cd1a6266aa2fbffec998ae26700f4ddd7903ab141ba3241

data/bin/augustus_to_proteindb.rb

@@ -110,13 +110,25 @@ def sequence_fasta_header(transcript_line,coding_sequences,scaffold)
 
   tmatch=transcript_line.match(/transcript\t(\d+)\t(\d+).*?([-\+]{1}).*?ID=(.*?);/)
 #  require 'debugger'; debugger
-  tstart=tmatch[1]
-  tend=tmatch[2]
-  tstrand="fwd"
-  tstrand = "rev" if tmatch[3]=="-"
+  tstart,tend,tstrand = transcript_line.match(/transcript\t(\d+)\t(\d+).*?([-\+]{1})/).captures
+
+  # tstart=tmatch[1]
+  # tend=tmatch[2]
+  tsidfield = transcript_line.split("\t")[8]
+  tid = nil
+  if tsidfield =~ /ID=/
+    tid = tsidfield.match(/ID=(.*?);/).captures[0]
+  else
+    tid = tsidfield.gsub(" ","_").gsub(";","_")
+  end
+
+   # require 'byebug';byebug
+
+  tstrandfr="fwd"
+  tstrandfr = "rev" if tstrand=="-"
 
-  tid=tmatch[4]
-  header=">lcl|#{sanitize_scaffold_idstring(scaffold)}_#{tstrand}_#{tid} #{tstart}|#{tend}"
+  # tid=tmatch[4]
+  header=">lcl|#{sanitize_scaffold_idstring(scaffold)}_#{tstrandfr}_#{tid} #{tstart}|#{tend}"
   if $add_transcript_info
     coding_sequences.each { |coding_sequence| header << " #{cds_to_header_text(coding_sequence,tid)}" }
   end
@@ -135,13 +147,14 @@ end
 def parse_gene(gene_lines)
 
   geneid=gene_lines[0].match(/start gene (.*)/)[1]
+  scaffold_id = gene_lines[1].split("\t")[0]
   transcripts=get_transcript_lines(gene_lines)
   coding_sequences=get_cds_lines(gene_lines)
   proteins=get_protein_sequence_lines(gene_lines)
   fasta_string=""
   throw "transcripts/protein mismatch" unless transcripts.length == proteins.length
   transcripts.each_with_index do |ts, i|  
-    fh=sequence_fasta_header(ts,coding_sequences,$current_scaffold)
+    fh=sequence_fasta_header(ts,coding_sequences,scaffold_id)
     fasta_string << "#{fh}\n"
     ps=protein_sequence(proteins[i])  
     fasta_string << "#{ps}\n"
@@ -152,14 +165,14 @@ def parse_gene(gene_lines)
   fasta_string
 end
 
-def capture_scaffold(line)
-  if line =~ /-- prediction on sequence number.*?name = (.*)\)/
-    $current_scaffold=line.match(/-- prediction on sequence number.*?name = (.*)\)/)[1]
-    if ( $print_progress)
-      puts $current_scaffold
-    end
-  end
-end
+# def capture_scaffold(line)
+#   if line =~ /-- prediction on sequence number.*?name = (.*)\)/
+#     $current_scaffold=line.match(/-- prediction on sequence number.*?name = (.*)\)/)[1]
+#     if ( $print_progress)
+#       puts $current_scaffold
+#     end
+#   end
+# end
 
 def capture_gene_start(line)
   if line =~ /# start gene/
@@ -174,14 +187,14 @@ def at_gene_end(line)
   return false
 end
 
-$current_scaffold=""
+# $current_scaffold=""
 gene_lines=[]
 $capturing_gene=false
 
 
 File.open(inname).each_with_index do |line, line_i|  
   line.chomp!
-  capture_scaffold(line)
+  # capture_scaffold(line)
   capture_gene_start(line)
 
   if at_gene_end(line)

data/bin/interprophet.rb

@@ -65,9 +65,11 @@ if ( !Pathname.new(output_file).exist? || prophet_tool.over_write )
 
   if for_galaxy
     inputs = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
+    input_files = inputs.collect { |e| e.staged_path }
+  else
+    input_files = inputs
   end
 
-  input_files = inputs.collect { |e| e.staged_path }
 
   cmd << " #{input_files.join(" ")} #{output_file}"
 

data/bin/protxml_to_gff.rb

@@ -11,12 +11,12 @@ require 'protk/gffdb'
 require 'protk/protein'
 require 'protk/peptide'
 require 'protk/tool'
+require 'protk/error'
 require 'libxml'
 require 'bio'
 
 include LibXML
 
-
 class NoGFFEntryFoundError < StandardError
 end
 
@@ -26,6 +26,9 @@ end
 class MultipleGFFEntriesForProteinError < StandardError
 end
 
+class GFFIDRegexNotMatchedError < ProtkError
+end
+
 def parse_proteins(protxml_file)
   protxml_parser=XML::Parser.file(protxml_file)
   protxml_doc=protxml_parser.parse
@@ -35,7 +38,14 @@ end
 
 def protein_id_to_gffid(protein_id,gff_idregex)
 	return protein_id if gff_idregex.nil?
-	return protein_id.match(/#{gff_idregex}/)[1]
+
+	m = protein_id.match(/#{gff_idregex}/)
+	if m
+		return m.captures[0]		
+	else
+		raise GFFIDRegexNotMatchedError.new("Unable to parse gff_id from #{protein_id} using regex #{gff_idregex}")
+	end
+
 end
 
 def protein_id_to_genomeid(protein_id,genome_idregex)
@@ -103,6 +113,8 @@ input_protxml=ARGV[0]
 $protk.log "Creating GFFDB", :info
 gffdb = GFFDB.create(tool.coords_file) if tool.coords_file
 
+#require 'byebug';byebug
+
 # genome_db = prepare_fasta(tool.genome,'nucl')
 $protk.log "Preparing FASTA index", :info
 prot_db = prepare_fasta(tool.database,'prot')
@@ -157,14 +169,22 @@ proteins.each do |protein|
 		rescue ProteinNotInDBError
 			$protk.log "No entry for #{parsed_name_for_protdb}", :info
 		rescue MultipleGFFEntriesForProteinError
-			$protk.log "Multiple entries in gff file for #{parsed_name_for_gffid}", :info
-		rescue PeptideNotInProteinError
-			$protk.log "A peptide was not found in its parent protein #{protein.protein_name}" , :warn
+			$protk.log "Multiple entries in gff file for #{parsed_name_for_gffid}", :warn
+			# require 'byebug';byebug
+			# puts gff_parent_entries
+		rescue PeptideNotInProteinError => e
+			# This is generally not fatal. It can happen because of Leucine Isoleucine issues
+			#
+			$protk.log "#{e.message}. Parent protein ID #{protein.protein_name}" , :info
+			# require 'byebug';byebug
+			# puts protein.protein_name
+		rescue GFFIDRegexNotMatchedError => e
+			$protk.log e.message, :info
 		end
 	end
 end
 
 if num_missing_gff_entries>0
-	$protk.log "Failed to lookup gff entries. Try setting --gff-idregex" if tool.gff_idregex.nil?
+	$protk.log "Failed to lookup gff entries. Try setting --gff-idregex", :error if tool.gff_idregex.nil?
 end
 

data/lib/protk/error.rb

@@ -0,0 +1,7 @@
+
+class ProtkError < StandardError
+	attr_accessor :message
+	def initialize(message)
+		@message=message
+	end
+end

data/lib/protk/galaxy_util.rb

@@ -23,6 +23,30 @@ class GalaxyUtil
   end
   
 
+    # Galaxy changes things like @ to __at__ we need to change it back
+    #
+    def self.decode_galaxy_string!(mstring)
+        mstring.gsub!("__at__","@")
+        mstring.gsub!("__oc__","{")
+        mstring.gsub!("__cc__","}")
+        mstring.gsub!("__ob__","[")
+        mstring.gsub!("__cb__","]")
+        mstring.gsub!("__gt__",">")
+        mstring.gsub!("__lt__","<")
+        mstring.gsub!("__sq__","'")
+        mstring.gsub!("__dq__","\"")
+        mstring.gsub!("__cn__","\n")
+        mstring.gsub!("__cr__","\r")
+        mstring.gsub!("__tc__","\t")
+        mstring.gsub!("__pd__","#")
+
+        # For characters not allowed at all by galaxy
+        mstring.gsub!("__pc__","|")
+
+        mstring
+    end
+
+
   # Unused
 
   # def self.stage_protxml(input_protxml_path)

data/lib/protk/peptide.rb

@@ -1,9 +1,11 @@
 require 'libxml'
 require 'bio'
 require 'protk/bio_gff3_extensions'
+require 'protk/error'
+
 include LibXML
 
-class PeptideNotInProteinError < StandardError
+class PeptideNotInProteinError < ProtkError
 end
 
 class Peptide
@@ -43,11 +45,11 @@ class Peptide
 	def coords_in_protein(prot_seq,reverse=false)
 		if reverse
 			pep_index = prot_seq.reverse.index(self.sequence.reverse)
-			raise PeptideNotInProteinError if pep_index.nil?
+			raise PeptideNotInProteinError.new("Peptide #{self.sequence} not found in protein #{prot_seq} ") if pep_index.nil?
 			pep_start_i = pep_index
 		else
 			pep_start_i = prot_seq.index(self.sequence)
-			raise PeptideNotInProteinError if pep_start_i.nil?			
+			raise PeptideNotInProteinError.new("Peptide #{self.sequence} not found in protein #{prot_seq} ") if pep_start_i.nil?			
 		end
 		pep_end_i = pep_start_i+self.sequence.length
 		{:start => pep_start_i,:end => pep_end_i}
@@ -91,31 +93,26 @@ class Peptide
 		pep_end_i = pep_start_i+self.sequence.length*3
 		fragments=[]
 		ordered_cds_records.each do |cds_record|
-			# puts cds_record
+
 			fragment = nil
 			fragment_len = 0
 			if on_reverse_strand
 
 				in_peptide = (i<pep_end_i) && (i>=pep_start_i)
 				before_len = [pep_start_i-i,0].max
-				# puts before_len
-				# puts in_peptide
-				# puts "i #{i} pi #{pep_end_i} psi #{pep_start_i}"
-				if in_peptide
 
+				if in_peptide
 					fragment_end = cds_record.end
 					fragment_len = [cds_record.length,pep_end_i-i].min
 					fragment_start = fragment_end-fragment_len+1
-					# fragment = {:start=>fragment_start,:end=>fragment_end}
 					fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
-
 				elsif before_len>0
 					fragment_end = cds_record.end - before_len
 					fragment_len = [cds_record.length-before_len,pep_end_i-i-before_len].min
-					# puts "Frag len #{fragment_len}"
 					fragment_start = fragment_end - fragment_len + 1
-					fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
-					# fragment = {:start=>fragment_start,:end=>fragment_end}
+					if fragment_len>0
+						fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+					end
 				else
 					fragment=nil
 				end				
@@ -126,14 +123,14 @@ class Peptide
 					fragment_start = cds_record.start
 					fragment_len = [cds_record.length,pep_end_i-i].min
 					fragment_end = fragment_start+fragment_len-1
-					# fragment = {:start=>fragment_start,:end=>fragment_end}
 					fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
 				elsif before_len>0
 					fragment_start = cds_record.start + before_len
 					fragment_len = [cds_record.length-before_len,pep_end_i-i-before_len].min
 					fragment_end = fragment_start + fragment_len-1
-					# fragment = {:start=>fragment_start,:end=>fragment_end}
-					fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+					if fragment_len>0
+						fragment = gff_record_for_peptide_fragment(fragment_start,fragment_end,cds_record)
+					end
 				else
 					fragment=nil
 				end

data/lib/protk/tandem_search_tool.rb

@@ -1,4 +1,5 @@
 require 'protk/search_tool'
+require 'protk/galaxy_util'
 
 class String
   def xtandem_modification_motif?
@@ -70,28 +71,6 @@ class TandemSearchTool < SearchTool
 	end
 
 	private
-	# Galaxy changes things like @ to __at__ we need to change it back
-	#
-	def decode_galaxy_string(mstring)
-  		mstring.gsub!("__at__","@")
-  		mstring.gsub!("__oc__","{")
-  		mstring.gsub!("__cc__","}")
-  		mstring.gsub!("__ob__","[")
-  		mstring.gsub!("__cb__","]")
-  		mstring.gsub!("__gt__",">")
-  		mstring.gsub!("__lt__","<")
-  		mstring.gsub!("__sq__","'")
-  		mstring.gsub!("__dq__","\"")
-  		mstring.gsub!("__cn__","\n")
-  		mstring.gsub!("__cr__","\r")
-  		mstring.gsub!("__tc__","\t")
-  		mstring.gsub!("__pd__","#")
-
-  		# For characters not allowed at all by galaxy
-  		mstring.gsub!("__pc__","|")
-
-  		mstring
-	end
 
 	def set_option(std_params, tandem_key, value)
   		notes = std_params.find("/bioml/note[@type=\"input\" and @label=\"#{tandem_key}\"]")
@@ -180,7 +159,7 @@ class TandemSearchTool < SearchTool
 				if opt_val.is_a?(TrueClass) || opt_val.is_a?(FalseClass)
 					opt_val = opt_val ? "yes" : "no"
 				end
-				append_option(std_params,xtandem_key,decode_galaxy_string(opt_val.to_s)) 
+				append_option(std_params,xtandem_key,GalaxyUtil.decode_galaxy_string!(opt_val.to_s)) 
 			end
 		end
 
@@ -208,7 +187,7 @@ class TandemSearchTool < SearchTool
 		#
 
 		var_mods = self.var_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject {|e| e.empty? }
-		var_mods=var_mods.collect {|mod| decode_galaxy_string(mod) }
+		var_mods=var_mods.collect {|mod| GalaxyUtil.decode_galaxy_string!(mod) }
 
 		# var_mods allows motif's as well as standard mods. These should be in a separate array
 		var_motifs = [].replace(var_mods)
@@ -216,7 +195,7 @@ class TandemSearchTool < SearchTool
 		var_motifs.keep_if {|mod| mod.xtandem_modification_motif? }
 
 		fix_mods = self.fix_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject { |e| e.empty? }
-		fix_mods=fix_mods.collect {|mod| decode_galaxy_string(mod)}
+		fix_mods=fix_mods.collect {|mod| GalaxyUtil.decode_galaxy_string!(mod)}
 
 		# We also support the --glyco and --methionineo shortcuts.
 		# Add these here. No check is made for duplication

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.4.1
 platform: ruby
 authors:
 - Ira Cooke
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-05-01 00:00:00.000000000 Z
+date: 2015-03-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: open4
@@ -266,6 +266,7 @@ files:
 - lib/protk/data/uniprot_accessions_table.txt
 - lib/protk/data/uniprot_input_accessions.loc
 - lib/protk/data/yum_packages.yaml
+- lib/protk/error.rb
 - lib/protk/fastadb.rb
 - lib/protk/galaxy_stager.rb
 - lib/protk/galaxy_util.rb