lib/spec_id/protein_summary.rb in mspire-0.2.1 vs lib/spec_id/protein_summary.rb in mspire-0.2.2

@@ -143,13 +143,17 @@
     else
       name
     end
   end
 
-  def prefix_to_regex(prefix)
-    if prefix
-      /^#{Regexp.escape(prefix)}/
+  def flag_to_regex(flag, prefix=false)
+    if flag
+      if prefix
+        /^#{Regexp.escape(flag)}/
+      else
+        /#{Regexp.escape(flag)}/
+      end
     else
       nil
     end
   end
 
@@ -162,16 +166,16 @@
       end
     end
   end
 
   # filters on the false positive regex and sorts by prot probability
-  def filter_and_sort(uniq_prots, prefix=nil)
-    prefix_re = prefix_to_regex(prefix) 
+  def filter_and_sort(uniq_prots, flag=nil, prefix=false)
+    false_flag_re = flag_to_regex(flag, prefix) 
     sorted = uniq_prots.sort_by {|prt| [prt._probability, prt.parent._probability]}.reverse
     ## filter on prefix
     if prefix
-      sorted = sorted.reject {|prot| prot._protein_name =~ prefix_re }
+      sorted = sorted.reject {|prot| prot._protein_name =~ false_flag_re }
     end
     sorted
   end
 
   # assumes that these are sorted on probability
@@ -290,11 +294,11 @@
       group.protein.each do |prt|
         prots << prt 
       end
     end
     uniq_prots = prots.hash_by(:_protein_name).map{|name,prot_arr| prot_arr.first }
-    filtered_sorted_prots = filter_and_sort(uniq_prots, opt.f)
+    filtered_sorted_prots = filter_and_sort(uniq_prots, opt.f, opt.prefix)
 
     ## num proteins above cutoff (if opt.c)
     num_prots_html = ''
     if opt.c || opt.cut_at
       (num_prots, actual_fppr) = num_prots_above_fppr(filtered_sorted_prots, actual_percent_fp)
@@ -320,21 +324,20 @@
   end
 
   # takes spec_id object
   # the outfn is the output filename
   # opt is an OpenStruct that holds opt.f = the false prefix
-  def bioworks_output(spec_id, outfn, file=nil, false_prefix=nil, fppr_output_as_html=nil)
+  def bioworks_output(spec_id, outfn, file=nil, false_flag_re=nil, fppr_output_as_html=nil)
     fppr_output_as_html ||= ''
     header_anchors = [at('#', 'number'), at('prob','protein probability (for Bioworks, lower is better)'), at('ref', 'gi number if available (or complete reference)'), at('annotation', 'annotation from the fasta file'), at('%cov', 'percent of protein sequence covered by corresponding peptides'), at('peps', 'unique peptides identified (at any confidence) Click number to show/hide.'), at('#peps', 'total number of peptides seen (not unique)')]
     num_cols = header_anchors.size
     theaders = ths(header_anchors)
     proteins = spec_id.prots
     protein_num = 0
     rows = ""
-    prefix_re = prefix_to_regex(false_prefix)
     proteins.each do |prot|
-      if false_prefix && prot.reference =~ prefix_re
+      if false_flag_re && prot.reference =~ false_flag_re
         next
       end
       uniq_peps = Hash.new {|h,k| h[k] = true; }
       protein_num += 1
       prot.peps.each do |pep|
@@ -391,11 +394,12 @@
     opts = OptionParser.new do |op|
       op.banner = "usage: #{File.basename(__FILE__)} [options] <file>.xml ..."
       op.separator "    where file = bioworks -or- <run>-prot (prophet output)"
       op.separator "    outputs: <file>.summary.html"
       op.separator ""
-      op.on("-f", "--false <prefix>", "ignore proteins with prefix (def: #{DEF_PREFIX})") {|v| opt.f = v }
+      op.on("-f", "--false <prefix>", "ignore proteins with flag (def: #{DEF_PREFIX})") {|v| opt.f = v }
+      op.on("--prefix", "false flag for prefixes only") {|v| opt.prefix = v }
       op.on("-p", "--precision", "include the output from precision.rb") {|v| opt.p = v }
       op.separator("             if --precision then -f is used to specify a file or prefix")
       op.separator("             that indicates the false positives.")
       op.on("--peptide_count <filename>", "outputs text file with # peptides per protein") {|v| opt.peptide_count = v}
       op.separator ""
@@ -432,20 +436,23 @@
       when "protproph"
         #spec_id = SpecID.new(file)
         proph_output(file, outfn, opt, fppr_output_as_html)
       when "bioworks"
         spec_id = SpecID.new(file)
-        bioworks_output(spec_id, outfn, file, opt.f, fppr_output_as_html)
+
+        false_regex = flag_to_regex(opt.f, opt.prefix)
+        bioworks_output(spec_id, outfn, file, false_regex, fppr_output_as_html)
       else 
         abort "filetype for #{file} not recognized!"
       end
     end
 
   end # method create_from_command_line
 
   def create_precision_argv(file, opt)
     # include only those options specific
     new_argv = [file]
+    if opt.prefix ; new_argv << '--prefix' end
     if opt.f ; new_argv << '-f' << opt.f end
     if opt.o ; new_argv << '-o' << opt.o end
     new_argv
   end