in progress

diff --git a/forester/ruby/evoruby/lib/evo/io/parser/hmmscan_multi_domain_extractor.rb b/forester/ruby/evoruby/lib/evo/io/parser/hmmscan_multi_domain_extractor.rb
index fe62a42..f773e26 100644 (file)
--- a/forester/ruby/evoruby/lib/evo/io/parser/hmmscan_multi_domain_extractor.rb
+++ b/forester/ruby/evoruby/lib/evo/io/parser/hmmscan_multi_domain_extractor.rb
@@ -190,7 +190,7 @@ module Evoruby
         log d.to_str
       end
       log
-      log'Failing target domain(s):'
+      log 'Failing target domain(s) (in proteins sequences with target domain architecture):'
       @failing_domains_data = @failing_domains_data.sort{|a, b|a<=>b}.to_h
       @failing_domains_data.each do |n, d|
         log d.to_str
@@ -560,13 +560,14 @@ module Evoruby
       target_das = target_da_str.split '--'
       target_das.each do |x|
         inds = x.split '='
-        unless inds.size == 4
+        unless inds.size == 1 || inds.size == 4
           raise IOError, 'domain architecture is ill formatted: ' + x
         end
+
         target_domain_name = inds[0]
-        ie_cutoff = Float(inds[1])
-        abs_len_cutoff = Integer(inds[2])
-        rel_len_cutoff = Float(inds[3])
+        ie_cutoff = inds.size == 4 ? Float(inds[1]) : IE_CUTOFF_FOR_DA_OVERVIEW
+        abs_len_cutoff = inds.size == 4 ? Integer(inds[2]) : 0
+        rel_len_cutoff = inds.size == 4 ? Float(inds[3]) : REL_LEN_CUTOFF_FOR_DA_OVERVIEW
         if target_domain_hash.has_key? target_domain_name
           target_domain_ary.push target_domain_hash[target_domain_name]
         else

diff --git a/forester/ruby/evoruby/lib/evo/tool/domains_to_forester.rb b/forester/ruby/evoruby/lib/evo/tool/domains_to_forester.rb
index 48459ae..a090d52 100644 (file)
--- a/forester/ruby/evoruby/lib/evo/tool/domains_to_forester.rb
+++ b/forester/ruby/evoruby/lib/evo/tool/domains_to_forester.rb
@@ -252,7 +252,7 @@ module Evoruby
 
       puts
       Util.print_message( PRG_NAME, "wrote: " + outfile )
-      Util.print_message( PRG_NAME, "next step in standard analysis pipeline: dsx.rb")
+      Util.print_message( PRG_NAME, "next step in standard analysis pipeline: dsx.rb or mdsx.rb")
       Util.print_message( PRG_NAME, 'OK' )
       puts
 
@@ -269,7 +269,7 @@ module Evoruby
       puts( "  options: -" + E_VALUE_THRESHOLD_OPTION  + "=<f>: E-value threshold, default is no threshold" )
       puts( "           -" + OVERWRITE_IF_SAME_FROM_TO_OPTION  + "    : overwrite domain with same start and end with domain with better E-value" )
       puts
-      puts( "  [next step in standard analysis pipeline: dsx.rb]")
+      puts( "  [next step in standard analysis pipeline: dsx.rb or mdsx.rb]")
       puts()
       puts( "Examples:" )
       puts

diff --git a/forester/ruby/evoruby/lib/evo/tool/multi_domain_seq_extractor.rb b/forester/ruby/evoruby/lib/evo/tool/multi_domain_seq_extractor.rb
index 506743a..b2f908d 100644 (file)
--- a/forester/ruby/evoruby/lib/evo/tool/multi_domain_seq_extractor.rb
+++ b/forester/ruby/evoruby/lib/evo/tool/multi_domain_seq_extractor.rb
@@ -13,7 +13,7 @@ module Evoruby
   class MultiDomainSeqExtractor
 
     PRG_NAME       = "mdsx"
-    PRG_VERSION    = "1.001"
+    PRG_VERSION    = "1.002"
     PRG_DESC       = "Extraction of multi domain sequences from hmmscan output"
     PRG_DATE       = "2017/03/08"
     WWW            = "https://sites.google.com/site/cmzmasek/home/software/forester"

diff --git a/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb b/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb
index 06c103e..5bc5bac 100644 (file)
--- a/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb
+++ b/forester/ruby/evoruby/lib/evo/tool/phylogenies_decorator.rb
@@ -29,11 +29,11 @@ module Evoruby
     #DECORATOR_OPTIONS_DOMAINS = '-r=1'
     DECORATOR_OPTIONS_DOMAINS = '-p -t'
     IDS_MAPFILE_SUFFIX        = '.nim'
-    DOMAINS_MAPFILE_SUFFIX    = '_hmmscan_10.dff'
+    DOMAINS_MAPFILE_SUFFIX    = '.dff'
     SLEEP_TIME                = 0.05
     REMOVE_NI                 = true
     IDS_ONLY                  = false #TODO this should be a command line option
-    FIXED_NIM_FILE            = 'all.nim' #TODO this should be a command line option
+    FIXED_NIM_FILE            = nil #'all.nim' #TODO this should be a command line option
     TMP_FILE_1                  = '___PD1___'
     TMP_FILE_2                  = '___PD2___'
     LOG_FILE                  = '00_phylogenies_decorator.log'
@@ -165,8 +165,8 @@ module Evoruby
             Util.fatal_error( PRG_NAME, 'could not get id from ' + phylogeny_file.to_s )
           end
           puts
-          Util.print_message( PRG_NAME, "id: " + phylogeny_id )
-          log << "id: " + phylogeny_id + NL
+          Util.print_message( PRG_NAME, "Id: " + phylogeny_id )
+          log << "Id: " + phylogeny_id + NL
 
           ids_mapfile_name = nil
           domains_mapfile_name = nil
@@ -177,28 +177,35 @@ module Evoruby
           else
             ids_mapfile_name = FIXED_NIM_FILE
           end
-          
+
+          Util.print_message( PRG_NAME, "Ids mapfile: " + ids_mapfile_name )
+          log << "Ids mapfile: " + ids_mapfile_name + NL
+
           unless IDS_ONLY
             domains_mapfile_name = get_file( files, phylogeny_id, DOMAINS_MAPFILE_SUFFIX )
             seqs_file_name = get_seq_file( files, phylogeny_id )
+            Util.print_message( PRG_NAME, "Domains file: " + domains_mapfile_name )
+            log << "Domains file: " + domains_mapfile_name + NL
+            Util.print_message( PRG_NAME, "Seq file: " + seqs_file_name )
+            log << "Seq file: " + seqs_file_name + NL
           end
 
           unless IDS_ONLY
             begin
               Util.check_file_for_readability( domains_mapfile_name )
-            rescue ArgumentError
+            rescue IOError
               Util.fatal_error( PRG_NAME, 'failed to read from [#{domains_mapfile_name}]: ' + $! )
             end
             begin
               Util.check_file_for_readability( seqs_file_name  )
-            rescue ArgumentError
+            rescue IOError
               Util.fatal_error( PRG_NAME, 'failed to read from [#{seqs_file_name }]: ' + $! )
             end
           end
 
           begin
             Util.check_file_for_readability( ids_mapfile_name )
-          rescue ArgumentError
+          rescue IOError
             Util.fatal_error( PRG_NAME, 'failed to read from [#{ids_mapfile_name}]: ' + $! )
           end
 
@@ -267,11 +274,7 @@ module Evoruby
     end
 
     def get_id( phylogeny_file_name )
-      if phylogeny_file_name =~ /^(.+?_.+?)_/
-        return $1
-      elsif phylogeny_file_name =~ /^(.+?)__/
-        return $1
-      elsif phylogeny_file_name =~ /^(.+?)_/
+      if phylogeny_file_name =~ /^(.+?)_/
         return $1
       end
       nil

diff --git a/forester/ruby/evoruby/lib/evo/tool/taxonomy_processor.rb b/forester/ruby/evoruby/lib/evo/tool/taxonomy_processor.rb
index 1d8a25b..b8f2cad 100644 (file)
--- a/forester/ruby/evoruby/lib/evo/tool/taxonomy_processor.rb
+++ b/forester/ruby/evoruby/lib/evo/tool/taxonomy_processor.rb
@@ -170,6 +170,8 @@ module Evoruby
       Util.print_message( PRG_NAME, "wrote: " + list_file )
       Util.print_message( PRG_NAME, "wrote: " + output )
       Util.print_message( PRG_NAME, "next steps in standard analysis pipeline: hmmscan followed by hsp.rb")
+      Util.print_message( PRG_NAME, "hmmscan example: hmmscan --max --domtblout P53_hmmscan_#{Constants::PFAM_V_FOR_EX}_10 -E 10 Pfam-A.hmm P53_ni.fasta")
+
       Util.print_message( PRG_NAME, "OK" )
     end
 
@@ -209,6 +211,7 @@ module Evoruby
       puts( "           -" + ANNOTATION_OPTION + "=<s>: to add an annotation to all entries" )
       puts()
       puts( "  [next steps in standard analysis pipeline: hmmscan followed by hsp.rb]")
+      puts( "  [hmmscan example: hmmscan --max --domtblout P53_hmmscan_#{Constants::PFAM_V_FOR_EX}_10 -E 10 Pfam-A.hmm P53_ni.fasta]")
       puts()
       puts( "Example:" )
       puts()