semin-ulla 0.9.8 → 0.9.9

data/History.txt

@@ -1,3 +1,8 @@
+== 0.9.9 09/08/2009
+
+* Changed default value for --classdef option from 'classdef.dat' to nil
+  When no definition file provided, --cys (-y) 2 and --nosmooth options are applied automatically
+
 == 0.9.8 21/07/2009
 
 * Fixed a bug in generating amino acids symbols when --cys 2 is set

data/README.rdoc

@@ -46,7 +46,8 @@ It's pretty much the same as Kenji's subst (http://www-cryst.bioc.cam.ac.uk/~ken
 == Options
     --tem-file (-f) FILE: a tem file
     --tem-list (-l) FILE: a list for tem files
-    --classdef (-c) FILE: a file for the defintion of environments (default: 'classdef.dat')
+    --classdef (-c) FILE: a file for the defintion of environmental class
+                          if no definition file provided, --cys (-y) 2 and --nosmooth options automatcially applied
     --outfile (-o) FILE: output filename (default 'allmat.dat')
     --weight (-w) INTEGER: clustering level (PID) for the BLOSUM-like weighting (default: 60)
     --noweight: calculate substitution counts with no weights
@@ -144,27 +145,27 @@ It's pretty much the same as Kenji's subst (http://www-cryst.bioc.cam.ac.uk/~ken
         sample2.tem
         ...
 
-4. To produce substitution count matrices, type
+4. To produce substitution count matrices,
 
         ~user $ ulla -l TEMLIST --output 0 -o substcount.mat
 
-5. To produce substitution probability matrices, type
+5. To produce substitution probability matrices,
 
         ~user $ ulla -l TEMLIST --output 1 -o substprob.mat
 
-6. To produce log odds ratio matrices, type
+6. To produce log odds ratio matrices,
 
         ~user $ ulla -l TEMLIST --output 2 -o substlogo.mat
 
-7. To produce substitution probability matrices only from the sequence pairs within a certain PID range, type (if you don't provide any name for output, 'allmat.dat' will be used.)
+7. To produce substitution probability matrices from the sequence pairs within a certain PID range (if you don't provide any name for output, 'allmat.dat' will be used.),
 
         ~user $ ulla -l TEMLIST --pidmin 60 --pidmax 80 --output 1
 
-8. To change the clustering level (default 60) to PID 80, type
+8. To change the clustering level (default 60) to PID 80,
 
         ~user $ ulla -l TEMLIST --weight 80 --output 1
 
-9. In case positions are masked with the character 'X' in any environmental features, all mutations from/to the position will be excluded from the calculation of substitution counts.
+9. In case positions are masked with the character 'X' in any environmental features, all mutations from/to the position will be excluded from substitution counts.
 
 10. Then, it will produce a file containing all the matrices, which will look like the one below. For more details, please check this notes (http://www-cryst.bioc.cam.ac.uk/~kenji/subst/NOTES).
 
@@ -235,8 +236,6 @@ It's pretty much the same as Kenji's subst (http://www-cryst.bioc.cam.ac.uk/~ken
 
     http://www-cryst.bioc.cam.ac.uk/~semin/images/myheatmaps.gif
 
-== TODO
-
 == Repository
 
 You can download a pre-built RubyGems package from
@@ -247,6 +246,9 @@ or, You can fetch the source from
 
 * github: http://github.com/semin/ulla/tree/master
 
+== Reference
+
+* {Lee S., Blundell T.L. (2009) Ulla: a program for calculating environment-specific amino acid substitution tables. Bioinformatics. 25(15):1976-1977; doi:10.1093/bioinformatics/btp300}[http://bioinformatics.oxfordjournals.org/cgi/content/full/25/15/1976]
 
 == Contact
 

data/lib/ulla/cli.rb

@@ -23,8 +23,8 @@ module Ulla
       # :call-seq:
       #   Ulla::CLI::print_usage
       #
-      def print_usage
-        puts <<-USAGE
+      def print_usage(verbose=false)
+        usage = <<-USAGE
 ulla: a program to calculate environment-specific amino acid substitution tables.
 
 Usage:
@@ -32,10 +32,14 @@ Usage:
         or
     ulla [ options ] -f TEM-file -c CLASSDEF-file
 
+        USAGE
+
+        options = <<-OPTIONS
 Options:
     --tem-file (-f) FILE: a tem file
     --tem-list (-l) FILE: a list for tem files
-    --classdef (-c) FILE: a file for the defintion of environments (default: 'classdef.dat')
+    --classdef (-c) FILE: a file for the defintion of environmental class
+                          if no definition file provided, --cys (-y) 2 and --nosmooth options automatcially applied
     --outfile (-o) FILE: output filename (default 'allmat.dat')
     --weight (-w) INTEGER: clustering level (PID) for the BLOSUM-like weighting (default: 60)
     --noweight: calculate substitution counts with no weights
@@ -83,7 +87,9 @@ Options:
     --version: print version
     --help (-h): show help
 
-        USAGE
+        OPTIONS
+
+        puts (verbose ? usage + options : usage)
       end
 
       # Calculate PID between two sequences
@@ -157,7 +163,7 @@ Options:
         $tem_file       = nil
         $environment    = 0
         $col_size       = nil
-        $classdef       = 'classdef.dat'
+        $classdef       = nil
         $outfile        = 'allmat.dat'
         $outfh          = nil # file hanfle for outfile
         $output         = 2 # default: log odds matrix
@@ -247,7 +253,7 @@ Options:
           opts.each do |opt, arg|
             case opt
             when '--help'
-              print_usage
+              print_usage(true)
               exit 0
             when '--tem-list'
               $tem_list     = arg
@@ -382,9 +388,15 @@ Options:
         # Reading Environment Class Definition File
         #
 
-        # if --cys option 2, then we don't care about 'J' (for both Cystine and Cystine)
+        # if no class definition provided, set --cys (-y) option 2 and --nosmooth option true
+        if $classdef.nil?
+          $cys      = 2
+          $nosmooth = true
+        end
+
+        # if --cys option 2, we don't care about 'J' (for both Cystine and Cystine)
         if $cys == 2
-          $amino_acids = 'ACDEFGHIKLMNPQRSTVWY'.delete('J').split('')
+          $amino_acids.delete('J')
         end
 
         # create an EnvironmentFeatureArray object for storing all environment
@@ -404,33 +416,35 @@ Options:
 
         # read environment class definiton file and store them into
         # the hash prepared above
-        env_index = 1
+        if !!$classdef
+          env_index = 1
 
-        IO.foreach($classdef) do |line|
-          line.chomp!
-          if line.start_with?('#') || line.blank?
-            next
-          elsif (env_ftr = line.split(/;/)).length == 5
-            $logger.info "An environment feature, #{line} detected."
-            if env_ftr[-1] == 'T'
-              # skip silenced environment feature
-              $logger.warn "The environment feature, #{line} silent."
+          IO.foreach($classdef) do |line|
+            line.chomp!
+            if line.start_with?('#') || line.blank?
               next
+            elsif (env_ftr = line.split(/;/)).length == 5
+              $logger.info "An environment feature, #{line} detected."
+              if env_ftr[-1] == 'T'
+                # skip silenced environment feature
+                $logger.warn "The environment feature, #{line} silent."
+                next
+              end
+              if env_ftr[-2] == 'T'
+                $cst_features << env_index
+                $logger.warn "The environment feature, #{line} constrained."
+              end
+              $env_features << EnvironmentFeature.new(env_ftr[0],
+                                                      env_ftr[1].split(''),
+                                                      env_ftr[2].split(''),
+                                                      env_ftr[3],
+                                                      env_ftr[4])
+              env_index += 1
+            else
+              $logger.error "\"#{line}\" doesn't seem to be a proper format for " +
+                            "an environment class definition."
+              exit 1
             end
-            if env_ftr[-2] == 'T'
-              $cst_features << env_index
-              $logger.warn "The environment feature, #{line} constrained."
-            end
-            $env_features << EnvironmentFeature.new(env_ftr[0],
-                                                    env_ftr[1].split(''),
-                                                    env_ftr[2].split(''),
-                                                    env_ftr[3],
-                                                    env_ftr[4])
-            env_index += 1
-          else
-            $logger.error "\"#{line}\" doesn't seem to be a proper format for " +
-                          "an environment class definition."
-            exit 1
           end
         end
 
@@ -447,7 +461,7 @@ Options:
         # every environment class into the hash prepared above with the label
         # as a key
         $env_features.label_combinations.each_with_index do |ef1, i|
-          key1 = ef1.flatten.join
+          key1 = ef1.respond_to?(:flatten) ? ef1.flatten.join : ef1
           $ext_amino_acids << key1
 
           if $environment == 0

data/lib/ulla.rb

@@ -2,5 +2,5 @@ $:.unshift(File.dirname(__FILE__)) unless
   $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
 
 module Ulla
-  VERSION = '0.9.8'
+  VERSION = '0.9.9'
 end

data/ulla.gemspec

@@ -2,11 +2,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{ulla}
-  s.version = "0.9.8"
+  s.version = "0.9.9"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Semin Lee"]
-  s.date = %q{2009-07-21}
+  s.date = %q{2009-08-09}
   s.default_executable = %q{ulla}
   s.description = %q{'ulla' is a program for calculating environment-specific substitution tables from user providing environmental class definitions and sequence alignments with the annotations of the environment classes.}
   s.email = ["seminlee@gmail.com"]
@@ -18,7 +18,7 @@ Gem::Specification.new do |s|
   s.rdoc_options = ["--main", "README.rdoc"]
   s.require_paths = ["lib"]
   s.rubyforge_project = %q{ulla}
-  s.rubygems_version = %q{1.3.4}
+  s.rubygems_version = %q{1.3.5}
   s.summary = %q{'ulla' is a program for calculating environment-specific substitution tables from user providing environmental class definitions and sequence alignments with the annotations of the environment classes.}
   s.test_files = ["test/test_math_extensions.rb", "test/test_narray_extensions.rb", "test/test_nmatrix_extensions.rb", "test/test_string_extensions.rb", "test/ulla/test_cli.rb", "test/ulla/test_environment_class_hash.rb", "test/ulla/test_environment_feature.rb", "test/test_helper.rb", "test/test_ulla.rb"]
 
@@ -31,19 +31,19 @@ Gem::Specification.new do |s|
       s.add_runtime_dependency(%q<bio>, [">= 1.2.1"])
       s.add_runtime_dependency(%q<facets>, [">= 2.4.5"])
       s.add_runtime_dependency(%q<rmagick>, [">= 2.9.1"])
-      s.add_development_dependency(%q<hoe>, [">= 2.3.2"])
+      s.add_development_dependency(%q<hoe>, [">= 2.3.3"])
     else
       s.add_dependency(%q<narray>, [">= 0.5.9.5"])
       s.add_dependency(%q<bio>, [">= 1.2.1"])
       s.add_dependency(%q<facets>, [">= 2.4.5"])
       s.add_dependency(%q<rmagick>, [">= 2.9.1"])
-      s.add_dependency(%q<hoe>, [">= 2.3.2"])
+      s.add_dependency(%q<hoe>, [">= 2.3.3"])
     end
   else
     s.add_dependency(%q<narray>, [">= 0.5.9.5"])
     s.add_dependency(%q<bio>, [">= 1.2.1"])
     s.add_dependency(%q<facets>, [">= 2.4.5"])
     s.add_dependency(%q<rmagick>, [">= 2.9.1"])
-    s.add_dependency(%q<hoe>, [">= 2.3.2"])
+    s.add_dependency(%q<hoe>, [">= 2.3.3"])
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: semin-ulla
 version: !ruby/object:Gem::Version 
-  version: 0.9.8
+  version: 0.9.9
 platform: ruby
 authors: 
 - Semin Lee
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-07-21 00:00:00 -07:00
+date: 2009-08-09 00:00:00 -07:00
 default_executable: ulla
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -60,7 +60,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 2.3.2
+        version: 2.3.3
     version: 
 description: "'ulla' is a program for calculating environment-specific substitution tables from user providing environmental class definitions and sequence alignments with the annotations of the environment classes."
 email: 
@@ -115,6 +115,7 @@ files:
 - website/template.html.erb
 has_rdoc: false
 homepage: http://www-cryst.bioc.cam.ac.uk/ulla
+licenses: 
 post_install_message: PostInstall.txt
 rdoc_options: 
 - --main
@@ -136,7 +137,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: ulla
-rubygems_version: 1.2.0
+rubygems_version: 1.3.5
 signing_key: 
 specification_version: 3
 summary: "'ulla' is a program for calculating environment-specific substitution tables from user providing environmental class definitions and sequence alignments with the annotations of the environment classes."