bio-grid 0.2.5 → 0.2.6

data/Gemfile

@@ -2,7 +2,7 @@ source "http://rubygems.org"
 # Add dependencies required to use your gem here.
 # Example:
 #   gem "activesupport", ">= 2.3.5"
-
+gem "uuid"
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
 group :development do
@@ -10,4 +10,5 @@ group :development do
   gem "rdoc", "~> 3.12"
   gem "bundler", "> 1.0.0"
   gem "jeweler", "~> 1.8.4"
+	gem "uuid"
 end

data/Gemfile.lock

@@ -9,6 +9,8 @@ GEM
       rake
       rdoc
     json (1.7.5)
+    macaddr (1.6.1)
+      systemu (~> 2.5.0)
     rake (0.9.2.2)
     rdoc (3.12)
       json (~> 1.4)
@@ -20,6 +22,9 @@ GEM
     rspec-expectations (2.8.0)
       diff-lcs (~> 1.1.2)
     rspec-mocks (2.8.0)
+    systemu (2.5.2)
+    uuid (2.3.5)
+      macaddr (~> 1.0)
 
 PLATFORMS
   ruby
@@ -29,3 +34,4 @@ DEPENDENCIES
   jeweler (~> 1.8.4)
   rdoc (~> 3.12)
   rspec (~> 2.8.0)
+  uuid

data/README.md

@@ -82,12 +82,13 @@ For a complete list of current BioGrid parameters, type "bio-grid -h":
     -s, --split-number NUMBER        Number of input files (or group of files) to use per job. If all the files in a location need to be used for a single job, just specify 'all'
     -p, --processes PROCESSES        Number of processes per job
     -c, --command-line COMMANDLINE   Command line to be executed
-    -o, --output OUTPUT              Output folder
+    -o, --output OUTPUT              Output folder. Needs a <output> placeholder in the command line
     -r, --copy-to LOCATION           Copy the output once a job is terminated
     -e, --erease-output              Delete job output data when completed (useful to delete output temporary files on a computing node)
+    -a, --params PARAM1,PARAM2...    List of parameters to use for testing. Needs a <param> placeholder in the command line
     -d, --dry                        Dry run. Just write the job scripts without sending them in queue (for debugging or testing)
     -t, --test                       Start the mapping only with the first group of reads (e.g. for testing parameters)
-    -i, --input INPUT1,INPUT2...     Location where to find input files (accepts wildcards). You can specify more than one input location, just provide a comma separated list
+    -i, --input INPUT1,INPUT2...     Location where to find input files (accepts wildcards). Needs <input(1,2,3...> placeholder(s) in the command line
         --sep SEPARATOR              Input file separator [Default: , ]
         --keep-scripts               Keep all the running scripts created for all the jobs
     -h, --help                       Display this screen
@@ -99,7 +100,7 @@ Advanced stuff
 Ok let's unleash the potential of BioGrid.
 By putting together an automatic system to generate and submit jobs on a queue systems and a command line template approach, we can do some interesting things.
 
-Parameters sampling and testing
+Numerical parameters sampling and testing
 -------------------------------
 
 The tipical scenario is when I have to run a tool on a new dataset and I would like to test different parameters to asses which are the better ones for my analysis.
@@ -119,7 +120,18 @@ So in this case, the ```-L``` parameter will take 6 different values: 22, 24, 26
 
 Last but not least, the ```-t``` option is essential so that only a single job per input file (or group of files) will be executed. Sampling parameters values is a typical combinatorial approach and this option avoids generating hundreds of different jobs only to sample a parameter. Coming back to the initial example, if I have 60 pairs of FastQ files, without the ```-t``` option, the job number will be 60x6 = 360, which is just crazy when you only want to test different parameter values. 
 
-So far, BioGrid does not support sampling more than one parameter at the same time.
+Others parameters sampling
+--------------------------
+
+If you want to sample non-numerical parameters, with BioGrid it is possible to use the ```--params``` option. So for instance, if I want to run Bowtie on my dataset to assess the results differences using the ```--sensitive```, ```--very-sensitive``` and ```--fast``` options, I can do it easely in this way:
+
+```shell
+bio-grid -i "/data/Project_X/Sample_Y/*_R1_*.fastq.gz","/data/Project_X/Sample_Y/*_R2_*.fastq.gz" -n bowtie_mapping -c "/software/bowtie2 -x /genomes/genome_index -p 8 <param> -1 <input1> -2 <input2> > <output>.sam" -o /data/Project_X/Sample_Y_mapping -s 1 -p 8 -r /results/Sample_Y_mapping -e --param "--sensitive","--very-sensitive","--fast" -t
+```
+
+In this case, the key points are the ```<param>``` placeholder in the command line and the corresponding ```--params``` options in BioGrid, which specify a list of parameters to be used to generate and run different jobs, each one with a different parameter in the list. Again, even in this case, it is recommended to do parameters testing using the ```-t``` option, which only runs a single job and not the full job array.
+
+So far, BioGrid does not support, for each run, sampling more than one parameter at the same time.
 
 Contributing to bioruby-grid
 ============================

data/VERSION

@@ -1 +1 @@
-0.2.5
+0.2.6

data/bin/bio-grid

@@ -26,7 +26,7 @@ optparse = OptionParser.new do |opts|
 		options[:cmd] = cmd
 	end
 
-	opts.on("-o","--output OUTPUT","Output folder") do |out|
+	opts.on("-o","--output OUTPUT","Output folder. Needs a <output> placeholder in the command line") do |out|
 		options[:output] = out
 	end
 
@@ -38,13 +38,17 @@ optparse = OptionParser.new do |opts|
 		options[:clean] = true
 	end
 
+	opts.on("-a","--params PARAM1,PARAM2...",Array,"List of parameters to use for testing. Needs a <param> placeholder in the command line") do |params|
+		options[:params] = params
+	end
+
 	opts.on("-d","--dry","Dry run. Just write the job scripts without sending them in queue (for debugging or testing)") {options[:dry] = true}
 
 	opts.on("-t","--test","Start the mapping only with the first group of reads (e.g. for testing parameters)") do |test|
 		options[:test] = true
 	end
 
-	opts.on("-i","--input INPUT1,INPUT2...",Array,"Location where to find input files (accepts wildcards). You can specify more than one input location, just provide a comma separated list") do |input|
+	opts.on("-i","--input INPUT1,INPUT2...",Array,"Location where to find input files (accepts wildcards). Needs <input(1,2,3...> placeholder(s) in the command line") do |input|
 		options[:input] = input
 	end
 

data/bio-grid.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "bio-grid"
-  s.version = "0.2.5"
+  s.version = "0.2.6"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Francesco Strozzi"]
@@ -44,21 +44,27 @@ Gem::Specification.new do |s|
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<uuid>, [">= 0"])
       s.add_development_dependency(%q<rspec>, ["~> 2.8.0"])
       s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
       s.add_development_dependency(%q<bundler>, ["> 1.0.0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.8.4"])
+      s.add_development_dependency(%q<uuid>, [">= 0"])
     else
+      s.add_dependency(%q<uuid>, [">= 0"])
       s.add_dependency(%q<rspec>, ["~> 2.8.0"])
       s.add_dependency(%q<rdoc>, ["~> 3.12"])
       s.add_dependency(%q<bundler>, ["> 1.0.0"])
       s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
+      s.add_dependency(%q<uuid>, [">= 0"])
     end
   else
+    s.add_dependency(%q<uuid>, [">= 0"])
     s.add_dependency(%q<rspec>, ["~> 2.8.0"])
     s.add_dependency(%q<rdoc>, ["~> 3.12"])
     s.add_dependency(%q<bundler>, ["> 1.0.0"])
     s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
+    s.add_dependency(%q<uuid>, [">= 0"])
   end
 end
 

data/lib/bio/grid.rb

@@ -20,7 +20,14 @@ module Bio
 					range.each do |value|
 						cmd_line = options[:cmd].gsub(/<(\d+),(\d+)(,\d+)*>/,value.to_s)
 						job = Bio::Grid::Job.new(options) # inherit global options
-						job.options[:parameter_value] = "-param-#{value}"
+						job.options[:parameter_value] = "-param:#{value}"
+						job.execute(cmd_line,inputs,input1,groups,index)
+					end
+				elsif options[:params]
+					options[:params].each do |p|
+						cmd_line = options[:cmd].gsub(/<param>|<parameter>/,p)
+						job = Bio::Grid::Job.new(options)
+						job.options[:parameter_value] = "-param:#{p}"
 						job.execute(cmd_line,inputs,input1,groups,index)
 					end
 				else

data/lib/bio/grid/job.rb

@@ -2,14 +2,16 @@ module Bio
 	class Grid
 		class Job
 			
-			attr_accessor :options, :instructions, :job_output, :runner
+			attr_accessor :options, :instructions, :job_output, :runner, :uuid
 			def initialize(options)
 				@options = options
-				self.instructions = ""
+				self.instructions = []
+				self.uuid = UUID.new.generate.split("-").first
 			end
 
 			def	set_output_dir
-				self.instructions << ("mkdir -p #{self.options[:output]}\n")
+				output_dir = (self.options[:output_folder]) ? "mkdir -p #{self.job_output}\ncd #{self.job_output}\n" : "mkdir -p #{self.options[:output]}\n"
+				self.instructions.insert(1,output_dir)
 			end
 
 			def set_commandline(cmd_line,inputs,input1,groups,index)	
@@ -20,13 +22,13 @@ module Bio
 				job_output = ""
 				if commandline =~/<output>\.(\S+)/
 					extension = $1
-					job_output = self.options[:output]+"/#{Time.now.to_i}"+self.options[:name]+"_output_%03d" % (index+1).to_s + "#{self.options[:parameter_value]}"
+					job_output = self.options[:output]+"/#{self.uuid}_"+self.options[:name]+"_output_%03d" % (index+1).to_s + "#{self.options[:parameter_value]}"
 					commandline.gsub!(/<output>/,job_output)	
 					job_output << ".#{extension}"
 				else
 					self.options[:output_folder] = true
-					commandline.gsub!(/<output>/,self.options[:output]+"/#{Time.now.to_i}_"+self.options[:name])
-					job_output = self.options[:output]+"/#{Time.now.to_i}_"+self.options[:name]
+					job_output = self.options[:output]+"/#{self.uuid}_"+self.options[:name]
+					commandline.gsub!(/<output>/,job_output)
 				end
 				self.instructions << commandline+"\n"
 				self.job_output = job_output
@@ -48,7 +50,7 @@ module Bio
 			def write_runner(filename)
 				self.runner = filename
 				out = File.open(Dir.pwd+"/"+filename,"w")
-				out.write(self.instructions+"\n")
+				out.write(self.instructions.join+"\n")
 				out.close
 			end
 
@@ -63,8 +65,8 @@ module Bio
 
 			def	execute(command_line,inputs,input1,groups,index)
 				self.set_scheduler_options(:pbs) # set script specific options for the scheduling system
-				self.set_output_dir
         self.set_commandline(command_line,inputs,input1,groups,index)
+				self.set_output_dir
         self.append_options
         job_filename = (self.options[:keep]) ? "job_#{index+1}#{self.options[:parameter_value]}.sh" : "job.sh"
         self.run(job_filename)

data/lib/bioruby-grid.rb

@@ -1,2 +1,3 @@
+require 'uuid'
 require 'bio/grid'
 require 'bio/grid/job'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bio-grid
 version: !ruby/object:Gem::Version
-  version: 0.2.5
+  version: 0.2.6
   prerelease: 
 platform: ruby
 authors:
@@ -11,6 +11,22 @@ bindir: bin
 cert_chain: []
 date: 2012-09-24 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: uuid
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -75,6 +91,22 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: 1.8.4
+- !ruby/object:Gem::Dependency
+  name: uuid
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A BioGem to submit jobs on a queue system
 email: francesco.strozzi@gmail.com
 executables:
@@ -114,7 +146,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 2636116439556584152
+      hash: -4333638046284412790
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: