full_lengther_next 0.6.2 → 0.9.8

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 66126c7a055d70f0e4c09649c600d4f6079c8f94
+  data.tar.gz: 00013e537413b9f3e9500698108974707c683803
+SHA512:
+  metadata.gz: 779038539317419bc72a04805b251ef09987f50f5e66bcdf5ae230b2dee0d4baf832a5769d6b0112d0618c8f7fc3318dc9af66fa0896a33b1834d3434306bb79
+  data.tar.gz: 7d8f6769012d728b79f0065664a7b869e037cfb41521bfcc221646b78fc5833d7cc5797e00ee77c7f090115d054fb3f5b77dd750f23eac283f01338c9af4b1e2

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.2.2
+before_install: gem install bundler -v 1.12.5

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,49 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, ethnicity, age, religion, or nationality.
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery
+* Personal attacks
+* Trolling or insulting/derogatory comments
+* Public or private harassment
+* Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+* Other unethical or unprofessional conduct
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+By adopting this Code of Conduct, project maintainers commit themselves to
+fairly and consistently applying these principles to every aspect of managing
+this project. Project maintainers who do not follow or enforce the Code of
+Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting a project maintainer at seoanezonjic@hotmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. Maintainers are
+obligated to maintain confidentiality with regard to the reporter of an
+incident.
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.3.0, available at
+[http://contributor-covenant.org/version/1/3/0/][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/3/0/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in full_lengther_next.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 seoanezonjic
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/Rakefile

@@ -1,37 +1,6 @@
-require 'rubygems'
-gem 'hoe', '>= 2.1.0'
-require 'hoe'
-require 'fileutils'
-require './lib/full_lengther_next'
-
-Hoe.plugin :newgem
-# Hoe.plugin :website
-# Hoe.plugin :cucumberfeatures
-
-# Generate all the Rake tasks
-# Run 'rake -T' to see list of generated tasks (from gem root directory)
-$hoe = Hoe.spec 'full_lengther_next' do
-  self.developer 'Pedro Seoane & Noe Fernandez & Dario Guerrero ', 'seoanezonjic@hotmail.com & noeisneo@gmail.com & dariogf@gmail.com'
-  self.post_install_message = 'PostInstall.txt' # TODO remove if post-install message not required
-  self.rubyforge_name       = self.name # TODO this is default value
-  # self.extra_deps         = [['activesupport','>= 2.0.2']]
-  self.extra_deps         = []
-  # self.extra_deps << ['narray','>=0']
-  # self.extra_deps << ['gnuplot','>=0']
-  # self.extra_deps << ['term-ansicolor','>=1.0.5']
-  self.extra_deps << ['xml-simple','>=1.0.12']
-  self.extra_deps << ['scbi_blast','>=0.0.32']
-  self.extra_deps << ['scbi_mapreduce','>=0.0.29']
-  self.extra_deps << ['scbi_zcat']
-  self.extra_deps << ['bio-cd-hit-report', '>= 0.1.0  ']
-  self.extra_deps << ['bio', '>= 1.4.3']
-  self.extra_deps << ['scbi_plot','>=0.0.6']
-  
-end
-
-require 'newgem/tasks'
-Dir['tasks/**/*.rake'].each { |t| load t }
-
-# TODO - want other tests/tasks run by default? Add them to the list
-# remove_task :default
-# task :default => [:spec, :features]
+require "bundler/gem_tasks"
+#require "rspec/core/rake_task"
+
+#RSpec::Core::RakeTask.new(:spec)
+
+#task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "full_lengther_next"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/download_fln_dbs.rb

@@ -1,11 +1,7 @@
 #!/usr/bin/env ruby
  
-# 15-2-2011 Noe Fernandez-Pozo
-# Script to download Full-LengtherNext databases.
-# Once in UniProtKB/Swiss-Prot, a protein entry is removed from UniProtKB/TrEMBL.
-
 ROOT_PATH=File.dirname(__FILE__)
-$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next/classes/"))
+$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next"))
 
 require 'bio'
 require 'net/ftp'
@@ -28,7 +24,7 @@ def download_ncrna(formatted_db_path, no_download)
 		puts "Downloading ncRNA database"
 		open(ncrna_zip, 'wb') do |my_file|
 		 	my_file.print open('ftp://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/sequences/rnacentral_active.fasta.gz').read
-		 	#my_file.print open('http://www.ncrna.org/frnadb/files/ncrna.zip').read
+		 	####my_file.print open('http://www.ncrna.org/frnadb/files/ncrna.zip').read
 		end
 		puts "\nncRNA database downloaded"
 	end
@@ -381,7 +377,6 @@ download_ncrna(formatted_db_path, options[:no_download]) if !options[:no_ncrna]
 if !options[:no_download]
 	if !options[:no_uniprot]
 		conecta_uniprot(options[:uniprot_div], formatted_db_path) 
-		#system('gunzip '+formatted_db_path+'*.gz')
 	end
 end
 

data/bin/full_lengther_next

@@ -3,10 +3,53 @@
 # 12-2-2011 Noe Fernandez Pozo.
 # Full-LengtherNEXT predicts if your sequences are complete, showing you the nucleotide sequences and the translated protein
 ROOT_PATH=File.dirname(__FILE__)
-$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next/classes/"))
+$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next"))
 
 require 'optparse'
+require 'fileutils'
 require 'socket'
+require 'report_html'
+require 'scbi_fasta'
+
+###############################################################################################
+## METHODS
+###############################################################################################
+def read_fasta(input_fasta)
+	fasta = []
+	fasta_file = FastaQualFile.new(input_fasta,'').each do |name, seq, qual|
+		if seq.downcase.count('n') == seq.length
+			STDERR.puts "Sequence #{name} is full of Ns. Skipped"
+		else
+			fasta << [name, seq]
+		end
+	end
+	return fasta
+end
+
+def split_fasta(input_fasta, output_folder, n_files, chunk_size)
+	fasta = read_fasta(input_fasta)
+	n_seqs = fasta.length
+	fasta.sort!{|s1, s2| s1.last.length <=> s2.last.length }
+	file_names = []
+	files = []
+	n_files.times do |i| 
+		file_name = "ref#{i}.fasta"
+		file_names << file_name
+		(chunk_size -1 ).times do 
+			file_names << :data_void # This fills file_names with void elements to sync a file name for worker when it does the chunk size loop
+		end
+		files << File.open(File.join(output_folder, file_name), 'w') 
+	end
+	count = 0
+	while !fasta.empty?
+		files[count].puts '>' + fasta.shift.join("\n")
+		files[count].puts '>' + fasta.pop.join("\n") if !fasta.empty?
+		count += 1
+		count = 0 if count == n_files
+	end
+	files.map{|file| file.close }
+	return file_names, n_seqs
+end
 
 ###############################################################################################
 # PARSE OPTIONS
@@ -122,7 +165,7 @@ optparse = OptionParser.new do |opts|
 	options[:user_db] = nil
 	opts.on( '-u', '--user_db UserDB', 'User blast+ database' ) do |db|
 		options[:user_db] = db	
-		if !File.exists?(File.expand_path(options[:user_db])+'.psq')
+		if !File.exists?(File.expand_path(db+'.psq'))
 			puts "user database: #{options[:user_db]} was not found"
 			exit
 		end 	
@@ -158,6 +201,16 @@ optparse = OptionParser.new do |opts|
 		options[:hdd] = TRUE
 	end
 
+
+	options[:files2map] = []
+	opts.on('-M', '--files2map STRING', 'Fastq files to map against analysed transcriptome This must be a comma separated string with the full paths to the files' ) do |files2map|
+		options[:files2map] = files2map.split(';').map{|map_files| map_files.split(',')}
+	end
+
+	options[:remove_unmapped] = TRUE
+	opts.on('-R', '--remove_unmapped', 'When fastq files are provided, all sequences without at least a read pair are removed. When this option is enabled this filtering is disabled' ) do 
+		options[:remove_unmapped] = FALSE
+	end
 	
 	# Set a banner, displayed at the top of the help screen.
 	opts.banner = "\nUsage: full_lengther_next -f input.fasta -g [fungi|human|invertebrates|mammals|plants|rodents|vertebrates] [options]\n\n"
@@ -188,8 +241,14 @@ else
   FULL_LENGTHER_NEXT_INIT=File.join(ROOT_PATH,'init_env')
 end
 
-if !File.exists?('temp')
-	Dir.mkdir('temp')
+if ENV['FLN_TEMP']
+	options[:temp] = File.join(ENV['FLN_TEMP'], 'temp') 
+else
+	options[:temp] = File.join(Dir.pwd, 'temp') 
+end
+
+if !File.exists?(options[:temp])
+	Dir.mkdir(options[:temp])
 end
 
 if ENV['BLASTDB'] && File.exists?(ENV['BLASTDB'])
@@ -226,11 +285,28 @@ require 'scbi_mapreduce'
 require 'my_worker_manager_fln' #First server
 require 'reptrans'
 
+require 'go_methods'
+require "benchmark"
+
+#Benchmark.bm do |x|
+#	x.report('main'){
+options[:ref_files] = []
+if !options[:files2map].empty? # Mapping
+	#$VERBOSE = true
+	temp = File.join(options[:temp], 'map')
+	options[:temp_map_folder] = temp
+	FileUtils.mkdir(temp) if !Dir.exists?(temp)
+	map_workers = options[:workers]
+	map_workers = options[:workers].length if options[:workers].class == Array
+	options[:ref_files], options[:n_refs] = split_fasta(options[:fasta], temp, map_workers-1, options[:chunk_size])
+
+end
+
 $LOG = Logger.new(STDOUT)
 $LOG.datetime_format = "%Y-%m-%d %H:%M:%S"
 
 main_path = File.dirname(ROOT_PATH)
-custom_worker_file = File.join(main_path, 'lib','full_lengther_next','classes','my_worker.rb')
+custom_worker_file = File.join(main_path, 'lib','full_lengther_next','my_worker.rb')
 
 $LOG.info 'Starting server'
 	# initialize work manager (open files, etc)
@@ -243,11 +319,14 @@ $LOG.info 'Starting server'
 	# launch server
 	server.start_server
 $LOG.info 'Closing server'
+seqs_annotation_prot, seqs_some_coding,seqs_unknown = MyWorkerManagerFln.get_annotations()
+
 
 if !options[:reptrans].nil?
-	seqs_annotation_prot, seqs_some_coding ,seqs_unknown= MyWorkerManagerFln.get_annotations()
 	reptrans(seqs_annotation_prot, seqs_some_coding ,seqs_unknown, options)
 end
 puts "\nGracias por utilizar Full-LengtherNEXT"
 
 
+#} #Bench
+#end #Bench

data/bin/make_user_db.rb

@@ -4,7 +4,7 @@
 # Script to create your own Full-LengtherNext User database.
 
 ROOT_PATH=File.dirname(__FILE__)
-$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next/classes/"))
+$: << File.expand_path(File.join(ROOT_PATH, "../lib/full_lengther_next"))
 
 require 'cdhit'
 require 'handle_db'
@@ -48,7 +48,7 @@ optparse = OptionParser.new do |opts|
   opts.on( '-u', '--file String', 'Uniprot DBs to taxon search. Posible options: human, fungi, invertebrates, mammals, plants, rodents, vertebrates.') do |uniprot_div|
 		if !divs.include?(uniprot_div)
 			puts 'This uniprot division not exists:', uniprot_div
-			process.exit
+			Process.exit
 		end         
 		options[:uniprot_div] = uniprot_div
   end
@@ -58,6 +58,11 @@ optparse = OptionParser.new do |opts|
   		options[:taxon] = taxon
   end
 
+  options[:name] = nil
+  opts.on( '-n', '--name STRING', 'Database name in case the creation of a local DB') do |name|
+	options[:name] = name
+  end
+
   options[:local] = FALSE
   opts.on( '-l', '--local', 'Only parse downloaded files without download them again') do 
 		options[:local] = TRUE
@@ -95,7 +100,7 @@ if options[:user_fasta].nil?
 		puts 'Taxon or uniprot division was not specified'
 	  	Process.exit(-1)
 	end
-elsif !File.exists?(options[:user_fasta]) || options[:taxon].nil?
+elsif !File.exists?(options[:user_fasta]) && options[:taxon].nil?
 	puts 'User fasta file not exists or taxon was not specified'
 	Process.exit(-1)
 end
@@ -106,15 +111,18 @@ else # otherwise use ROOTPATH + DB
 	formatted_db_path = File.expand_path(File.join(ROOT_PATH, "blast_dbs"))
 end
 
+name_db = nil
 if !options[:local]
 	user_db_folder = File.join(formatted_db_path, options[:taxon])
+	name_db = options[:taxon]
 else
-	user_db_folder = File.join(Dir.pwd, options[:taxon])
+	user_db_folder = File.join(Dir.pwd, options[:name])
+	name_db = options[:name]
 end
 
 user_db_folder.gsub!(' ', '_')
 Dir.mkdir(user_db_folder) if !File.exists?(user_db_folder)
-output_file_path = File.join(user_db_folder, options[:taxon]+".fasta")
+output_file_path = File.join(user_db_folder, name_db)
 output_file_path.gsub!(' ', '_')
 
 seqs = ''

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/full_lengther_next.gemspec

@@ -0,0 +1,42 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'full_lengther_next/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "full_lengther_next"
+  spec.version       = FullLengtherNext::VERSION
+  spec.authors       = ['Pedro Seoane', 'Noe Fernandez', 'Dario Guerrero']
+  spec.email         = ['seoanezonjic@hotmail.com', 'noeisneo@gmail.com', 'dariogf@gmail.com']
+
+  spec.summary       = %q{Tool to annotate transcriptomes and it is able to stablish the integrity of each transcript. Also, FLN can detect novel genes on a target organism. }
+  spec.description   = %q{FULL-LENGTHERNEXT is a tool adapted to NGS technologies, able to work in parallel and in a distributed way to minimise computing time. It is able to classify unigenes to full-length, 5’-end, 3’-end and internal, suggesting which unknown genes are coding or not. It will be also shown that FULL-LENGTHERNEXT fixes frame shifts, one of the main mistake found in wrong entries of full-length sequences databases, and it is a fast tool to compare different transcriptome assemblies.}
+  spec.homepage      = "https://github.com/seoanezonjic"
+  spec.license       = "MIT"
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  # if spec.respond_to?(:metadata)
+  #   spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
+  # else
+  #   raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
+  # end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "bin"
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+  
+  spec.add_runtime_dependency 'xml-simple'
+  spec.add_runtime_dependency 'scbi_fasta'
+  spec.add_runtime_dependency 'scbi_blast'
+  spec.add_runtime_dependency 'scbi_mapreduce'
+  spec.add_runtime_dependency 'scbi_zcat'
+  spec.add_runtime_dependency 'bio-cd-hit-report'
+  spec.add_runtime_dependency 'report_html'
+
+
+  spec.add_development_dependency "bundler", "~> 1.12"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end