DomFun 0.1.0

data/lib/DomFun.rb

@@ -0,0 +1,6 @@
+require "DomFun/version"
+
+module DomFun
+  class Error < StandardError; end
+  # Your code goes here...
+end

data/lib/DomFun/generalMethods.rb

@@ -0,0 +1,105 @@
+def load_proteins_file(file, annotation_types)
+	protein_annotations = {}
+	proteins_without_annotations = []
+	annotation_types.each do |type| # initialize annotation hashes
+		protein_annotations[type] = {}
+	end
+	counter = 0
+	File.open(file).each do |line|
+		line.chomp!
+		if counter == 0
+			counter += 1
+			next
+		end
+		line.gsub!(' ', '')
+		fields = line.split("\t", 4)
+		protID = fields.shift
+		annotation_types.each_with_index do |type, i|
+			annotations = fields[i].split(/[;,]/)
+			if !annotations.empty?
+				if type.include?('go')
+					go_annotations = []
+					annotations.each do |go_term|
+						go_name, go_id = go_term.split('GO:')
+						go_annotations << "GO:".concat(go_id.tr(']', '')) unless go_id.nil?	
+					end
+					protein_annotations[type][protID] = go_annotations
+				else
+					protein_annotations[type][protID] = annotations
+				end
+			end
+			if fields.count("") == 3
+				proteins_without_annotations << protID
+			end
+		end
+		counter += 1
+	end
+	return protein_annotations, counter, proteins_without_annotations.uniq
+end
+
+def load_cath_data(file, category, meth='protACC')
+	cath_data = {}
+	protein2gene = {}
+	gene2proteins = {}
+	csv_file = CSV.read(file, { :col_sep => "\t" })
+	csv_file.delete_at(0)
+	csv_file.each do |protein_domains_data|
+		next if protein_domains_data.empty?
+		protein_id = protein_domains_data[0]
+		if meth == 'protACC'
+			field = 3
+		elsif meth == 'geneID'
+			field = 4
+		end
+		gene_name = protein_domains_data[field]
+		next if gene_name.include?('fusion')
+		gene_name = gene_name.gsub(' ', '_') if gene_name.include?(' ')
+		superfamilyID = protein_domains_data[5]
+		funfamID = protein_domains_data[6]
+		term2save = nil
+		if category == 'superfamilyID'
+			term2save = superfamilyID
+		elsif category == 'funfamID'
+			term2save = funfamID
+		end
+		add_term2dictionary(cath_data, protein_id, term2save)
+		protein2gene[protein_id] = gene_name if gene_name != 'NULL'
+		query = gene2proteins[gene_name]
+	    if query.nil?
+	      	gene2proteins[gene_name] = [protein_id] if protein_id != 'NULL'
+	    else
+	      query << protein_id if protein_id != 'NULL'
+		end
+	end
+	cath_proteins_number = cath_data.keys.length
+	return cath_data, protein2gene, gene2proteins, cath_proteins_number
+end
+
+def add_term2dictionary(dict, key, term)
+	query = dict[key]
+	if query.nil?
+        	dict[key] = [term]
+	else
+		query << term
+	end
+end
+
+def load_cafa_data(cafa_file)
+	cafa_data = {}
+	File.open(cafa_file).each do |line|
+		line.chomp!
+		next if line.include?('GO_Ont')
+		cafa_info = line.split("\t")
+		next unless cafa_info[1] == 'MF'
+		go_term = cafa_info[4]
+		gene_name = cafa_info[6]
+		next if gene_name == 'NA'
+		query = cafa_data[gene_name]
+		if query.nil?
+			cafa_data[gene_name] = [go_term]
+		else
+			query << go_term
+		end
+	end
+	return cafa_data
+end

data/lib/DomFun/version.rb

@@ -0,0 +1,3 @@
+module DomFun
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,128 @@
+--- !ruby/object:Gem::Specification
+name: DomFun
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elena Rojano, Pedro Seoane
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2019-11-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: NetAnalyzer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.5
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.1.5
+description: From associations calculated between protein domains and functional systems
+  (FunSys), DomFun can predict the functions of proteins looking up domains and the
+  FunSys that have been associated with. The system is validated using data from CAFA.
+email:
+- elenarojano@uma.es, seoanezonjic@hotmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- DomFun.gemspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/add_protein_functional_families.rb
+- bin/console
+- bin/domains_to_function_predictor.rb
+- bin/generate_CAFA2_dataset.rb
+- bin/generate_CAFA2_tripartite_network.rb
+- bin/generate_cafa_control.rb
+- bin/get_kegg_pathways.R
+- bin/lines.R
+- bin/merge_pairs.rb
+- bin/normalize_combined_scores.rb
+- bin/prepare_cafa_network.rb
+- bin/setup
+- bin/standardize_scores.R
+- bin/translate_kegg_genes2pathways.rb
+- bin/validate_ProtFunSys_predictions.rb
+- lib/DomFun.rb
+- lib/DomFun/generalMethods.rb
+- lib/DomFun/version.rb
+homepage: https://github.com/ElenaRojano/DomFun
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.14
+signing_key: 
+specification_version: 4
+summary: Tool to predict protein functions based on domains-FunSys associations.
+test_files: []