most_frequent_seq 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 75fa8faad532a7542135ec0564a69d8d9a8d78001b2bb82dd365f9d020e8b54f
+  data.tar.gz: a2867365be614d19bba1227fd74b737a61c571cdd708369230f95f9f5860373c
+SHA512:
+  metadata.gz: 9787d33933b14263996017f39be246e4fec356688b5d31fe509f784a2772000fbe3690840e16e2e7477531a4a11b01e5b746eb5985d9c55d0fdbbba1c1ebee08
+  data.tar.gz: fbc1963bcffb51c1694efad0d71713b49251b6e5f74d6062b98dad6b4c0818c989367ab298afb7f48dff4e11349b185038e0364368b40b0e17590d531143346b

data/lib/most_frequent_seq.rb

@@ -0,0 +1,110 @@
+#  SEQUENCE FREQUENCY ANALYSIS - DNA most_frequent_seq - Consensus Reference Builder
+
+##############################################################
+# MIT License
+
+# Copyright (c) [2020] [ZACHARY L. DWIGHT]
+
+# 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.
+##############################################################
+#
+#
+# Use for creating consensus or reference sequence from array of seqs
+
+#EXAMPLE
+#require 'most_frequent_seq'
+#seqs = ['tgactgactgatcgatcgatcgnaaa','tgactgactgatcgatcgatcgaagg','tgactgactgatcgatcgatcgaggg','tgactggctgatcgatcgatcgaccc','tgactg-ctgatcgctcgatcgaccg','agactgactgancgctcgatcgccct']
+#puts CONSENSUS::Sequences.calcConsensus(seqs)
+# >> TGACTGACTGATCGATCGATCGACCG
+
+
+module CONSENSUS
+class Sequences
+	def self.calcConsensus(seqs)
+		seql = seqs[0].length - 1
+		seqr = ""
+
+		#loop through each base index
+		for i in 0..seql
+
+			#establish array for counting bases at i position
+			bases = [0,0,0,0,0,0,0] # A,G,C,T,N,-,U
+			
+			#for each seq, count the type of base at each index
+			seqs.each { |n| 
+				n = n.upcase
+				if(n[i]=='A')
+					bases[0] = bases[0]+1
+				end
+				if(n[i]=='G')
+					bases[1] = bases[1]+1
+				end
+				if(n[i]=='C')
+					bases[2] = bases[2]+1
+				end
+				if(n[i]=='T')
+					bases[3] = bases[3]+1
+				end
+				if(n[i]=='N')
+					bases[4] = bases[4]+1
+				end
+				if(n[i]=='-')
+					bases[5] = bases[5]+1
+				end
+				if(n[i]=='U')
+					bases[6] = bases[6]+1
+				end
+				
+				}
+			
+			#find the max frequency , most frequent base at this index
+			cb = bases.each_with_index.max[1]
+
+			#convert back to string
+			if(cb==0)
+				base = 'A'
+			end
+			if(cb==1)
+				base = 'G'
+			end
+			if(cb==2)
+				base = 'C'
+			end
+			if(cb==3)
+				base = 'T'
+			end
+			if(cb==4)
+				base = 'N'
+			end
+			if(cb==5)
+				base = '-'
+			end
+			if(cb==6)
+				base = 'U'
+			end
+			
+			#concat base to our consensus sequence
+			seqr.concat(base.to_s)
+				 
+			
+			end
+		return seqr
+end
+end
+end

metadata

@@ -0,0 +1,48 @@
+--- !ruby/object:Gem::Specification
+name: most_frequent_seq
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Zachary L. Dwight
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2020-11-20 00:00:00.000000000 Z
+dependencies: []
+description: A Ruby Gem used for calculating a consensus (most frequent) DNA sequence
+  from an array of ALIGNED sequences.  Useful for bioinformatics pipelines to create
+  a reference sequence when using another sequence aligning utility.  Also, helpful
+  in finding consensus regions for primer design or viral genotyping.
+email: zach.dwight@path.utah.edu
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/most_frequent_seq.rb
+homepage: https://dna-utah.org
+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: 2.7.6
+signing_key: 
+specification_version: 4
+summary: Calculate the most frequent (consensus) DNA sequence from an array of ALIGNED
+  sequences
+test_files: []