viral_seq 0.3.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 5429096d449465668f4b515257602d1451007b84ad20841d5035a66b45569cc5
+  data.tar.gz: c910521dcee98650f0db6a3c9d83a4435fae535b4a087a87117820da5c8459c1
+SHA512:
+  metadata.gz: c2603d523affd6eca26bf39935f7137406a8f44a0451b1458ae528b631e0b916032aedacadb630cd00cdb9aeb745c0e276286e9480345c5add77e3ba47afe8eb
+  data.tar.gz: 9bfe02dee55538b08e268e96a5d0b2b1e27ae14db034e89fef47f0f00a0ac30e5533a6f69e43de21076335d34ab417bba7405748f3d4d8cca300732e8cab4c1b

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status
+
+# gem files
+*.gem

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,7 @@
+---
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+  - 2.6.0
+before_install: gem install bundler -v 2.0.1

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+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.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at swanstromlab@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

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

data/Gemfile.lock

@@ -0,0 +1,37 @@
+PATH
+  remote: .
+  specs:
+    viral_seq (0.3.0)
+      muscle_bio (~> 0.4)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.3)
+    muscle_bio (0.4.0)
+    rake (10.5.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.0)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-mocks (3.8.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 2.0)
+  rake (~> 10.0)
+  rspec (~> 3.0)
+  viral_seq!
+
+BUNDLED WITH
+   2.0.1

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2019 Shuntai Zhou (shuntai.zhou@gmail.com)
+
+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/README.md

@@ -0,0 +1,39 @@
+# viral_seq
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ViralSeq'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install viral_seq
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/viral_seq. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the viral_seq project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/viral_seq/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+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 "viral_seq"
+
+# 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(__FILE__)

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/lib/viral_seq/a3g.rb

@@ -0,0 +1,172 @@
+# viral_seq/a3g
+# APOBEC3g/f hypermutation function including
+# ViralSeq::a3g_hypermut_seq_hash
+# ViralSeq::apobec3gf
+
+# APOBEC3g/f G to A hypermutation
+# APOBEC3G/F pattern: GRD -> ARD
+# control pattern: G[YN|RC] -> A[YN|RC]
+# use the sample consensus to determine potential a3g sites
+
+# Two criteria to identify hypermutation
+# 1. Fisher's exact test on the frequencies of G to A mutation at A3G positons vs. non-A3G positions
+# 2. Poisson distribution of G to A mutations at A3G positions, outliers sequences
+# note:  criteria 2 only applies on a sequence file containing more than 20 sequences
+#        b/c Poisson model does not do well on small sample size.
+
+# ViralSeq.a3g_hypermut_seq_hash(sequence_hash)
+# sequence_hash is a Hash object for sequences. {:name => :sequence, ...}
+# return array [hypermutation_hash, statistic_info]
+# hypermutation_hash is a Hash object for sequences
+# statistic_info is a hash object of [sequence_name, stats],
+# in which stats String object in csv format (separated by ',') containing
+#   sequence tag
+#   G to A mutation numbers at potential a3g positions
+#   total potential a3g G positions
+#   G to A mutation numbers at non a3g positions
+#   total non a3g G positions
+#   a3g G to A mutation rate / non-a3g G to A mutation rate
+#   Fishers Exact P-value
+#
+# =USAGE
+#   # example 1
+#   sequences = ViralSeq.fasta_to_hash('spec/sample_files/sample_a3g_sequence1.fasta')
+#   hypermut = ViralSeq.a3g_hypermut_seq_hash(sequences)
+#   hypermut[0].keys
+#   => [">Seq7", ">Seq14"]
+#   stats = hypermut[1]
+#   stats.values
+#   => [">Seq7,23,68,1,54,18.26,4.308329383112348e-06", ">Seq14,45,68,9,54,3.97,5.2143571971582974e-08"]
+#
+#   # example 2
+#   sequences = ViralSeq.fasta_to_hash('spec/sample_files/sample_a3g_sequence2.fasta')
+#   hypermut = ViralSeq.a3g_hypermut_seq_hash(sequences)
+#   stats = hypermut[1]
+#   stats = values
+#   => [">CTAACACTCA_134_a3g-sample2,4,35,0,51,Infinity,0.02465676660128911", ">ATAGTGCCCA_60_a3g-sample2,4,35,1,51,5.83,0.1534487353839561"]
+#   # notice sequence ">ATAGTGCCCA_60_a3g-sample2" has a p value at 0.15, greater than 0.05, but it is still called as hypermutation sequence b/c it's Poisson outlier sequence.
+
+
+# ViralSeq.apobec3gf(sequence)
+# APOBEC3G/F pattern: GRD -> ARD
+# control pattern: G[YN|RC] -> A[YN|RC]
+# input a sequence String object
+# return all two arrays of position numbers of
+#   a3g G positions (a3g)
+#   non-a3g G positions (control)
+
+
+module ViralSeq
+  def ViralSeq.a3g_hypermut_seq_hash(seq_hash)
+    # mut_hash number of apobec3g/f mutations per sequence
+    mut_hash = {}
+    hm_hash = {}
+    out_hash = {}
+
+    # total G->A mutations at apobec3g/f positions.
+    total = 0
+
+    # make consensus sequence for the input sequence hash
+    ref = ViralSeq.consensus(seq_hash.values)
+
+    # obtain apobec3g positions and control positions
+    apobec = ViralSeq.apobec3gf(ref)
+    mut = apobec[0]
+    control = apobec[1]
+
+    seq_hash.each do |k,v|
+      a = 0 # muts
+      b = 0 # potential mut sites
+      c = 0 # control muts
+      d = 0 # potenrial controls
+      mut.each do |n|
+        next if v[n] == "-"
+        if v[n] == "A"
+          a += 1
+          b += 1
+        else
+          b += 1
+        end
+      end
+      mut_hash[k] = a
+      total += a
+
+      control.each do |n|
+        next if v[n] == "-"
+        if v[n] == "A"
+          c += 1
+          d += 1
+        else
+          d += 1
+        end
+      end
+      rr = (a/b.to_f)/(c/d.to_f)
+
+      t1 = b - a
+      t2 = d - c
+
+      fet = Rubystats::FishersExactTest.new
+      fisher = fet.calculate(t1,t2,a,c)
+      perc = fisher[:twotail]
+      info = k + "," + a.to_s + "," + b.to_s + "," + c.to_s + "," + d.to_s + "," + rr.round(2).to_s + "," + perc.to_s
+      out_hash[k] = info
+      if perc < 0.05
+        hm_hash[k] = info
+      end
+    end
+
+    if seq_hash.size > 20
+      rate = total.to_f/(seq_hash.size)
+
+      count_mut = ViralSeq.count(mut_hash.values)
+      maxi_count = count_mut.values.max
+
+      poisson_hash = ViralSeq.poisson_distribution(rate,maxi_count)
+
+      cut_off = 0
+      poisson_hash.each do |k,v|
+        cal = seq_hash.size * v
+        obs = count_mut[k]
+        if obs >= 20 * cal
+          cut_off = k
+          break
+        elsif k == maxi_count
+          cut_off = maxi_count
+        end
+      end
+
+      mut_hash.each do |k,v|
+        if v > cut_off
+          hm_hash[k] = out_hash[k]
+        end
+      end
+    end
+
+    hm_seq_hash = {}
+    hm_hash.keys.each do |k|
+      hm_seq_hash[k] = seq_hash[k]
+    end
+    return [hm_seq_hash,hm_hash]
+  end
+
+  # APOBEC3G/F mutation position identification
+  # APOBEC3G/F pattern: GRD -> ARD
+  # control pattern: G[YN|RC] -> A[YN|RC]
+
+  def self.apobec3gf(seq = "")
+    seq.tr!("-", "")
+    seq_length = seq.size
+    apobec_position = []
+    control_position = []
+    (0..(seq_length - 3)).each do |n|
+      tri_base = seq[n,3]
+      if tri_base =~ /G[A|G][A|G|T]/
+        apobec_position << n
+      elsif seq[n] == "G"
+        control_position << n
+      end
+    end
+    return [apobec_position,control_position]
+  end
+
+end

data/lib/viral_seq/fasta.rb

@@ -0,0 +1,154 @@
+# fasta.rb
+# methods for converting sequence formats, including
+#   ViralSeq::fasta_to_hash
+#   ViralSeq::fastq_to_fasta
+#   ViralSeq::fastq_to_hash
+#   ViralSeq::fasta_hash_to_rsphylip
+#   ViralSeq::pair_fasta_to_hash
+
+# =USAGE
+#   sequence_fasta_hash = ViralSeq.fasta_to_hash(input_fasta_file)
+#   # input a sequence file in fasta format, read as a sequence hash
+#   # {:sequence_name1 => sequence1, ...}
+
+#   sequence_fasta_hash = ViralSeq.fastq_to_fasta(input_fastq_file)
+#   # input a sequence file in fastq format, read as a sequence hash
+#   # discard sequence quality score
+
+#   sequence_fastq_hash = ViralSeq.fasta_to_hash(input_fastq_file)
+#   # input a sequence file in fastq format, read as a sequence hash
+#   # keep sequence quality score
+#   # {:sequence_name1 => [sequence1, quality1], ...}
+
+#   phylip_hash = ViralSeq.fasta_hash_to_rsphylip(sequence_fasta_hash)
+#   # convert a aligned fasta sequence hash into relaxed sequencial phylip format
+
+#   paired_sequence_hash = ViralSeq.pair_fasta_to_hash(directory_of_paired_fasta)
+#   # input a directory containing paired sequence files in the fasta format
+#   # ├───lib1
+#         │     lib1_r1.txt
+#         │     lib1_r2.txt
+#   # paired sequence files need to have "r1" and "r2" in their file names
+#   # the sequence taxa should only differ by last 3 characters to distinguish r1 and r2 sequence.
+#   # return a paired sequence hash :seq_name => [r1_seq, r2_seq]
+
+module ViralSeq
+
+  def self.fasta_to_hash(infile)
+    f=File.open(infile,"r")
+    return_hash = {}
+    name = ""
+    while line = f.gets do
+      line.tr!("\u0000","")
+      next if line == "\n"
+      next if line =~ /^\=/
+      if line =~ /^\>/
+        name = line.chomp
+        return_hash[name] = ""
+      else
+        return_hash[name] += line.chomp.upcase
+      end
+    end
+    f.close
+    return return_hash
+  end
+
+
+  # fastq file to fasta, discard quality, return a sequence hash
+
+  def self.fastq_to_fasta(fastq_file)
+      count = 0
+      sequence_a = []
+      count_seq = 0
+
+      File.open(fastq_file,'r') do |file|
+        file.readlines.collect do |line|
+          count +=1
+          count_m = count % 4
+          if count_m == 1
+            line.tr!('@','>')
+            sequence_a << line.chomp
+            count_seq += 1
+          elsif count_m == 2
+            sequence_a << line.chomp
+          end
+        end
+      end
+      Hash[*sequence_a]
+  end
+
+  # fastq file to hash, including quality. {:seq_name => [seq,quality]}
+
+  def self.fastq_to_hash(fastq_file)
+      count = 0
+      sequence_a = []
+      quality_a = []
+      count_seq = 0
+
+      File.open(fastq_file,'r') do |file|
+        file.readlines.collect do |line|
+          count +=1
+          count_m = count % 4
+          if count_m == 1
+            line.tr!('@','>')
+            sequence_a << line.chomp
+            quality_a << line.chomp
+            count_seq += 1
+          elsif count_m == 2
+            sequence_a << line.chomp
+          elsif count_m == 0
+            quality_a << line.chomp
+          end
+        end
+      end
+      sequence_hash = Hash[*sequence_a]
+      quality_hash = Hash[*quality_a]
+      return_hash = {}
+      sequence_hash.each do |k,v|
+        return_hash[k] = [v, quality_hash[k]]
+      end
+      return return_hash
+  end
+
+  # fasta sequence hash to relaxed sequencial phylip format
+
+  def self.fasta_hash_to_rsphylip(seqs)
+    outline = "\s" + seqs.size.to_s + "\s" + seqs.values[0].size.to_s + "\n"
+    names = seqs.keys
+    max_name_l = (names.max.size - 1)
+    max_name_l > 10 ? name_block_l = max_name_l : name_block_l = 10
+    seqs.each do |k,v|
+      outline += k[1..-1] + "\s" * (name_block_l - k.size + 2) + v.scan(/.{1,10}/).join("\s") + "\n"
+    end
+    return outline
+  end
+
+  # input a directory with r1 and r2 sequences, return a hash :seq_name => [r1_seq, r2_seq]
+  # r1 and r2 file names should contain "r1" and "r2" respectively
+  # the sequence taxa should only differ by last 3 characters to distinguish r1 and r2 sequence.
+  def self.pair_fasta_to_hash(indir)
+    files = Dir[indir + "/*"]
+    r1_file = ""
+    r2_file = ""
+    files.each do |f|
+      if File.basename(f) =~ /r1/i
+        r1_file = f
+      elsif File.basename(f) =~ /r2/i
+        r2_file = f
+      end
+    end
+
+    seq1 = ViralSeq.fasta_to_hash(r1_file)
+    seq2 = ViralSeq.fasta_to_hash(r2_file)
+
+    new_seq1 = seq1.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
+    new_seq2 = seq2.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
+
+    seq_pair_hash = {}
+
+    new_seq1.each do |seq_name,seq|
+      seq_pair_hash[seq_name] = [seq, new_seq2[seq_name]]
+    end
+    return seq_pair_hash
+  end
+end