bioroebe 0.10.80

data/doc/using_biomart.md

@@ -0,0 +1,258 @@
+= Biomart
+
+Biomart is integrated into Bioroebe, although it is also mildly
+deprecated as of 2020.
+
+In principle, Biomart gives you a simple interface for working
+with the Biomart servers.
+
+The Biomart server can be seen here:
+
+    http://www.biomart.org
+
+Have a look at it for more information on Biomart itself.
+
+== Usage
+
+Include the bioroebe gem in your code:
+
+    require 'bioroebe'
+  
+To basically connect to a Biomart server and have access to all of its 
+information and meta data, you can adapt the following code:
+
+    biomart = Bioroebe::Biomart::Server.new('http://www.biomart.org/biomart')
+
+    # Next, list all of the available datasets on this Biomart server
+    # (be patient - this will take a while on this server as there's 
+    # a lot there...)
+    datasets = biomart.list_datasets
+
+    pp datasets.sort; ''
+
+    # Grab the 'wormbase_gene' dataset
+    wormbase_gene = biomart.datasets['wormbase_gene']
+
+    # List all filters and attributes of the kermits dataset:
+    p wormbase_gene.list_filters
+    p wormbase_gene.list_attributes
+
+    # Count the total number of records in the dataset:
+    p wormbase_gene.count
+
+    # Do a count with a filter added:
+    p wormbase_gene.count( :filters => { "sponsor" => "EUCOMM" } )
+
+    # Do a search using the default filters and attributes
+    # - this will return a hash with :headers (an array of the headers) 
+    #   and :data (an array of arrays of results)
+    #
+    # Doing a search like this is generally a BAD idea as biomarts tend 
+    # to hold a LOT of data... Unless you have time to kill...
+    p wormbase_gene.search
+
+    # Do a search using some specific filters (but the default attributes)
+    p wormbase_gene.search( :filters => { "marker_symbol" => "Cbx1" } )
+
+    # Do a search with specific filters and attributes
+    p wormbase_gene.search( 
+        :filters => { "marker_symbol" => "Cbx1" }, 
+        :attributes => ["marker_symbol"] 
+      )
+
+    # If you would like to retrieve a more useful results object - i.e. an 
+    # array of hashes, where each hash represents a row of results (keyed 
+    # by the attribute name), add the :process_results argument
+    p kermits.search( 
+        :filters => { "marker_symbol" => "Cbx1" }, 
+        :process_results => true 
+      )
+
+Or if you know the dataset you wish to work with and would like to 
+just get on with things:
+  
+  htgt_targ = Bioroebe::Biomart::Dataset.new( 
+    "http://www.sanger.ac.uk/htgt/biomart", 
+    { :name => "htgt_targ" } 
+  )
+  p htgt_targ.count( :filters => { "is_eucomm" => "1" } )
+
+  # etc. etc.
+
+See Biomart module and Class docs for more detail.
+
+== Advanced Filtering
+
+Most filters in biomart are just pure textual filters, i.e.
+
+  kermits.search( :filters => { "marker_symbol" => "Cbx1" } )
+
+To filter on more than one term, simply pass a comma concatenated string, 
+or an array (the following two searches are equivalent):
+
+  kermits.search( :filters => { "marker_symbol" => "Cbx1,Mysm1" } )
+  kermits.search( :filters => { "marker_symbol" => ["Cbx1","Mysm1"] } )
+
+Finally, there are also boolean filters (shown in the standard MartView 
+interface as a filter name and then two radio buttons: 'Only' or 
+'Excluded').  These filers can only accept the following:
+
+- 'Only': true / 'only' / 'included'
+- 'Excluded': false / 'excluded'
+
+Here's some example usage:
+
+  snp_mart = Bioroebe::Biomart::Dataset.new(
+    "http://www.ensembl.org/biomart", { :name => "hsapiens_snp" }
+  )
+  
+  # These are equivalent to selecting 'Only' in MartView
+  snp_mart.search( :filters => { 'with_variation_annotation' => true,       'ensembl_gene' => 'ENSG00000244734' } )
+  snp_mart.search( :filters => { 'with_variation_annotation' => 'only',     'ensembl_gene' => 'ENSG00000244734' } )
+  snp_mart.search( :filters => { 'with_variation_annotation' => 'included', 'ensembl_gene' => 'ENSG00000244734' } )
+  
+  # These are equivalent to selecting 'Excluded' in MartView
+  snp_mart.search( :filters => { 'with_variation_annotation' => false,      'ensembl_gene' => 'ENSG00000244734' } )
+  snp_mart.search( :filters => { 'with_variation_annotation' => 'excluded', 'ensembl_gene' => 'ENSG00000244734' } )
+
+== Federated Searches
+
+To perform a federated search across two datasets, do this:
+
+  htgt = Bioroebe::Biomart::Server.new( "http://www.sanger.ac.uk/htgt/biomart" )
+
+  res = htgt.datasets["htgt_targ"].search(
+    :filters => {
+      "status"     => [
+        "Mice - Genotype confirmed",
+        "Mice - Germline transmission",
+        "Mice - Microinjection in progress",
+        "ES Cells - Targeting Confirmed"
+      ]
+    },
+    :attributes => [
+      "marker_symbol",
+      "mgi_accession_id",
+      "status"
+    ],
+    :federate => [
+      {
+        :dataset => htgt.datasets["mmusculus_gene_ensembl"],
+        :filters => {
+          "chromosome_name" => "1",
+          "start"           => "1",
+          "end"             => "10000000"
+        },
+        :attributes => []
+      }
+    ]
+  )
+  
+The above will perform a federated query for all genes with available 
+mice knockout es cells in the first 10Mb of chromosome 1 from the IKMC 
+projects (not really important, but it's an example of a complex query).
+
+The basic search arguments are the same as if we were searching across 
+a single dataset, with the addition of the :federate option, which is 
+an array of hashes for each dataset (and additional filters/attributes) 
+that we want to federate our search with.
+
+Note: at present you can only federate across two datasets, this is 
+limitation in the current stable release of biomart (0.7).
+
+If you try federate across more than two datasets, a Biomart::ArgumentError
+will be raised. This limitation shall be removed from this API when it is 
+possible to federate across more than two datasets in biomart itself.
+
+Count queries are only allowed on single datasets.
+
+== Required Attributes
+
+As biomarts are generally big de-normalised data stores, a common task 
+after receiving a set of results is to filter out rows that don't have 
+information for a given attribute or set of attributes.
+
+A facility for doing this has been included into the project.
+
+  htgt = Bioroebe::Biomart::Server.new('http://www.sanger.ac.uk/htgt/biomart')
+  
+  res = htgt.datasets["mmusculus_gene_ensembl"].search(
+    :filters => {
+      "chromosome_name" => "1",
+      "start"           => "1",
+      "end"             => "10000000"
+    },
+    :attributes => [
+      "ensembl_gene_id", "ensembl_transcript_id",
+      "mouse_paralog_ensembl_gene", "mouse_paralog_chromosome"
+    ],
+    :required_attributes => ["mouse_paralog_ensembl_gene"]
+  )
+
+The above will perform a basic search and then automatically remove 
+any result row that does not have a value for the "mouse_paralog_ensembl_gene" 
+attribute.
+
+Note: You can specify more than one required attribute.  If more than one 
+required attribute is specified, ALL of these attributes must be present 
+for a data row to be returned (it is using AND logic).
+
+== Using a Proxy
+
+If you need to channel all of your requests via a proxy, specify your 
+proxy via Biomart.proxy:
+
+  Bioroebe::Biomart.proxy = "http://proxy.example.com/"
+
+Now all requests made through Biomart will be proxied via proxy.example.com.
+
+Alternatively you can also set your proxy url in the environment variable 
+'http_proxy', and Biomart will automatically detect this.
+
+== Setting a Timeout Value
+
+If you need to alter the default request timeout value, you can alter this 
+globally via Biomart.timeout:
+
+  Biomart.timeout = 60     # For a 60 second timeout...
+
+Or on a per-request basis by passing the :timeout option when searching:
+
+  kermits.search( 
+    :filters         => { "marker_symbol" => "Cbx1" }, 
+    :process_results => true, 
+    :timeout         => 60
+  )
+
+== Meta
+
+Written by Darren Oakley (daz dot oakley at gmail dot com)
+
+http://github.com/dazoakley/biomart
+
+http://rdoc.info/projects/dazoakley/biomart
+
+== License
+
+(The MIT License)
+
+Copyright (c) 2009 Darren Oakley
+
+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/html/test.html

@@ -0,0 +1,144 @@
+<html>
+<meta http-equiv="content-type" content="text/html; charset=UTF-8" />
+
+<style>
+
+.hover {
+  position: relative;
+  background-color: #F0F0F0; /* Light-grey background */
+}
+
+.input:hover
+{
+  background-color: #F0F0F0;
+}
+
+h4 {
+  margin-bottom: 5px;
+}
+
+h1 {
+  width: 30%;
+  border-bottom: 1px dotted darkblue;
+}
+
+textarea {
+  border:  1px solid black;
+  padding: 5px;
+  resize: none;
+}
+
+body
+{
+  background-image: url('http://www.livefoods.co.uk/images/02%20small-med_locust.jpg');
+  background-repeat:no-repeat;
+  background-position: center center;
+  font-size: 0.95em;
+}
+
+.submit {
+  border: 2px solid black;
+  font-weight: bold;
+  font-size: 1.05em;
+}
+
+.submit:hover
+{
+  background-color: gold;
+} 
+
+.circle {
+  display: block;
+  width:  40px;
+  height: 40px;
+  background-position: center center;
+  border-radius: 2.5em;
+  box-shadow: 5px 10px 1px rgba(0, 0, 0, 0.1);
+}
+
+.div_indent {
+  margin-left: 0.8em;
+}
+
+</style>
+
+<head>
+
+</head>
+<body>
+
+<h1 class="circle">
+Taxonomy
+</h1>
+
+<h3>
+
+(1) Welche Datenbanken haben wir lokal verfügbar?
+
+</h3>
+
+TODO: -> 
+<img src="http://www.phillips.com/imgs/nav/arrow_small_right.gif" alt="arrow_right">
+
+Hier anzeigen der lokalen Liste an Proteomen,
+die sich verändern kann.
+<br>
+<br>
+<br>
+localome ( from 
+<b>
+/data/curated/sequences/localome/
+</b>
+):
+<br>
+<br>
+
+Zusatzfile Template über web frontend.<br><br>
+taxid : type        <br>
+proteome vs. genome <br>
+
+<form name="taxonomy" action="demo_form.asp" method="POST">
+
+ taxid: <input type="text" name="taxid" class="input"><br>
+ Last name: <input type="text" name="lname" class="input"><br>
+ <!-- The Radiobuttons -->
+
+ (3) Comments field:
+  <textarea rows="4" cols="50" onclick="this.focus();this.select()" onmouseover="this.className='hover';" onmouseout="this.className='';">
+  # Input your comments here
+  </textarea>
+  <br>
+<input type="radio" name="group1" value="Proteom">Proteom
+<input type="radio" name="group1" value="Genom" checked>Genom
+<input type="radio" name="group1" value="Other">Other
+  
+  <h4>Protein-Data:</h4>
+  <div class="div_indent">
+  - n_sequences (1) <br>
+  - mod_date    (2) <br>
+  - File Size   (3)
+  </div>
+  <input type="submit" value="Submit" class="submit">
+</form>
+
+<br><br><br>
+Select Statements are:
+
+SELECT * FROM names WHERE name_txt LIKE 'Guill%';
+<br>
+
+file:///Y:/test.html
+
+<br><br>
+Test
+
+<form enctype="application/x-www-form-urlencoded" name="EntrezForm" method="post" onsubmit="return false;" action="http://www.ncbi.nlm.nih.gov/taxonomy" id="EntrezForm">
+<input name="EntrezSystem2.PEntrez.Taxonomy.Entrez_PageController.PreviousPageName" sid="1" type="hidden" value="results" />
+<input type="">
+<input type="submit" value="Submit">
+</form>
+
+<li onmouseover="this.className='hover';" onmouseout="this.className='';">Test1</li>
+
+</body>
+</html>

data/lib/bioroebe/aminoacids/aminoacid_substitution.rb

@@ -0,0 +1,118 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::AminoacidSubstitution
+#
+# This class can be used to modify a local .fasta file, and change a
+# specific aminoacid in the given sequence.
+#
+# Usage example:
+#
+#   Bioroebe::AminoacidSubstitution.new
+#
+# =========================================================================== #
+# require 'bioroebe/aminoacids/aminoacid_substitution.rb'
+# Bioroebe::AminoacidSubstitution.new(ARGV)
+# =========================================================================== #
+require 'bioroebe/base/commandline_application/commandline_application.rb'
+
+module Bioroebe
+
+class AminoacidSubstitution < ::Bioroebe::CommandlineApplication # === Bioroebe::AminoacidSubstitution
+
+  # ========================================================================= #
+  # === NAMESPACE
+  # ========================================================================= #
+  NAMESPACE = inspect
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize(
+      use_this_input_file   = nil,
+      modify_which_position = nil,
+      run_already           = true
+    )
+    reset
+    set_work_on_this_file(
+      use_this_input_file
+    )
+    set_modify_this_position(
+      modify_which_position
+    )
+    run if run_already
+  end
+
+  # ========================================================================= #
+  # === reset                                                     (reset tag)
+  # ========================================================================= #
+  def reset
+    super()
+    # ======================================================================= #
+    # === @namespace
+    # ======================================================================= #
+    @namespace = NAMESPACE
+  end
+
+  # ========================================================================= #
+  # === set_work_on_this_file
+  # ========================================================================= #
+  def set_work_on_this_file(i)
+    @work_on_this_file = i
+  end
+
+  # ========================================================================= #
+  # === set_modify_this_position
+  # ========================================================================= #
+  def set_modify_this_position(i)
+    @modify_which_position = i
+  end
+
+  # ========================================================================= #
+  # === run                                                         (run tag)
+  # ========================================================================= #
+  def run
+    require 'bioroebe/fasta_and_fastq/parse_fasta/parse_fasta.rb'
+    if @work_on_this_file and File.exist?(@work_on_this_file)
+      dataset = ::Bioroebe.parse_fasta(@work_on_this_file)
+      position = @modify_which_position.scan(/\d{1,50000}/).flatten.first.to_i
+      position -= 1 # Because ruby starts at 0.
+      sequence = dataset.sequence?.to_s
+      if sequence[position, 1] == @modify_which_position[0,1]
+        # =================================================================== #
+        # In this clause we can modify the sequence.
+        # =================================================================== #
+        sequence[position, 1] = @modify_which_position[-1,1]
+        dataset.set_sequence(sequence)
+        dataset.save
+      else
+        e 'Unable to do the operation - was the given input valid?'
+      end
+      # dataset.exchange_this_with_that(@modify_which_position,1], po
+    else
+      opne 'Please assign a file.'
+    end
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::AminoacidSubstitution[]
+  # ========================================================================= #
+  def self.[](i = '')
+    new(i)
+  end
+
+end
+
+# =========================================================================== #
+# === Bioroebe.aminoacid_substitution
+# =========================================================================== #
+def self.aminoacid_substitution(from_this_sequence = :default)
+  Bioroebe::AminoacidSubstitution.new(from_this_sequence)
+end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  Bioroebe::AminoacidSubstitution.new(ARGV)
+end # aminoacidsubstitution protein_P0095.fasta L12F

data/lib/bioroebe/aminoacids/aminoacids_mass_table.rb

@@ -0,0 +1,118 @@
+#!/usr/bin/ruby -w
+# Encoding: UTF-8
+# frozen_string_literal: true
+# =========================================================================== #
+# === Bioroebe::AminoacidsMassTable
+#
+# This small class will display the mass table for aminoacids.
+# =========================================================================== #
+# require 'bioroebe/aminoacids/aminoacids_mass_table.rb'
+# =========================================================================== #
+require 'bioroebe/base/base.rb'
+
+module Bioroebe
+
+class AminoacidsMassTable < Base # === Bioroebe::AminoacidsMassTable 
+
+  # ========================================================================= #
+  # === PADDING_TO_USE
+  # ========================================================================= #
+  PADDING_TO_USE = '  '
+
+  # ========================================================================= #
+  # === initialize
+  # ========================================================================= #
+  def initialize
+    reset
+    Bioroebe::AminoacidsMassTable.show
+  end
+
+  # ========================================================================= #
+  # === reset
+  # ========================================================================= #
+  def reset
+    super()
+  end
+
+  # ========================================================================= #
+  # === AminoacidsMassTable.erev
+  # ========================================================================= #
+  def self.erev(i)
+    ::Bioroebe.erev(i)
+  end
+
+  # ========================================================================= #
+  # === AminoacidsMassTable.e
+  # ========================================================================= #
+  def self.e(i = '')
+    puts i
+  end
+
+  # ========================================================================= #
+  # === Bioroebe::AminoacidsMassTable.show
+  # ========================================================================= #
+  def self.show(
+      optional_padding = PADDING_TO_USE
+    )
+    sum = 0
+    erev 'Aminoacids Mass Table - Molecular Weight of '\
+         'Amino Acids:'; e # Need a newline here.
+    AMINO_ACIDS_MASS_TABLE.each {|key, value|
+      long_amino_acid = AMINO_ACIDS[key].select {|inner_key, _|
+        inner_key.size == 3
+      }.values.first
+      left = optional_padding+
+             key.to_s+
+             ' ('+long_amino_acid+')'+': '
+      sum += value # Add to the sum.
+      # ===================================================================== #
+      # Next pad the value.
+      # ===================================================================== #
+      value = value.to_s.rjust(10)
+      left = left.ljust(22)
+      # ===================================================================== #
+      # The variable left may look like this:
+      #   "  T (threonine): "
+      # ===================================================================== #
+      if left.include? '('
+        splitted = left.split('(')
+        splitted[0] = ::Bioroebe.springgreen(splitted[0])+::Bioroebe.rev
+        left = splitted.join('(')
+      end
+      erev left+
+           Colours.sfancy(value)
+    }
+    e
+    erev 'Average weight of an amino acid: '+
+      Colours.simp(
+        (sum.to_f / AMINO_ACIDS_MASS_TABLE.keys.size).round(2).to_s
+      )
+    e # Trailing newline.
+  end
+
+  # ========================================================================= #
+  # === AminoacidsMassTable.report_which_file_is_used
+  #
+  # The purpose of this method is to simply report which file
+  # we use to read in the mass table.
+  # ========================================================================= #
+  def self.report_which_file_is_used
+    erev 'We will read from the file `'+
+          Colours.sfile(FILE_AMINO_ACIDS_MASS_TABLE)+
+          Colours.rev+'`.'
+  end
+
+end
+
+# =========================================================================== #
+# === Bioroebe.show_aminoacids_mass_table
+# =========================================================================== #
+def self.show_aminoacids_mass_table
+  Bioroebe::AminoacidsMassTable.show
+end
+
+end
+
+if __FILE__ == $PROGRAM_NAME
+  Bioroebe::AminoacidsMassTable.show
+end # aminoacidsmasstable