bio-ucsc-api 0.0.1

data/lib/bio-ucsc.rb

@@ -0,0 +1,20 @@
+#
+# = ucsc.rb
+# Copyright::   Cioyrught (C) 2011
+#               MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+# License::     Ruby licence (Ryby's / GPLv2 dual)
+
+base = File.dirname(__FILE__)
+require "#{base}/bio-ucsc/ucsc_bin"
+require "bio-genomic-interval"
+
+module Bio
+  module Ucsc
+    base = File.dirname(__FILE__)
+    autoload :Hg18,  "#{base}/bio-ucsc/hg18"
+    autoload :Hg19,  "#{base}/bio-ucsc/hg19"
+
+    # ToDo
+    # autoload :Mm9,   "#{base}/bio-ucsc/mm9"
+  end
+end

data/lib/bio-ucsc/hg18.rb

@@ -0,0 +1,27 @@
+#
+# = ucsc.rb
+# Copyright::   Cioyrught (C) 2011
+#               MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+# Copyright::   Copyright (C) 2008
+#               Jan Aerts <jan.aerts@gmail.com>
+# License::     Ruby's
+
+base = File.dirname(__FILE__)
+require "#{base}/hg18/db_connection"
+require "#{base}/hg18/activerecord"
+
+module Bio
+  module Ucsc
+    module Hg18
+      base = File.dirname(__FILE__)
+      autoload :RefGene,      "#{base}/hg18/refgene"
+      autoload :Dgv,          "#{base}/hg18/dgv"
+      autoload :CnpIafrate2,  "#{base}/hg18/cnpiafrate2"
+      autoload :CnpLocke,     "#{base}/hg18/cnplocke"
+      autoload :CnpRedon,     "#{base}/hg18/cnpredon"
+      autoload :CnpSebat2,    "#{base}/hg18/cnpsebat2"
+      autoload :CnpSharp2,    "#{base}/hg18/cnpsharp2"
+      autoload :Rmsk,         "#{base}/hg18/rmsk.rb"
+    end
+  end
+end

data/lib/bio-ucsc/hg18/activerecord.rb

@@ -0,0 +1,166 @@
+#
+# = ucsc/hg18/activerecord.rb - ActiveRecord mappings to UCSC hg18 database
+# 
+# Copyright::
+#   Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp>
+#   Copyright (C) 2008 Jan Aerts <jan.aerts@gmail.com>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = DESCRIPTION
+# == What is it?
+# The UCSC module provides an API to the UCSC databases
+# stored at genome-mysql.cse.ucsc.edu. This is the same information that is
+# available from http://genome.ucsc.edu
+#
+# The Ucsc::Hg18 module covers the hg19 (= GRCh37) assembly.
+#
+# == ActiveRecord
+# The UCSC API provides a ruby interface to the UCSC mysql databases
+# at genome-mysql.cse.ucsc.edu. Most of the API is based on ActiveRecord to
+# get data from that database. In general, each table is described by a
+# class with the same name: the cnpRedon table is covered by the
+# CnpRedon class, the dgv table is covered by the Dgv class,
+# etc. As a result, accessors are available for all columns in each table.
+# For example, the cnpRedon table has the following columns: chrom, chromStart, 
+# chromEnd and name. Through ActiveRecord, these column names become available 
+# as attributes of CnpRedon objects:
+#   puts my_cnp_redon.name
+#   puts my_cnp_redon.chrom
+#   puts my_cnp_redon.chromStart
+#   puts my_cnp_redon.chromEnd
+#
+# ActiveRecord makes it easy to extract data from those tables using the
+# collection of #find methods. There are three types of #find methods (e.g.
+# for the CnpRedon class):
+# a. find based on primary key in table:
+#  # not possible with the UCSC database
+# b. find_by_sql:
+#  my_cnp = CnpRedon.find_by_sql('SELECT * FROM cnpRedon WHERE name = 'cnp1'")
+# c. find_by_<insert_your_column_name_here>
+#  my_cnp = CnpRedon.find_by_name('cnp1')
+#  my_cnp2 = CnpRedon.find_by_chrom_and_chromStart('chr1',377)
+# To find out which find_by_<column> methods are available, you can list the
+# column names using the column_names class methods:
+#
+#  puts Ucsc::Hg18::CnpRedon.column_names.join("\t")
+#
+# For more information on the find methods, see
+# http://ar.rubyonrails.org/classes/ActiveRecord/Base.html#M000344
+#
+
+module Bio
+  module Ucsc
+
+    # = DESCRIPTION
+    # The Bin::Ucsc::Hg18 module covers the hg18 database from
+    # genome-mysql.cse.ucsc.edu and covers mainly sequences and their annotations.
+    # For a more information about the database tables, click on the "Describe 
+    # table schema" in the Table Browser.
+    module Hg18
+      # interval: chromStart, chromEnd
+      # bin index is enabled
+      module QueryUsingChromBin
+        def find_by_interval(interval)
+          zstart = interval.zero_start
+          zend   = interval.zero_end
+          where = <<-SQL
+    chrom = :chrom
+AND bin in (:bins)
+AND ((chromStart BETWEEN :zstart AND :zend)
+ OR (chromEnd BETWEEN :zstart AND :zend)
+ OR (chromStart <= :zstart AND chromEnd >= :zend))
+          SQL
+          cond = {
+            :chrom => interval.chrom,
+            :bins  => Ucsc::UcscBin.bin_all(zstart, zend),
+            :zstart => zstart,
+            :zend => zend,
+          }
+          
+          self.find(:all,
+                    :select => "*",
+                    :conditions => [where, cond],
+                    )
+        end
+      end # module QueryUsingChromBin 
+
+      # interval: chromStart, chromEnd
+      # bin index is disabled
+      module QueryUsingChrom
+        def find_by_interval(interval)
+          zstart = interval.zero_start
+          zend   = interval.zero_end
+          where = <<-SQL
+       chrom = :chrom
+ AND ((chromStart BETWEEN :zstart AND :zend)
+ OR   (chromEnd BETWEEN :zstart AND :zend)
+ OR   (chromStart <= :zstart AND chromEnd >= :zend))
+          SQL
+          cond = {
+            :chrom => interval.chrom,
+            :zstart => zstart,
+            :zend => zend,
+          }
+          self.find(:all,
+                    :select => "*",
+                    :conditions => [where, cond],
+                    )
+        end
+      end # module QueryUsingChrom
+
+      # interval: chromStart, chromEnd
+      # bin index is disabled
+      module QueryUsingTxBin
+        def find_by_interval(interval)
+          zstart = interval.zero_start
+          zend   = interval.zero_end
+          where = <<-SQL
+      chrom = :chrom
+AND   bin in (:bins)
+AND ((txStart BETWEEN :zstart AND :zend)
+OR   (txEnd BETWEEN :zstart AND :zend)
+OR   (txStart <= :zstart AND txEnd >= :zend))
+          SQL
+          cond = {
+            :chrom  => interval.chrom,
+            :bins   => Bio::Ucsc::UcscBin.bin_all(zstart, zend),
+            :zstart => zstart,
+            :zend   => zend,
+          }
+          self.find(:all,
+                    :select => "*",
+                    :conditions => [where, cond],
+                    )
+        end
+      end # module QueryUsingTxBin
+
+      # interval: genoName, genoStart, genoEnd
+      # bin index is enabled
+      module QueryUsingGenoBin
+        def find_by_interval(interval)
+          zstart = interval.zero_start
+          zend   = interval.zero_end
+          where = <<-SQL
+    genoName = :chrom
+AND bin in (:bins)
+AND ((genoStart BETWEEN :zstart AND :zend)
+ OR (genoEnd BETWEEN :zstart AND :zend)
+ OR (genoStart <= :zstart AND genoEnd >= :zend))
+          SQL
+          cond = {
+            :chrom => interval.chrom,
+            :bins  => Ucsc::UcscBin.bin_all(zstart, zend),
+            :zstart => zstart,
+            :zend => zend,
+          }
+          
+          self.find(:all,
+                    :select => "*",
+                    :conditions => [where, cond],
+                    )
+        end
+      end # module QueryUsingChromBin 
+
+    end # module Hg18
+  end # module Ucsc
+end # module Bio 

data/lib/bio-ucsc/hg18/cnpiafrate2.rb

@@ -0,0 +1,31 @@
+#
+# = hg18/cnpiafrate2.rb
+# Copyright::
+#  Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+#  Copyright (C) 2008 Jan Aerts <jan.aerts@gmail.com>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = Table desfription in UCSC Table Browser
+# This annotation shows regions detected as putative copy number
+# polymorphisms (CNP) and sites of detected intermediate-sized
+# structural variation (ISV). The CNPs and ISVs were determined by
+# various methods, displayed in individual subtracks within the
+# annotation.
+#
+# Iafrate BAC microarray analysis
+# All hybridizations were performed in duplicate incorporating a
+# dye-reversal using proprieta#ry 1 Mb GenomeChip V1.2 Human BAC Arrays
+# consisting of 2,632 BAC clones (Spectral Genomics,# Houston, TX). The
+# false positive rate was estimated at ~1 clone per 5,264 tested.
+
+module Bio
+  module Ucsc
+    module Hg18
+      class CnpIafrate2 < DBConnection
+        extend  Bio::Ucsc::Hg18::QueryUsingChromBin
+        set_table_name 'cnpIafrate2'
+        set_primary_key nil
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg18/cnplocke.rb

@@ -0,0 +1,31 @@
+#
+# = hg18/cnplocke.rb
+# Copyright::
+#  Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+#  Copyright (C) 2008 Jan Aerts <jan.aerts@gmail.com>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = Table desfription in UCSC Table Browser
+# This annotation shows regions detected as putative copy number
+# polymorphisms (CNP) and sites of detected intermediate-sized
+# structural variation (ISV). The CNPs and ISVs were determined by
+# various methods, displayed in individual subtracks within the
+# annotation.
+#
+# Locke analysis of duplication-rich regions
+# DNA samples were obtained from Coriell Cell Repositories. The
+# reference DNA used for all hybridizations was from a single male of
+# Czechoslovakian descent, Coriell ID GM15724 (also used in the Sharp
+# study).
+
+module Bio
+  module Ucsc
+    module Hg18
+      class CnpLocke < DBConnection
+        extend Bio::Ucsc::Hg18::QueryUsingChromBin
+        set_table_name 'cnpLocke'
+        set_primary_key nil
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg18/cnpredon.rb

@@ -0,0 +1,32 @@
+#
+# = hg18/cnpredon.rb
+# Copyright::
+#  Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+#  Copyright (C) 2008 Jan Aerts <jan.aerts@gmail.com>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = Table desfription in UCSC Table Browser
+# This annotation shows regions detected as putative copy number
+# polymorphisms (CNP) and sites of detected intermediate-sized
+# structural variation (ISV). The CNPs and ISVs were determined by
+# various methods, displayed in individual subtracks within the
+# annotation.
+#
+# Redon analysis of HapMap data
+# Experiments were performed with the International HapMap DNA and
+# cell-line collection using two technologies: comparative analysis of
+# hybridization intensities on Affymetric GeneChip Human Mapping 500K
+# early access arrays (500K EA) and comparative genomic hybridization
+# with a Whole Genome TilePath (WGTP) array.
+
+module Bio
+  module Ucsc
+    module Hg18
+      class CnpRedon < DBConnection
+        extend  Bio::Ucsc::Hg18::QueryUsingChromBin
+        set_table_name 'cnpRedon'
+        set_primary_key nil
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg18/cnpsebat2.rb

@@ -0,0 +1,35 @@
+# 
+# = hg18/cnpsebat2.rb
+# Copyright::
+#  Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+#  Copyright (C) 2008 Jan Aerts <jan.aerts@gmail.com>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = Table desfription in UCSC Table Browser
+# This annotation shows regions detected as putative copy number
+# polymorphisms (CNP) and sites of detected intermediate-sized
+# structural variation (ISV). The CNPs and ISVs were determined by
+# various methods, displayed in individual subtracks within the
+# annotation.
+#
+# Sebat ROMA Following digestion with BglII or HindIII, genomic DNA
+# was hybridized to a custom array consisting of 85,000
+# oligonucleotide probes. The probes were selected to be free of
+# common repeats and have unique homology within the human genome. The
+# average resolution of the array was -5 kb; however, only intervals
+# in which three consecutive probes showed concordant signals were
+# scored as CNPs. All hybridizations were performed in duplicate
+# incorporating a dye-reversal, with the false positive rate estimated
+# to be -6%.
+
+module Bio
+  module Ucsc
+    module Hg18
+      class CnpSebat2 < DBConnection
+        extend Bio::Ucsc::Hg18::QueryUsingChrom
+        set_table_name 'cnpSebat2'
+        set_primary_key nil
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg18/cnpsharp2.rb

@@ -0,0 +1,32 @@
+# 
+# = hg18/cnpsharp2.rb
+# Copyright::
+#  Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+#  Copyright (C) 2008 Jan Aerts <jan.aerts@gmail.com>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = Table desfription in UCSC Table Browser
+# This annotation shows regions detected as putative copy number
+# polymorphisms (CNP) and sites of detected intermediate-sized
+# structural variation (ISV). The CNPs and ISVs were determined by
+# various methods, displayed in individual subtracks within the
+# annotation.
+#
+# Sharp BAC microarray analysis
+# All hybridizations were performed in duplicate incorporating a
+# dye-reversal using a custom array consisting of 2,194 end-sequence
+# or FISH-confirmed BACs, targeted to regions of the genome flanked by
+# segmental duplications. The false positive rate was estimated at -3
+# clones per 4,000 tested.
+
+module Bio
+  module Ucsc
+    module Hg18
+      class CnpSharp2 < DBConnection
+        extend  Bio::Ucsc::Hg18::QueryUsingChromBin
+        set_table_name 'cnpSharp2'
+        set_primary_key nil
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg18/db_connection.rb

@@ -0,0 +1,61 @@
+#
+# = lib/ucsc/hg18/db_connection.rb - UCSC hg18 DB connection
+#
+# Copyright::   Cioyrught (C) 2011
+#               MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+# Copyright::   Copyright (C) 2008
+#               Jan Aerts <jan.aerts@gmail.com>
+# License::     Ruby licence (Ryby's / GPLv2 dual)
+
+require 'rubygems'
+require 'active_record'
+
+module Bio
+  module Ucsc
+
+    module Hg18
+      # = DESCRIPTION
+      # The Ucsc::Hg18::DBConnection is the actual connection established
+      # with the UCSC mysql server.
+
+      class DBConnection < ActiveRecord::Base
+        # = DESCRIPTION
+        # The Ucsc::Hg18::DBConnection#connect method makes the connection
+        # to the UCSC hg18 database.
+        #
+        # = USAGE
+        #  # Connect to the hg18
+        #  Ensembl::Core::DBConnection.connect
+        #
+        # ---
+        # *Arguments*: none
+        @@db_adapter  = 'mysql'
+        @@db_host     = 'genome-mysql.cse.ucsc.edu'
+        @@db_username = 'genome'
+        @@db_password = ''
+
+        cattr_accessor :db_host, :db_username, :db_password
+
+        self.abstract_class = true
+
+        def self.default
+          @@db_adapter  = 'mysql'
+          @@db_host     = 'genome-mysql.cse.ucsc.edu'
+          @@db_username = 'genome'
+          @@db_password = ''
+        end
+
+        def self.connect
+          establish_connection(
+                               :adapter =>  @@db_adapter,
+                               :host =>     @@db_host,
+                               :database => 'hg18',
+                               :username => @@db_username,
+                               :password => @@db_password
+                               )
+        end
+      end
+    end # module Hg18
+    
+  end # module Ucsc
+end # module Bio