bio-ucsc-api 0.0.1

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

@@ -0,0 +1,27 @@
+#
+# = hg18/dgv.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 track displays copy number variants (CNVs),
+# insertions/deletions (InDels), inversions and inversion breakpoints
+# annotated by the Database of Genomic Variants (DGV), which contains
+# genomic variations observed in healthy individuals. DGV focuses on
+# structural variation, defined as genomic alterations that involve
+# segments of DNA that are larger than 1000 bp. Insertions/deletions
+# of 100 bp or larger are also included.
+#
+module Bio
+  module Ucsc
+    module Hg18
+      class Dgv < DBConnection
+        extend Bio::Ucsc::Hg18::QueryUsingChromBin
+        set_table_name 'dgv'
+        set_primary_key nil
+      end
+    end
+  end
+end

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

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+# = hg18/refgene.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
+# The RefSeq Genes track shows known human protein-coding and
+# non-protein-coding genes taken from the NCBI RNA reference sequences
+# collection (RefSeq). The data underlying this track are updated
+# daily.
+#
+# = ommitted dynamic method(s) due to the method name collision
+#  none
+
+module Bio
+  module Ucsc
+    module Hg18
+      class RefGene < DBConnection
+        extend Bio::Ucsc::Hg18::QueryUsingTxBin
+        set_table_name 'refGene'
+        set_primary_key nil
+      end # class RefGene
+    end # module Hg18
+  end # module Ucsc
+end # Bio

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

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+# = hg18/rmsk.rb
+# Copyright::
+#  Copyright (C) 2011 MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+# = Table description in UCSC Table Browser
+# This track was created by using Arian Smit's RepeatMasker program,
+# which screens DNA sequences for interspersed repeats and low
+# complexity DNA sequences. The program outputs a detailed annotation
+# of the repeats that are present in the query sequence (represented
+# by this track), as well as a modified version of the query sequence
+# in which all the annotated repeats have been masked (generally
+# available on the Downloads page). RepeatMasker uses the RepBase
+# library of repeats from the Genetic Information Research Institute
+# (GIRI). RepBase is described in Jurka, J. (2000) in the References
+# section below.
+#
+# = ommitted dynamic method(s) due to the method name collision
+# none
+#
+# = Note
+# In the hg18 database, the Rmsk table is actually separated
+# into "chr1_rmsk", "chr2_rmsk", etc. The Rmsk class dynamically
+# define Rmsk::Chr1_Rmsk, Rmsk::Chr2_Rmsk, etc. The
+# Rmsk.find_by_interval calls an appropreate class automatically.
+
+module Bio
+  module Ucsc
+    module Hg18
+      class Rmsk
+        %w(
+ChrM Chr1 Chr2 Chr3 Chr4 Chr5 Chr6 Chr7 Chr8 Chr9
+Chr10 Chr11 Chr12 Chr13 Chr14 Chr15 Chr16 Chr17 Chr18 Chr19
+Chr20 Chr21 Chr22 ChrX ChrY).each do |chr|
+          klass = Class.new(DBConnection) do
+            extend Bio::Ucsc::Hg18::QueryUsingGenoBin
+            set_table_name "#{chr.downcase}_rmsk"
+            set_primary_key nil
+          end
+           self.const_set("#{chr}_Rmsk", klass)
+        end
+
+        def self.find_by_interval(interval)
+          chr_klass = self.const_get("#{interval.chrom.capitalize}_Rmsk")
+          chr_klass.__send__(:find_by_interval, interval)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,142 @@
+=begin     
+      # = DESCRIPTION
+      # From Structural Variants description page when clicking the "Describe 
+      # table schema" in the table browser:
+      # "Paired-end sequences from a human fosmid DNA library were mapped to the 
+      # assembly. The average resolution of this technique was ~8kb, and included 
+      # 56 sites of inversion not detectable by the array-based approaches. 
+      # However, because of the physical constraints of fosmid insert size, this 
+      # technique was unable to detect insertions greater than 40 kb in size."
+      class CnpTuzun < DBConnection
+        include Ucsc::Hg19::Feature
+        
+        set_table_name 'cnpTuzun'
+        set_primary_key nil
+        
+        def self.find_by_slice(slice)
+          start = slice.range.begin
+          stop = slice.range.end
+          CnpTuzun.find_by_sql('SELECT * FROM cnpTuzun' + overlap_sql(slice, start, stop))
+        end
+      end
+      
+     
+      # = DESCRIPTION
+      # From Simple Repeats description page when clicking the "Describe 
+      # table schema" in the table browser:
+      # "This track displays simple tandem repeats (possibly imperfect) located 
+      # by Tandem Repeats Finder (TRF), which is specialized for this purpose. 
+      # These repeats can occur within coding regions of genes and may be quite 
+      # polymorphic. Repeat expansions are sometimes associated with specific 
+      # diseases."
+      class SimpleRepeat < DBConnection
+        include Ucsc::Hg19::Feature
+        
+        set_table_name 'simpleRepeat'
+        set_primary_key nil
+
+        def self.find_by_slice(slice)
+          start = slice.range.begin
+          stop = slice.range.end
+          SimpleRepeat.find_by_sql('SELECT * FROM simpleRepeat' + overlap_sql(slice, start, stop))
+        end
+      end
+      
+      # = DESCRIPTION
+      # From Structural Variants description page when clicking the "Describe 
+      # table schema" in the table browser:
+      # "This track shows regions detected as putative genomic duplications 
+      # within the golden path. The following display conventions are used to 
+      # distinguish levels of similarity:
+      #   * Light to dark gray: 90 - 98% similarity
+      #   * Light to dark yellow: 98 - 99% similarity
+      #   * Light to dark orange: greater than 99% similarity
+      #   * Red: duplications of greater than 98% similarity that lack sufficient 
+      #   Segmental Duplication Database evidence (most likely missed overlaps) 
+      # For a region to be included in the track, at least 1 Kb of the total 
+      # sequence (containing at least 500 bp of non-RepeatMasked sequence) had 
+      # to align and a sequence identity of at least 90% was required."
+      class GenomicSuperDup < DBConnection
+        include Ucsc::Hg19::Feature
+        
+        set_table_name 'genomicSuperDups'
+        set_primary_key nil
+        
+        def self.find_by_slice(slice)
+          start = slice.range.begin
+          stop = slice.range.end
+          return GenomicSuperDup.find_by_sql('SELECT * FROM genomicSuperDups' + overlap_sql(slice, start, stop))
+        end
+      end
+      
+      # = DESCRIPTION
+      # From Exapted Repeat description page when clicking the "Describe 
+      # table schema" in the table browser:
+      # "This track displays conserved non-exonic elements that have been 
+      # deposited by mobile elements (repeats), a process termed "exaptation" 
+      # (Gould et al., 1982). These regions were identified during a genome-wide 
+      # survey (Lowe et al., 2007) with the expectation that regions of this type 
+      # may act as distal transcriptional regulators for nearby genes. A previous 
+      # case study experimentally verified an exapted mobile element acting as a 
+      # distal enhancer (Bejerano et al. , 2006)."
+      class ExaptedRepeat < DBConnection
+        include Ucsc::Hg19::Feature
+        
+        set_table_name 'exaptedRepeats'
+        set_primary_key nil
+        
+        def self.find_by_slice(slice)
+          start = slice.range.begin
+          stop = slice.range.end
+          return ExaptedRepeat.find_by_sql('SELECT * FROM exaptedRepeats' + overlap_sql(slice, start, stop))
+        end
+      end
+
+      # = DESCRIPTION
+      # From Interrupted Repeat description page when clicking the "Describe 
+      # table schema" in the table browser:
+      # "This track shows joined fragments of interrupted repeats extracted from 
+      # the output of the RepeatMasker program, which screens DNA sequences for 
+      # interspersed repeats and low complexity DNA sequences using the RepBase 
+      # library of repeats from the Genetic Information Research Institute (GIRI). 
+      # RepBase is described in Jurka, J. (2000) in the References section below.
+      #
+      # The detailed annotations from RepeatMasker are in the RepeatMasker track. 
+      # This track shows fragments of original repeat insertions which have been 
+      # interrupted by insertions of younger repeats or through local 
+      # rearrangements. The fragments are joined using the ID column of 
+      # RepeatMasker output."
+      class InterruptedRepeat < DBConnection
+        include Ucsc::Hg19::Feature
+        
+        set_table_name 'nestedRepeats'
+        set_primary_key nil
+        
+        def self.find_by_slice(slice)
+          start = slice.range.begin
+          stop = slice.range.end
+          return InterruptedRepeat.find_by_sql('SELECT * FROM nestedRepeats' + overlap_sql(slice, start, stop))
+        end
+      end
+      
+      # = DESCRIPTION
+      # From Microsatellite description page when clicking the "Describe 
+      # table schema" in the table browser:
+      # "This track displays regions that are likely to be useful as 
+      # microsatellite markers. These are sequences of at least 15 perfect 
+      # di-nucleotide and tri-nucleotide repeats, and tend to be highly 
+      # polymorphic in the population."
+      class Microsatellite < DBConnection
+        include Ucsc::Hg19::Feature
+        
+        set_table_name 'microsat'
+        set_primary_key nil
+        
+        def self.find_by_slice(slice)
+          start = slice.range.begin
+          stop = slice.range.end
+          return Microsatellite.find_by_sql('SELECT * FROM microsat' + overlap_sql(slice, start, stop))
+        end
+      end
+
+=end

data/lib/bio-ucsc/hg19.rb

@@ -0,0 +1,54 @@
+#
+# = hg19.rb
+# Copyright::   Cioyrught (C) 2011
+#               MISHIMA, Hiroyuki <missy at be.to / hmishima at nagasaki-u.ac.jp> 
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+
+base = File.dirname(__FILE__)
+require "#{base}/hg19/activerecord"
+require "#{base}/hg19/db_connection"
+
+
+module Bio 
+  module Ucsc
+    module Hg19
+      base = File.dirname(__FILE__)
+      autoload :Dgv,                  "#{base}/hg19/dgv"
+
+      autoload :Snp131,               "#{base}/hg19/snp131"
+
+      autoload :Snp132,               "#{base}/hg19/snp132"
+      autoload :Snp132Common,         "#{base}/hg19/snp132common"
+      autoload :Snp132Flagged,        "#{base}/hg19/snp132flagged"
+      autoload :Snp132Mult,           "#{base}/hg19/snp132mult"
+      autoload :Snp132CodingDbSnp,    "#{base}/hg19/snp132codingdbsnp"
+
+      autoload :KnownGene,            "#{base}/hg19/knowngene"
+      autoload :RefGene,              "#{base}/hg19/refgene"      
+      autoload :GwasCatalog,          "#{base}/hg19/gwascatalog"
+      autoload :CytoBand,             "#{base}/hg19/cytoband"
+      autoload :OmimGene,             "#{base}/hg19/omimgene"
+      autoload :WgRna,                "#{base}/hg19/wgrna"
+      autoload :EnsGene,              "#{base}/hg19/ensgene"
+
+      autoload :HapMapSnpsASW,        "#{base}/hg19/hapmapsnpsasw"
+      autoload :HapMapSnpsCEU,        "#{base}/hg19/hapmapsnpsceu"
+      autoload :HapMapSnpsCHB,        "#{base}/hg19/hapmapsnpschb"
+      autoload :HapMapSnpsCHD,        "#{base}/hg19/hapmapsnpschd"
+      autoload :HapMapSnpsGIH,        "#{base}/hg19/hapmapsnpsgih"
+      autoload :HapMapSnpsJPT,        "#{base}/hg19/hapmapsnpsjpt"
+      autoload :HapMapSnpsLWK,        "#{base}/hg19/hapmapsnpslwk"
+      autoload :HapMapSnpsMEX,        "#{base}/hg19/hapmapsnpsmex"
+      autoload :HapMapSnpsMKK,        "#{base}/hg19/hapmapsnpsmkk"
+      autoload :HapMapSnpsTSI,        "#{base}/hg19/hapmapsnpstsi"
+      autoload :HapMapSnpsYRI,        "#{base}/hg19/hapmapsnpsyri"
+      autoload :HapMapAllelesChimp,   "#{base}/hg19/hapmapalleleschimp"
+      autoload :HapMapAllelesMacaque, "#{base}/hg19/hapmapallelesmacaque"
+
+      autoload :Rmsk,                 "#{base}/hg19/rmsk"
+
+      autoload :PhyloP46wayPrimates,  "#{base}/hg19/phylop46wayprimates"
+      autoload :PhastConsElements46wayPrimates, "#{base}/hg19/phastconselements46wayprimates"
+    end
+  end
+end

data/lib/bio-ucsc/hg19/activerecord.rb

@@ -0,0 +1,217 @@
+#
+# = ucsc/hg19/activerecord.rb - ActiveRecord mappings to UCSC hg19 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::Hg19 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::Hg19::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::Hg19 module covers the hg19 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 Hg19
+
+      # 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: txStart, txEnd
+      # bin index is disabled
+      module QueryUsingTx
+        def find_by_interval(interval)
+          zstart = interval.zero_start
+          zend   = interval.zero_end
+          where = <<-SQL
+       chrom = :chrom
+AND ((txStart BETWEEN :zstart AND :zend)
+ OR   (txEnd BETWEEN :zstart AND :zend)
+ OR   (txStart <= :zstart AND txEnd >= :zend))
+          SQL
+          cond = {
+            :chrom => interval.chrom,
+            :zstart => zstart,
+            :zend => zend,
+          }
+          self.find(:all,
+                    :select => "*",
+                    :conditions => [where, cond],
+                    )
+        end
+      end # module QueryUsingTx
+ 
+      # interval: txStart, txEnd
+      # bin index is enabled
+      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 QueryUsingUsingTxBin
+
+      # interval: ccdsStart, ccdsEnd
+      # bin index is enabled
+      module QueryUsingCcdsBin
+        def find_by_interval(interval)
+          zstart = interval.zero_start
+          zend   = interval.zero_end
+          where = <<-SQL
+      chrom = :chrom
+AND   bin in (:bins)
+AND ((cdsStart BETWEEN :zstart AND :zend)
+OR   (cdsEnd BETWEEN :zstart AND :zend)
+OR   (cdsStart <= :zstart AND cdsEnd >= :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 QueryUsingCcdsBin
+
+      # 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 Hg19
+  end # module Ucsc
+end # module Bio