bio-ucsc-api 0.0.1

data/lib/bio-ucsc/hg19/snp132codingdbsnp.rb

@@ -0,0 +1,29 @@
+#
+# = hg19/snp132codingdbsnp.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 contains information about a subset of the single
+# nucleotide polymorphisms and small insertions and deletions (indels)
+# -- collectively Simple Nucleotide Polymorphisms -- from dbSNP
+# build 132, available from ftp.ncbi.nih.gov/snp. Only SNPs that have a
+# minor allele frequency of at least 1% and are mapped to a single
+# location in the reference genome assembly are included in this
+# subset. Frequency data are not available for all SNPs, so this subset
+# is incomplete.
+# 
+# Annotations of the effects of SNPs on translated protein sequence.
+
+module Bio
+  module Ucsc
+    module Hg19
+      class Snp132CodingDbSnp < DBConnection
+        extend Bio::Ucsc::Hg19::QueryUsingChromBin
+        set_table_name 'snp132CodingDbSnp'
+        set_primary_key nil
+       end
+    end
+  end
+end

data/lib/bio-ucsc/hg19/snp132common.rb

@@ -0,0 +1,32 @@
+#
+# = hg19/snp132common.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 desfription in UCSC Table Browser
+# This track contains information about a subset of the single
+# nucleotide polymorphisms and small insertions and deletions (indels)
+# -- collectively Simple Nucleotide Polymorphisms -- from dbSNP
+# build 132, available from ftp.ncbi.nih.gov/snp. Only SNPs that have a
+# minor allele frequency of at least 1% and are mapped to a single
+# location in the reference genome assembly are included in this
+# subset. Frequency data are not available for all SNPs, so this subset
+# is incomplete.
+# 
+# Common SNPs (132): uniquely mapped variants that appear in at least
+# 1% of the population
+
+module Bio
+  module Ucsc
+    module Hg19
+      class Snp132Common < DBConnection
+        extend Bio::Ucsc::Hg19::QueryUsingChromBin
+        set_table_name 'snp132Common'
+        set_primary_key nil
+        columns_hash.delete("valid")
+        columns_hash.delete("class")
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg19/snp132flagged.rb

@@ -0,0 +1,31 @@
+# = hg19/snp132flagged.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 desfription in UCSC Table Browser
+# This track contains information about a subset of the single
+# nucleotide polymorphisms and small insertions and deletions (indels)
+# -- collectively Simple Nucleotide Polymorphisms -- from dbSNP
+# build 132, available from ftp.ncbi.nih.gov/snp. Only SNPs that have a
+# minor allele frequency of at least 1% and are mapped to a single
+# location in the reference genome assembly are included in this
+# subset. Frequency data are not available for all SNPs, so this subset
+# is incomplete.
+#
+# Flagged SNPs (132): uniquely mapped variants, excluding Common SNPs,
+# that have been flagged by dbSNP as "clinically associated"
+
+module Bio
+  module Ucsc
+    module Hg19
+      class Snp132Flagged < DBConnection
+        extend Bio::Ucsc::Hg19::QueryUsingChromBin
+        set_table_name 'snp132Flagged'
+        set_primary_key nil
+        columns_hash.delete("valid")
+        columns_hash.delete("class")
+      end
+    end
+  end
+end

data/lib/bio-ucsc/hg19/snp132mult.rb

@@ -0,0 +1,32 @@
+#
+# = hg19/snp132mult.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 contains information about a subset of the single
+# nucleotide polymorphisms and small insertions and deletions (indels)
+# -- collectively Simple Nucleotide Polymorphisms -- from dbSNP
+# build 132, available from ftp.ncbi.nih.gov/snp. Only SNPs that have a
+# minor allele frequency of at least 1% and are mapped to a single
+# location in the reference genome assembly are included in this
+# subset. Frequency data are not available for all SNPs, so this subset
+# is incomplete.
+# 
+# Mult. SNPs(132): variants that have been mapped to more than one
+# genomic location
+
+module Bio
+  module Ucsc
+    module Hg19
+      class Snp132Mult < DBConnection
+        extend Bio::Ucsc::Hg19::QueryUsingChromBin
+        set_table_name 'snp132Mult'
+        set_primary_key nil
+        columns_hash.delete("valid")
+        columns_hash.delete("class")
+      end
+    end
+  end
+end

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

@@ -0,0 +1,29 @@
+#
+# = hg19/wbrna.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 positions of four different types of RNA in the
+# human genome:
+#  * precursor forms of microRNAs (pre-miRNAs) C/D box small
+#  * nucleolar RNAs (C/D box snoRNAs) H/ACA box snoRNAs small Cajal
+#  * body-specific RNAs (scaRNAs)
+#
+# = ommitted dynamic method(s) due to the method name collision
+#  use results[:type] instead of results.type
+
+module Bio
+  module Ucsc
+    module Hg19
+      class WgRna < DBConnection
+        extend  Bio::Ucsc::Hg19::QueryUsingChromBin
+        set_table_name 'wgRna'
+        set_primary_key nil
+        columns_hash.delete("type")
+      end
+    end
+  end
+end

data/lib/bio-ucsc/ucsc_bin.rb

@@ -0,0 +1,148 @@
+# = UCSCBin
+# Author::    MISHIMA, Hiroyuki
+# Copyright:: MISHIMA, Hiroyuki, 2010-2011
+# License::   The Ruby licence (Ryby's / GPLv2 dual)
+#
+# Original program in C by Jim Kent, 2002
+# See also http://genomewiki.ucsc.edu/index.php/Bin_indexing_system;
+# a paper Kent, et. al. Genome Research 2002.12:996-1006;
+# and src/lib/binRange.c in the kent source tree.
+#
+# Bio::Ucsc::UcscBin - 
+# 1) convert between 0-based half-open interval and
+#    1-based full-close intervals.
+# 2) Calculate Bin number from genomic physical position
+# according to UCSC's Bin Indexing System. 
+#
+module Bio
+  module Ucsc
+    class UcscBin
+      # Version = "0.1.0" # 20100714
+      # Version = "0.2.0" # 20101028
+      # Version = "0.2.1" # 20110408
+      Version = "0.2.2" # 20110418 the licence is changed 
+                        # embeded in BioRubyUcscApi
+                        # handle the case, start==end in [start, end) 
+
+      # 'zero_start' and 'zero_end' are 0-based half-open
+      # used in UCSC MySQL database and the BED format.
+      # the first one base in a chromosome is [0, 1)
+      # OLD: Positions must be start<end
+      # New: Positions can be start<=end (e.g. positions for insersions)
+
+      def self.zero_to_one(zero_start, zero_end)
+        case
+        when (zero_start < 0 || zero_end < 0) 
+          raise ArgumentError, "positions must be >=0"
+        when zero_start > zero_end
+          raise ArgumentError, "positions must be start<=end"
+        when zero_start == zero_end
+          [zero_start + 1, zero_end + 1]
+        else
+          [zero_start + 1, zero_end]
+        end
+      end
+
+      # 'one_start' and 'one_end' are 1-based full-close
+      # used in UCSC genome browser's human interface and most of other formats
+      # the first one base in a chromosome is [1, 1]
+      # Positions must be start<=end
+      def self.one_to_zero(one_start, one_end)
+        case
+        when (one_start < 1 || one_end < 1) 
+          raise ArgumentError, "positions must be >=1"
+        when one_start > one_end
+          raise ArgumentError, "positions must be start<=end"
+        end
+        [one_start - 1 , one_end]
+      end
+      
+      BINRANGE_MAXEND_512M       = (512*1024*1024)
+      BIN_OFFSETS_EXTENDED       = [4096+512+64+8+1, 512+64+8+1, 64+8+1, 8+1, 1, 0]
+      BIN_OFFSETS                = [512+64+8+1, 64+8+1, 8+1, 1, 0]
+      BIN_OFFSET_OLD_TO_EXTENDED = 4681
+      # How much to shift to get to finest bin.
+      BIN_FIRST_SHIFT            = 17 
+      # How much to shift to get to next larger bin.
+      BIN_NEXT_SHIFT             = 3 
+
+      # Return a Integer of a BIN which is the smallest/finest bin 
+      # containing whole the interval/range.
+      # 
+      # Extended bin index for positions >= 512M is not supported yet
+      # Do you need it? Please email me.
+      def self.bin_from_range(bin_start, bin_end)
+        if bin_end <= BINRANGE_MAXEND_512M
+          bin_from_range_standard(bin_start, bin_end)
+        else
+          bin_from_range_extended(bin_start, bin_end)
+        end
+      end
+      
+      class << self;  alias bin bin_from_range; end
+
+      # Return an Array of BINs which are all bins containing whole the
+      # interval/range. Thus, it always contains "0" indicating a bin
+      # containing whole of a chromosome.
+      # 
+      # extended bin index for positions >= 512M is not supported yet
+      # Do you need it? Please email me.
+      #
+      def self.bin_all(p_start, p_end)
+        if p_end <= BINRANGE_MAXEND_512M
+          bin_all_standard(p_start, p_end)
+        else
+          bin_all_extended(p_start, p_end)
+        end
+      end
+
+      private
+
+      def self.bin_from_range_standard(bin_start, bin_end)
+        # Given start,end in chromosome coordinates assign it
+        # a bin.   There's a bin for each 128k segment, for each
+        # 1M segment, for each 8M segment, for each 64M segment,
+        # and for each chromosome (which is assumed to be less than
+        # 512M.)  A range goes into the smallest bin it will fit in.
+
+        bin_start >>= BIN_FIRST_SHIFT
+        bin_end -= 1
+        bin_end >>= BIN_FIRST_SHIFT
+
+        BIN_OFFSETS.each do |offset|
+          return offset + bin_start if bin_start == bin_end
+          bin_start >>= BIN_NEXT_SHIFT
+          bin_end   >>= BIN_NEXT_SHIFT
+        end
+        raise RangeError, \
+        "start #{bin_start}, end #{bin_end} out of range in findBin (max is 512M)"
+      end
+
+      def self.bin_from_range_extended(bin_start, bin_end)
+        raise NotImplementedError, "Extended bins are not supported yet"
+      end
+
+      def self.bin_all_standard(bin_start, bin_end)
+        bin_start_orig = bin_start
+        bin_end_orig   = bin_end 
+        results = Array.new
+        
+        bin_start >>= BIN_FIRST_SHIFT
+        bin_end -= 1
+        bin_end >>= BIN_FIRST_SHIFT
+
+        BIN_OFFSETS.each do |offset|
+          results.concat(((offset + bin_start)..(offset + bin_end)).to_a)
+          bin_start >>= BIN_NEXT_SHIFT
+          bin_end   >>= BIN_NEXT_SHIFT
+        end
+        return results
+      end
+      
+      def self.bin_all_extended(bin_start, bin_end)
+        raise NotImplementedError, "Extended bins are not supported yet"
+      end
+
+    end # class UcscBin
+  end # module Ucsc
+end # module Bio 

data/samples/hg19-sample.rb

@@ -0,0 +1,66 @@
+#!/usr/local/bin/ruby-1.9
+#
+# Copyright::
+#   Copyright (C) 2011 MISHIMA, Hiroyuki
+#                      <missy at be.to / hmishima at nagasaki-u.ac.jp>
+# License::     The Ruby licence (Ryby's / GPLv2 dual)
+#
+
+require File.dirname(__FILE__) + '/../lib/bio-ucsc'
+
+include Bio::Ucsc
+
+Hg19::DBConnection.default
+Hg19::DBConnection.connect
+
+itvs_a =
+  [Bio::GenomicInterval.parse("chr1:1-200,000"),
+   Bio::GenomicInterval.parse("chr2:1-200,000"),
+   Bio::GenomicInterval.parse("chr3:1-300,000"),
+  ]
+
+puts
+puts "Queries in Slice objects using 1-based [start,end] closed intervals"
+puts "Results in 0-based [start,end) half-open intervals"
+puts
+
+::puts "test 1 (hg19/RefGene) --- Bio::Ucsc::Hg19::RefGene.find_by_interval"
+results = itvs_a.map{|i|Hg19::RefGene.find_by_interval(i)}
+puts "0-based interval\t1-based interval\tGene Symbol"
+results.flatten.each do |e|
+  i = Bio::GenomicInterval.zero_based(e.chrom, e.txStart, e.txEnd)
+  print "#{e.chrom}:#{e.txStart}-#{e.txEnd}\t"
+  print "#{i.chrom}:#{i.chr_start}-#{i.chr_end}\t#{e.name2}\n"
+end
+
+#
+#
+
+itvs_b =
+  [Bio::GenomicInterval.parse("chr1:1-11,000"),
+   Bio::GenomicInterval.parse("chr2:1-11,000"),
+   Bio::GenomicInterval.parse("chr3:1-12,000"),
+  ]
+
+puts
+puts "test 2 (hg19/Snp131) --- Bio::Ucsc::Hg19::Snp131.find_by_interval" 
+puts "0-based interval\t1-based interval\tdbSNP rs ID\tClass"
+results = itvs_b.map{|i|Hg19::Snp131.find_by_interval(i)}
+results.flatten.each do |e|
+  i = Bio::GenomicInterval.zero_based(e.chrom, e.chromStart, e.chromEnd)
+  print "#{e.chrom}:#{e.chromStart}-#{e.chromEnd}\t"
+  print "#{i.chrom}:#{i.chr_start}-#{i.chr_end}\t#{e.name}\t#{e[:class]}\n"
+end
+
+#
+#
+
+names = %w(rs56289060 rs62636508 rs28888107)
+
+puts
+puts "test 3 (hg19/Snp131) ---Bio::Ucsc::Hg19::Snp131.find_by_name"
+names.each do |n|
+  r =  Hg19::Snp131.find_by_name(n)
+  i = Bio::GenomicInterval.zero_based(r.chrom, r.chromStart, r.chromEnd)
+  puts "Query: #{n}\t#{i.chrom}\t#{i.chr_start}\t#{i.chr_end}\t#{r[:class]}"
+end

data/spec/hg18/cnpiafrate2_spec.rb

@@ -0,0 +1,23 @@
+require 'bio-ucsc'
+describe "Bio::Ucsc::Hg18::CnpIafrate2" do 
+
+  describe "#find_by_inetrval" do
+    context "given range chr1:1-2,000,000" do
+      it "returens an array of results" do
+        Bio::Ucsc::Hg18::DBConnection.default
+        Bio::Ucsc::Hg18::DBConnection.connect
+        i = Bio::GenomicInterval.parse("chr1:1-2,000,000")
+        Bio::Ucsc::Hg18::CnpIafrate2.find_by_interval(i).should have(2).items
+      end
+
+      it "returens an array of results with column accessors" do
+        Bio::Ucsc::Hg18::DBConnection.default
+        Bio::Ucsc::Hg18::DBConnection.connect
+        i = Bio::GenomicInterval.parse("chr1:1-2,000,000")
+        r = Bio::Ucsc::Hg18::CnpIafrate2.find_by_interval(i)
+        r[0].chrom.should == "chr1"
+      end
+    end
+  end
+
+end

data/spec/hg18/cnplocke_spec.rb

@@ -0,0 +1,23 @@
+require 'bio-ucsc'
+describe "Bio::Ucsc::Hg18::CnpLocke" do 
+
+  describe "#find_by_interval" do
+    context "given range chr1:1-2,000,000" do
+      it "returens an array of results" do
+        Bio::Ucsc::Hg18::DBConnection.default
+        Bio::Ucsc::Hg18::DBConnection.connect
+        i = Bio::GenomicInterval.parse("chr1:1-2,000,000")
+        Bio::Ucsc::Hg18::CnpLocke.find_by_interval(i).should have(2).items
+      end
+
+      it "returens an array of results with column accessors" do
+        Bio::Ucsc::Hg18::DBConnection.default
+        Bio::Ucsc::Hg18::DBConnection.connect
+        i = Bio::GenomicInterval.parse("chr1:1-2,000,000")
+        r = Bio::Ucsc::Hg18::CnpLocke.find_by_interval(i)
+        r[0].chrom.should == "chr1"
+      end
+    end
+  end
+
+end

data/spec/hg18/cnpredon_spec.rb

@@ -0,0 +1,23 @@
+require 'bio-ucsc'
+describe "Bio::Ucsc::Hg18::CnpRedon" do 
+
+  describe "#find_by_interval" do
+    context "given range chr1:1-2,000,000" do
+      it "returns an array of results" do
+        Bio::Ucsc::Hg18::DBConnection.default
+        Bio::Ucsc::Hg18::DBConnection.connect
+        i = Bio::GenomicInterval.parse("chr1:1-2,000,000")
+        Bio::Ucsc::Hg18::CnpRedon.find_by_interval(i).should have(3).items
+      end
+
+      it "returns an array of results with column accessors" do
+        Bio::Ucsc::Hg18::DBConnection.default
+        Bio::Ucsc::Hg18::DBConnection.connect
+        i = Bio::GenomicInterval.parse("chr1:1-2,000,000")
+        r = Bio::Ucsc::Hg18::CnpRedon.find_by_interval(i)
+        r[0].chrom.should == "chr1"
+      end
+    end
+  end
+
+end