mspire 0.2.4 → 0.3.0

data/test_files/yeast_gly_small2.parentTimes

@@ -0,0 +1,6 @@
+# PROTCUTOFF: 1.0 NSPPEPCUTOFF: 1.0 INITPEPCUTOFF: 1.0
+# These are the times of the precursor scan!
+# filename sequence charge time1 prec_mz prec_int time2 ...
+020a EVIDTILALVK 2 5575.870000 610.063965 4030201.000000 5537.900000 615.687988 9531986.000000
+020a TPANAAVPASTPLK 2 1037.230000 669.406616 6435475.000000 1030.090000 672.593262 5464264.000000
+020a YVRPPIIVGDLSR 3 2772.160000 498.767334 3464513.000000 2755.730000 493.924683 2817155.000000

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.9.2
 specification_version: 1
 name: mspire
 version: !ruby/object:Gem::Version 
-  version: 0.2.4
-date: 2007-05-17 00:00:00 -05:00
+  version: 0.3.0
+date: 2007-12-13 00:00:00 -06:00
 summary: Mass Spectrometry Proteomics Objects, Scripts, and Executables
 require_paths: 
 - lib
@@ -29,43 +29,105 @@ post_install_message:
 authors: 
 - John Prince
 files: 
+- INSTALL
+- README
+- Rakefile
+- LICENSE
+- changelog.txt
+- release_notes.txt
 - lib/spec_id
 - lib/align
-- lib/spec
+- lib/ms
 - lib/spec_id.rb
 - lib/fasta.rb
 - lib/align.rb
 - lib/sample_enzyme.rb
+- lib/ms.rb
 - lib/gi.rb
 - lib/roc.rb
 - lib/spec_id_xml.rb
-- lib/toppred.rb
+- lib/validator.rb
+- lib/transmem
+- lib/transmem.rb
+- lib/xml_style_parser.rb
+- lib/xmlparser_wrapper.rb
+- lib/bsearch.rb
+- lib/group_by.rb
+- lib/xml.rb
+- lib/merge_deep.rb
+- lib/index_by.rb
+- lib/validator
+- lib/mspire.rb
+- lib/scan_i.rb
 - lib/spec_id/sequest.rb
 - lib/spec_id/bioworks.rb
 - lib/spec_id/proph.rb
-- lib/spec_id/precision.rb
+- lib/spec_id/parser
 - lib/spec_id/srf.rb
 - lib/spec_id/aa_freqs.rb
 - lib/spec_id/protein_summary.rb
-- lib/spec_id/filter.rb
+- lib/spec_id/precision
+- lib/spec_id/digestor.rb
+- lib/spec_id/proph
+- lib/spec_id/sequest
+- lib/spec_id/mass.rb
+- lib/spec_id/parser/proph.rb
+- lib/spec_id/precision/prob.rb
+- lib/spec_id/precision/filter
+- lib/spec_id/precision/filter.rb
+- lib/spec_id/precision/prob
+- lib/spec_id/precision/output.rb
+- lib/spec_id/precision/filter/interactive.rb
+- lib/spec_id/precision/filter/output.rb
+- lib/spec_id/precision/filter/cmdline.rb
+- lib/spec_id/precision/prob/output.rb
+- lib/spec_id/precision/prob/cmdline.rb
+- lib/spec_id/proph/pep_summary.rb
+- lib/spec_id/proph/prot_summary.rb
+- lib/spec_id/sequest/params.rb
+- lib/spec_id/sequest/pepxml.rb
 - lib/align/chams.rb
-- lib/spec/mzxml
-- lib/spec/mzdata
-- lib/spec/msrun.rb
-- lib/spec/scan.rb
-- lib/spec/mzxml.rb
-- lib/spec/mzdata.rb
-- lib/spec/mzxml/parser.rb
-- lib/spec/mzdata/parser.rb
-- INSTALL
-- README
-- Rakefile
-- LICENSE
-- changelog.txt
-- release_notes.txt
+- lib/ms/converter
+- lib/ms/parser
+- lib/ms/spectrum.rb
+- lib/ms/gradient_program.rb
+- lib/ms/msrun.rb
+- lib/ms/precursor.rb
+- lib/ms/scan.rb
+- lib/ms/msrun_index.rb
+- lib/ms/parser.rb
+- lib/ms/converter/mzxml.rb
+- lib/ms/parser/mzdata
+- lib/ms/parser/mzxml
+- lib/ms/parser/mzdata.rb
+- lib/ms/parser/mzxml.rb
+- lib/ms/parser/mzdata/libxml.rb
+- lib/ms/parser/mzdata/axml.rb
+- lib/ms/parser/mzdata/dom.rb
+- lib/ms/parser/mzxml/xmlparser.rb
+- lib/ms/parser/mzxml/libxml.rb
+- lib/ms/parser/mzxml/rexml.rb
+- lib/ms/parser/mzxml/regexp.rb
+- lib/ms/parser/mzxml/axml.rb
+- lib/ms/parser/mzxml/hpricot.rb
+- lib/ms/parser/mzxml/dom.rb
+- lib/transmem/toppred.rb
+- lib/transmem/phobius.rb
+- lib/validator/prot_from_pep.rb
+- lib/validator/true_pos.rb
+- lib/validator/aa.rb
+- lib/validator/decoy.rb
+- lib/validator/transmem.rb
+- lib/validator/cmdline.rb
+- lib/validator/bias.rb
+- lib/validator/background.rb
+- lib/validator/digestion_based.rb
+- lib/validator/probability.rb
 - bin/bioworks_to_pepxml_gui.rb
 - bin/gi2annot.rb
 - bin/protein_summary.rb
+- bin/ms_to_lmat.rb
+- bin/aafreqs.rb
 - bin/bioworks2excel.rb
 - bin/pepproph_filter.rb
 - bin/fasta_shaker.rb
@@ -73,11 +135,10 @@ files:
 - bin/protxml2prots_peps.rb
 - bin/id_precision.rb
 - bin/id_class_anal.rb
-- bin/mzxml_to_lmat.rb
-- bin/find_aa_freq.rb
-- bin/filter.rb
+- bin/prob_validate.rb
+- bin/srf_to_sqt.rb
+- bin/filter_and_validate.rb
 - bin/srf_group.rb
-- bin/precision.rb
 - bin/raw_to_mzXML.rb
 - script/create_little_pepxml.rb
 - script/mzXML2timeIndex.rb
@@ -86,39 +147,184 @@ files:
 - script/histogram_probs.rb
 - script/prep_dir.rb
 - script/top_hit_per_scan.rb
-- script/filter-peps.rb
 - script/genuine_tps_and_probs.rb
+- script/compile_and_plot_smriti_final.rb
 - script/simple_protein_digestion.rb
 - script/estimate_fpr_by_cysteine.rb
 - script/find_cysteine_background.rb
 - script/degenerate_peptides.rb
+- script/smriti_final_analysis.rb
+- script/toppred_to_yaml.rb
+- script/get_apex_values_rexml.rb
+- script/extract_gradient_programs.rb
+- specs/transmem_spec.rb
+- specs/roc_spec.rb
+- specs/ms
+- specs/load_bin_path.rb
+- specs/validator
+- specs/spec_helper.rb
+- specs/transmem
+- specs/spec_id
+- specs/spec_id_helper.rb
+- specs/fasta_spec.rb
+- specs/gi_spec.rb
+- specs/bin
+- specs/validator_helper.rb
+- specs/merge_deep_spec.rb
+- specs/xml_spec.rb
+- specs/spec_id_spec.rb
+- specs/align_spec.rb
+- specs/rspec_autotest.rb
+- specs/sample_enzyme_spec.rb
+- specs/spec_id_xml_spec.rb
+- specs/transmem_spec_shared.rb
+- specs/ms/gradient_program_spec.rb
+- specs/ms/msrun_spec.rb
+- specs/ms/parser_spec.rb
+- specs/ms/spectrum_spec.rb
+- specs/validator/background_spec.rb
+- specs/validator/decoy_spec.rb
+- specs/validator/transmem_spec.rb
+- specs/validator/true_pos_spec.rb
+- specs/validator/prot_from_pep_spec.rb
+- specs/validator/aa_spec.rb
+- specs/validator/fasta_helper.rb
+- specs/validator/bias_spec.rb
+- specs/transmem/toppred_spec.rb
+- specs/transmem/phobius_spec.rb
+- specs/spec_id/bioworks_spec.rb
+- specs/spec_id/aa_freqs_spec.rb
+- specs/spec_id/srf_spec.rb
+- specs/spec_id/precision
+- specs/spec_id/srf_spec_helper.rb
+- specs/spec_id/sequest
+- specs/spec_id/digestor_spec.rb
+- specs/spec_id/protein_summary_spec.rb
+- specs/spec_id/proph
+- specs/spec_id/sqt_spec.rb
+- specs/spec_id/precision/filter
+- specs/spec_id/precision/prob_spec.rb
+- specs/spec_id/precision/filter_spec.rb
+- specs/spec_id/precision/prob_spec_helper.rb
+- specs/spec_id/precision/filter/cmdline_spec.rb
+- specs/spec_id/precision/filter/output_spec.rb
+- specs/spec_id/sequest/params_spec.rb
+- specs/spec_id/sequest/pepxml_spec.rb
+- specs/spec_id/proph/prot_summary_spec.rb
+- specs/spec_id/proph/pep_summary_spec.rb
+- specs/bin/filter_and_validate_spec.rb
+- specs/bin/fasta_shaker_spec.rb
+- specs/bin/bioworks_to_pepxml_spec.rb
+- specs/bin/protein_summary_spec.rb
+- specs/bin/ms_to_lmat_spec.rb
+- specs/bin/filter_and_validate__multiple_vals_helper.yaml
+- specs/bin/prob_validate_spec.rb
+- test_files/4-03-03_mzXML
+- test_files/opd1
+- test_files/orbitrap_mzData
+- test_files/messups.fasta
+- test_files/small.fasta
+- test_files/toppred.xml.out
+- test_files/smallraw.RAW
+- test_files/bioworks_single_run_small.xml
+- test_files/tf_bioworks2excel.txt.actual
+- test_files/pepproph_small.xml
+- test_files/000_pepxml18_small.xml
+- test_files/tf_bioworks2excel.bioXML
+- test_files/bioworks31.params
+- test_files/bioworks_small.xml
+- test_files/bioworks32.params
+- test_files/yeast_gly_small.xml
+- test_files/4-03-03_small.xml
+- test_files/bioworks_with_INV_small.xml
+- test_files/020a.mzXML.timeIndex
+- test_files/yeast_gly_small2.parentTimes
+- test_files/s01_anC1_ld020mM.meth
+- test_files/yeast_gly_small-prot.xml
+- test_files/bioworks-3.3_10prots.xml
+- test_files/4-03-03_small-prot.xml
+- test_files/bioworks33.params
+- test_files/head_of_7MIX.srf
+- test_files/yeast_gly_small.1.0_1.0_1.0.parentTimes
+- test_files/bioworks_with_SHUFF_small.xml
+- test_files/toppred.small.out
+- test_files/phobius.small.small.txt
+- test_files/s01_anC1_ld020mM.key.txt
+- test_files/7MIX_STD_110802_1.sequest_params_fragment.srf
+- test_files/phobius.small.noheader.txt
+- test_files/interact-opd1_mods_small-prot.xml
+- test_files/corrupted_900.srf
+- test_files/validator_hits_separate
+- test_files/bioworks_small.phobius
+- test_files/bioworks_small.params
+- test_files/bioworks_small.toppred.out
+- test_files/bioworks_small.fasta
+- test_files/opd1_020_beginning.RAW
+- test_files/opd1_2runs_2mods
+- test_files/4-03-03_mzXML/000.mzXML.timeIndex
+- test_files/4-03-03_mzXML/020.mzXML.timeIndex
+- test_files/opd1/opd1_cat_inv_small-prot.xml
+- test_files/opd1/000.v2.1.mzXML.timeIndex
+- test_files/opd1/000.tpp_2.9.2.first10.xml
+- test_files/opd1/000_020-prot.png
+- test_files/opd1/twenty_scans.mzXML
+- test_files/opd1/000.my_answer.100lines.xml
+- test_files/opd1/twenty_scans_answ.lmat
+- test_files/opd1/twenty_scans_answ.lmata
+- test_files/opd1/000.tpp_1.2.3.first10.xml
+- test_files/opd1/sequest.3.1.params
+- test_files/opd1/000_020_3prots-prot.xml
+- test_files/opd1/twenty_scans.v2.1.mzXML
+- test_files/opd1/sequest.3.2.params
+- test_files/opd1/000_020_3prots-prot.mod_initprob.xml
+- test_files/orbitrap_mzData/000_cut.xml
+- test_files/validator_hits_separate/bioworks_small_HS.xml
+- test_files/validator_hits_separate/bias_bioworks_small_HS.fasta
+- test_files/opd1_2runs_2mods/interact-opd1_mods__small.xml
 test_files: 
-- test/tc_aa_freqs.rb
-- test/tc_proph.rb
-- test/tc_gi.rb
-- test/tc_align.rb
-- test/tc_sequest.rb
-- test/tc_spec.rb
-- test/tc_bioworks.rb
-- test/tc_protein_summary.rb
-- test/tc_fasta.rb
-- test/tc_msrun.rb
-- test/tc_peptide_parent_times.rb
-- test/tc_spec_id.rb
-- test/tc_mzxml.rb
-- test/tc_srf.rb
-- test/tc_id_precision.rb
-- test/tc_id_class_anal.rb
-- test/tc_filter_peps.rb
-- test/tc_precision.rb
-- test/tc_filter.rb
-- test/tc_roc.rb
-- test/tc_scan.rb
-- test/tc_bioworks_to_pepxml.rb
-- test/tc_mzxml_to_lmat.rb
-- test/tc_fasta_shaker.rb
-- test/tc_sample_enzyme.rb
-- test/tc_spec_id_xml.rb
+- specs/transmem_spec.rb
+- specs/roc_spec.rb
+- specs/fasta_spec.rb
+- specs/gi_spec.rb
+- specs/merge_deep_spec.rb
+- specs/xml_spec.rb
+- specs/spec_id_spec.rb
+- specs/align_spec.rb
+- specs/sample_enzyme_spec.rb
+- specs/spec_id_xml_spec.rb
+- specs/ms/gradient_program_spec.rb
+- specs/ms/msrun_spec.rb
+- specs/ms/parser_spec.rb
+- specs/ms/spectrum_spec.rb
+- specs/validator/background_spec.rb
+- specs/validator/decoy_spec.rb
+- specs/validator/transmem_spec.rb
+- specs/validator/true_pos_spec.rb
+- specs/validator/prot_from_pep_spec.rb
+- specs/validator/aa_spec.rb
+- specs/validator/bias_spec.rb
+- specs/transmem/toppred_spec.rb
+- specs/transmem/phobius_spec.rb
+- specs/spec_id/bioworks_spec.rb
+- specs/spec_id/aa_freqs_spec.rb
+- specs/spec_id/srf_spec.rb
+- specs/spec_id/digestor_spec.rb
+- specs/spec_id/protein_summary_spec.rb
+- specs/spec_id/sqt_spec.rb
+- specs/spec_id/precision/prob_spec.rb
+- specs/spec_id/precision/filter_spec.rb
+- specs/spec_id/precision/filter/cmdline_spec.rb
+- specs/spec_id/precision/filter/output_spec.rb
+- specs/spec_id/sequest/params_spec.rb
+- specs/spec_id/sequest/pepxml_spec.rb
+- specs/spec_id/proph/prot_summary_spec.rb
+- specs/spec_id/proph/pep_summary_spec.rb
+- specs/bin/filter_and_validate_spec.rb
+- specs/bin/fasta_shaker_spec.rb
+- specs/bin/bioworks_to_pepxml_spec.rb
+- specs/bin/protein_summary_spec.rb
+- specs/bin/ms_to_lmat_spec.rb
+- specs/bin/prob_validate_spec.rb
 rdoc_options: 
 - --main
 - README
@@ -132,6 +338,8 @@ executables:
 - bioworks_to_pepxml_gui.rb
 - gi2annot.rb
 - protein_summary.rb
+- ms_to_lmat.rb
+- aafreqs.rb
 - bioworks2excel.rb
 - pepproph_filter.rb
 - fasta_shaker.rb
@@ -139,16 +347,15 @@ executables:
 - protxml2prots_peps.rb
 - id_precision.rb
 - id_class_anal.rb
-- mzxml_to_lmat.rb
-- find_aa_freq.rb
-- filter.rb
+- prob_validate.rb
+- srf_to_sqt.rb
+- filter_and_validate.rb
 - srf_group.rb
-- precision.rb
 - raw_to_mzXML.rb
 extensions: []
 
 requirements: 
-- "\"xmlparser\" is the prefered xml parser right now.  REXML and regular expressions are used as fallback in some routines."
+- "\"libxml\" is the prefered xml parser right now.  libxml, xmlparser, REXML and regular expressions are used as fallback in some routines."
 - some plotting functions will not be available without the "gnuplot" gem (and underlying gnuplot binary)
 - the "t2x" binary (in archive) or readw.exe is required to convert .RAW files to mzXML in some applications
 - "\"rake\" is useful for development"
@@ -161,5 +368,14 @@ dependencies:
     requirements: 
     - - ~>
       - !ruby/object:Gem::Version 
-        version: 0.1.4
+        version: 0.2.5
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: axml
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Version::Requirement 
+    requirements: 
+    - - ">"
+      - !ruby/object:Gem::Version 
+        version: 0.0.0
     version: 

data/bin/filter.rb

@@ -1,6 +0,0 @@
-#!/usr/bin/ruby -w
-
-
-require 'spec_id/filter'
-
-SpecID::Filter.run_from_argv(ARGV)

data/bin/precision.rb

@@ -1,5 +0,0 @@
-#!/usr/bin/ruby
-
-require 'spec_id'
-
-SpecID.precision(ARGV)

data/lib/spec/mzdata/parser.rb

@@ -1,108 +0,0 @@
-require 'spec/msrun'
-require 'spec/mzdata'
-
-begin
-  require 'xmlparser'
-rescue LoadError
-  puts "*******************************************************************"
-  puts "WARNING: 'xmlparser' library not installed:"
-  puts "Defaulting to REXML (slower, but guaranteed to parse correct xml)"
-  puts "Use :parse_type => 'regex' for faster (but not guaranteed) parsing"
-  puts "Or install 'xmlparser'!"
-  puts "*******************************************************************"
-end
-begin 
-  $XMLParserClass = XMLParser
-rescue NameError
-  $XMLParserClass = Object
-end
-
-
-module Spec::MzData::PrecMzByNum; end
-module Spec::MzData::XMLParser; end
-
-
-class Spec::MzData::XMLParser::PrecMzByNum < $XMLParserClass
-
-## This is an example from mzXML
-=begin
-  @@scan_num = nil
-  @@get_data = false
-
-  attr_accessor :prec_mz
-  def initialize
-    @prec_mz = [] 
-  end
-
-  def startElement(name,attrs)
-    if name == "scan"
-      @@scan_num = attrs["num"].to_i
-    elsif name == "precursorMz"
-      @prec_mz[@@scan_num] = ""
-      @@get_data = true
-    end
-  end
-
-  def endElement(name)
-    if name == "precursorMz"
-      @@get_data = false
-    end
-  end
-
-  def character(data)
-    if @@get_data
-      @prec_mz[@@scan_num] << data
-    end
-  end
-=end
-
-end
-
-
-class Spec::MzData::Parser
-
-  def default_parser
-    xmlparser = false 
-    $".each do |lib|
-      if lib =~ /xmlparser/
-        xmlparser = true
-      end
-    end
-    if xmlparser
-      return "xmlparser"
-    else
-      return "rexml"
-    end
-  end
-
-
-  # Returns array where array[scan_num] = precursorMz
-  # Parent scans are not arrayed
-  # Values are strings.  Array index likely starts at 1!
-  # parse_type = "regex" | "rexml" | "xmlparser"
-  # (only xmlparser works for now!)
-  def precursor_mz_by_scan(file, parse_type=nil)
-    puts "NO PARSERS AVAIALABLE YET!!"
-    throw Exception
-#    unless parse_type then parse_type = default_parser end
-#    case parse_type
-#    when "xmlparser"
-#      ##XMLParser:
-#      parser = Spec::MzData::XMLParser::PrecMzByNum.new
-#      File.open(file) do |fh|
-#        parser.parse(fh.read)
-#      end
-#      parser.prec_mz
-#    when "regex"
-#      Spec::MzData::Regexp.precursor_mz_by_scan(file)
-#    when "rexml"
-#      listener = Spec::MzData::REXMLStreamListener::PrecMzByNum.new
-#      REXML::Document.parse_stream(File.new(file), listener)
-#      listener.prec_mz
-#    else
-#      puts "Don't recognize parse_type: #{parse_type}"
-#    end
-  end
-
-
-end

data/lib/spec/mzdata.rb

@@ -1,48 +0,0 @@
-
-#######################################################
-# THIS NEEDS TO BE WORKED FOR mzdata!
-#######################################################
-
-require 'base64'
-
-module Spec; end
-
-module Spec::MzData
-
-  ####################
-  # THIS IS FOR mzXML right now!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
-  ####################
-  # takes a base64 peaks string and returns an array of [m/z,intens] doublets
-  # mzXML as network ordered
-  def base64_peaks_to_pairs(string, precision=32)
-    data = base64_peaks_to_array(string, precision)
-    ndata = []
-    data.each_with_index do |dat,ind|
-      if (ind % 2) == 0  # even
-        arr = Array.new(2)
-        arr[0] = dat
-        ndata.push( arr )
-      else
-        ndata.last[1] = dat 
-      end
-    end
-    ndata
-  end
-
-  ####################
-  # THIS IS FOR mzXML right now!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
-  ####################
-  # takes a base64 peaks string and returns an array of alternating m/z and
-  # intensity mzXML as network ordered
-  def base64_peaks_to_array(string, precision=32)
-    b64d = Base64.decode64(string) 
-    if precision == 32
-      unpack_code = "g*"
-    elsif precision == 64
-      unpack_code = "G*"
-    end
-    b64d.unpack(unpack_code)
-  end
-
- 
-end