RubyGems - mspire - Versions diffs - 0.2.4 → 0.3.0 - Mend

mspire 0.2.4 → 0.3.0

Files changed (233) hide show

data/INSTALL +1 -0
data/README +25 -0
data/Rakefile +129 -40
data/bin/{find_aa_freq.rb → aafreqs.rb} +2 -2
data/bin/bioworks_to_pepxml.rb +1 -0
data/bin/fasta_shaker.rb +1 -96
data/bin/filter_and_validate.rb +5 -0
data/bin/{mzxml_to_lmat.rb → ms_to_lmat.rb} +8 -7
data/bin/prob_validate.rb +6 -0
data/bin/raw_to_mzXML.rb +2 -2
data/bin/srf_group.rb +1 -0
data/bin/srf_to_sqt.rb +40 -0
data/changelog.txt +68 -0
data/lib/align/chams.rb +6 -6
data/lib/align.rb +4 -3
data/lib/bsearch.rb +120 -0
data/lib/fasta.rb +318 -86
data/lib/group_by.rb +10 -0
data/lib/index_by.rb +11 -0
data/lib/merge_deep.rb +21 -0
data/lib/{spec → ms/converter}/mzxml.rb +77 -109
data/lib/ms/gradient_program.rb +171 -0
data/lib/ms/msrun.rb +209 -0
data/lib/{spec/msrun.rb → ms/msrun_index.rb} +7 -40
data/lib/ms/parser/mzdata/axml.rb +12 -0
data/lib/ms/parser/mzdata/dom.rb +160 -0
data/lib/ms/parser/mzdata/libxml.rb +7 -0
data/lib/ms/parser/mzdata.rb +25 -0
data/lib/ms/parser/mzxml/axml.rb +11 -0
data/lib/ms/parser/mzxml/dom.rb +159 -0
data/lib/ms/parser/mzxml/hpricot.rb +253 -0
data/lib/ms/parser/mzxml/libxml.rb +15 -0
data/lib/ms/parser/mzxml/regexp.rb +122 -0
data/lib/ms/parser/mzxml/rexml.rb +72 -0
data/lib/ms/parser/mzxml/xmlparser.rb +248 -0
data/lib/ms/parser/mzxml.rb +175 -0
data/lib/ms/parser.rb +108 -0
data/lib/ms/precursor.rb +10 -0
data/lib/ms/scan.rb +81 -0
data/lib/ms/spectrum.rb +193 -0
data/lib/ms.rb +10 -0
data/lib/mspire.rb +4 -0
data/lib/roc.rb +61 -1
data/lib/sample_enzyme.rb +31 -8
data/lib/scan_i.rb +21 -0
data/lib/spec_id/aa_freqs.rb +7 -3
data/lib/spec_id/bioworks.rb +20 -14
data/lib/spec_id/digestor.rb +139 -0
data/lib/spec_id/mass.rb +116 -0
data/lib/spec_id/parser/proph.rb +236 -0
data/lib/spec_id/precision/filter/cmdline.rb +209 -0
data/lib/spec_id/precision/filter/interactive.rb +134 -0
data/lib/spec_id/precision/filter/output.rb +147 -0
data/lib/spec_id/precision/filter.rb +623 -0
data/lib/spec_id/precision/output.rb +60 -0
data/lib/spec_id/precision/prob/cmdline.rb +139 -0
data/lib/spec_id/precision/prob/output.rb +88 -0
data/lib/spec_id/precision/prob.rb +171 -0
data/lib/spec_id/proph/pep_summary.rb +92 -0
data/lib/spec_id/proph/prot_summary.rb +484 -0
data/lib/spec_id/proph.rb +2 -466
data/lib/spec_id/protein_summary.rb +2 -2
data/lib/spec_id/sequest/params.rb +316 -0
data/lib/spec_id/sequest/pepxml.rb +1513 -0
data/lib/spec_id/sequest.rb +2 -1672
data/lib/spec_id/srf.rb +445 -177
data/lib/spec_id.rb +183 -95
data/lib/spec_id_xml.rb +8 -10
data/lib/transmem/phobius.rb +147 -0
data/lib/transmem/toppred.rb +368 -0
data/lib/transmem.rb +157 -0
data/lib/validator/aa.rb +135 -0
data/lib/validator/background.rb +73 -0
data/lib/validator/bias.rb +95 -0
data/lib/validator/cmdline.rb +260 -0
data/lib/validator/decoy.rb +94 -0
data/lib/validator/digestion_based.rb +69 -0
data/lib/validator/probability.rb +48 -0
data/lib/validator/prot_from_pep.rb +234 -0
data/lib/validator/transmem.rb +272 -0
data/lib/validator/true_pos.rb +46 -0
data/lib/validator.rb +214 -0
data/lib/xml.rb +38 -0
data/lib/xml_style_parser.rb +105 -0
data/lib/xmlparser_wrapper.rb +19 -0
data/script/compile_and_plot_smriti_final.rb +97 -0
data/script/extract_gradient_programs.rb +56 -0
data/script/get_apex_values_rexml.rb +44 -0
data/script/mzXML2timeIndex.rb +1 -1
data/script/smriti_final_analysis.rb +103 -0
data/script/toppred_to_yaml.rb +47 -0
data/script/tpp_installer.rb +1 -1
data/{test/tc_align.rb → specs/align_spec.rb} +21 -27
data/{test/tc_bioworks_to_pepxml.rb → specs/bin/bioworks_to_pepxml_spec.rb} +25 -41
data/specs/bin/fasta_shaker_spec.rb +259 -0
data/specs/bin/filter_and_validate__multiple_vals_helper.yaml +202 -0
data/specs/bin/filter_and_validate_spec.rb +124 -0
data/specs/bin/ms_to_lmat_spec.rb +34 -0
data/specs/bin/prob_validate_spec.rb +62 -0
data/specs/bin/protein_summary_spec.rb +10 -0
data/{test/tc_fasta.rb → specs/fasta_spec.rb} +354 -310
data/specs/gi_spec.rb +22 -0
data/specs/load_bin_path.rb +7 -0
data/specs/merge_deep_spec.rb +13 -0
data/specs/ms/gradient_program_spec.rb +77 -0
data/specs/ms/msrun_spec.rb +455 -0
data/specs/ms/parser_spec.rb +92 -0
data/specs/ms/spectrum_spec.rb +89 -0
data/specs/roc_spec.rb +251 -0
data/specs/rspec_autotest.rb +149 -0
data/specs/sample_enzyme_spec.rb +41 -0
data/specs/spec_helper.rb +133 -0
data/specs/spec_id/aa_freqs_spec.rb +52 -0
data/{test/tc_bioworks.rb → specs/spec_id/bioworks_spec.rb} +56 -71
data/specs/spec_id/digestor_spec.rb +75 -0
data/specs/spec_id/precision/filter/cmdline_spec.rb +20 -0
data/specs/spec_id/precision/filter/output_spec.rb +31 -0
data/specs/spec_id/precision/filter_spec.rb +243 -0
data/specs/spec_id/precision/prob_spec.rb +111 -0
data/specs/spec_id/precision/prob_spec_helper.rb +0 -0
data/specs/spec_id/proph/pep_summary_spec.rb +143 -0
data/{test/tc_proph.rb → specs/spec_id/proph/prot_summary_spec.rb} +52 -32
data/{test/tc_protein_summary.rb → specs/spec_id/protein_summary_spec.rb} +85 -0
data/specs/spec_id/sequest/params_spec.rb +68 -0
data/specs/spec_id/sequest/pepxml_spec.rb +452 -0
data/specs/spec_id/sqt_spec.rb +138 -0
data/specs/spec_id/srf_spec.rb +209 -0
data/specs/spec_id/srf_spec_helper.rb +302 -0
data/specs/spec_id_helper.rb +33 -0
data/specs/spec_id_spec.rb +361 -0
data/specs/spec_id_xml_spec.rb +33 -0
data/specs/transmem/phobius_spec.rb +423 -0
data/specs/transmem/toppred_spec.rb +297 -0
data/specs/transmem_spec.rb +60 -0
data/specs/transmem_spec_shared.rb +64 -0
data/specs/validator/aa_spec.rb +107 -0
data/specs/validator/background_spec.rb +51 -0
data/specs/validator/bias_spec.rb +146 -0
data/specs/validator/decoy_spec.rb +51 -0
data/specs/validator/fasta_helper.rb +26 -0
data/specs/validator/prot_from_pep_spec.rb +141 -0
data/specs/validator/transmem_spec.rb +145 -0
data/specs/validator/true_pos_spec.rb +58 -0
data/specs/validator_helper.rb +33 -0
data/specs/xml_spec.rb +12 -0
data/test_files/000_pepxml18_small.xml +206 -0
data/test_files/020a.mzXML.timeIndex +4710 -0
data/test_files/4-03-03_mzXML/000.mzXML.timeIndex +3973 -0
data/test_files/4-03-03_mzXML/020.mzXML.timeIndex +3872 -0
data/test_files/4-03-03_small-prot.xml +321 -0
data/test_files/4-03-03_small.xml +3876 -0
data/test_files/7MIX_STD_110802_1.sequest_params_fragment.srf +0 -0
data/test_files/bioworks-3.3_10prots.xml +5999 -0
data/test_files/bioworks31.params +77 -0
data/test_files/bioworks32.params +62 -0
data/test_files/bioworks33.params +63 -0
data/test_files/bioworks_single_run_small.xml +7237 -0
data/test_files/bioworks_small.fasta +212 -0
data/test_files/bioworks_small.params +63 -0
data/test_files/bioworks_small.phobius +109 -0
data/test_files/bioworks_small.toppred.out +2847 -0
data/test_files/bioworks_small.xml +5610 -0
data/test_files/bioworks_with_INV_small.xml +3753 -0
data/test_files/bioworks_with_SHUFF_small.xml +2503 -0
data/test_files/corrupted_900.srf +0 -0
data/test_files/head_of_7MIX.srf +0 -0
data/test_files/interact-opd1_mods_small-prot.xml +304 -0
data/test_files/messups.fasta +297 -0
data/test_files/opd1/000.my_answer.100lines.xml +101 -0
data/test_files/opd1/000.tpp_1.2.3.first10.xml +115 -0
data/test_files/opd1/000.tpp_2.9.2.first10.xml +126 -0
data/test_files/opd1/000.v2.1.mzXML.timeIndex +3748 -0
data/test_files/opd1/000_020-prot.png +0 -0
data/test_files/opd1/000_020_3prots-prot.mod_initprob.xml +62 -0
data/test_files/opd1/000_020_3prots-prot.xml +62 -0
data/test_files/opd1/opd1_cat_inv_small-prot.xml +139 -0
data/test_files/opd1/sequest.3.1.params +77 -0
data/test_files/opd1/sequest.3.2.params +62 -0
data/test_files/opd1/twenty_scans.mzXML +418 -0
data/test_files/opd1/twenty_scans.v2.1.mzXML +382 -0
data/test_files/opd1/twenty_scans_answ.lmat +0 -0
data/test_files/opd1/twenty_scans_answ.lmata +9 -0
data/test_files/opd1_020_beginning.RAW +0 -0
data/test_files/opd1_2runs_2mods/interact-opd1_mods__small.xml +753 -0
data/test_files/orbitrap_mzData/000_cut.xml +1920 -0
data/test_files/pepproph_small.xml +4691 -0
data/test_files/phobius.small.noheader.txt +50 -0
data/test_files/phobius.small.small.txt +53 -0
data/test_files/s01_anC1_ld020mM.key.txt +25 -0
data/test_files/s01_anC1_ld020mM.meth +0 -0
data/test_files/small.fasta +297 -0
data/test_files/smallraw.RAW +0 -0
data/test_files/tf_bioworks2excel.bioXML +14340 -0
data/test_files/tf_bioworks2excel.txt.actual +1035 -0
data/test_files/toppred.small.out +416 -0
data/test_files/toppred.xml.out +318 -0
data/test_files/validator_hits_separate/bias_bioworks_small_HS.fasta +7 -0
data/test_files/validator_hits_separate/bioworks_small_HS.xml +5651 -0
data/test_files/yeast_gly_small-prot.xml +265 -0
data/test_files/yeast_gly_small.1.0_1.0_1.0.parentTimes +6 -0
data/test_files/yeast_gly_small.xml +3807 -0
data/test_files/yeast_gly_small2.parentTimes +6 -0
metadata +273 -57
data/bin/filter.rb +0 -6
data/bin/precision.rb +0 -5
data/lib/spec/mzdata/parser.rb +0 -108
data/lib/spec/mzdata.rb +0 -48
data/lib/spec/mzxml/parser.rb +0 -449
data/lib/spec/scan.rb +0 -55
data/lib/spec_id/filter.rb +0 -797
data/lib/spec_id/precision.rb +0 -421
data/lib/toppred.rb +0 -18
data/script/filter-peps.rb +0 -164
data/test/tc_aa_freqs.rb +0 -59
data/test/tc_fasta_shaker.rb +0 -149
data/test/tc_filter.rb +0 -203
data/test/tc_filter_peps.rb +0 -46
data/test/tc_gi.rb +0 -17
data/test/tc_id_class_anal.rb +0 -70
data/test/tc_id_precision.rb +0 -89
data/test/tc_msrun.rb +0 -88
data/test/tc_mzxml.rb +0 -88
data/test/tc_mzxml_to_lmat.rb +0 -36
data/test/tc_peptide_parent_times.rb +0 -27
data/test/tc_precision.rb +0 -60
data/test/tc_roc.rb +0 -166
data/test/tc_sample_enzyme.rb +0 -32
data/test/tc_scan.rb +0 -26
data/test/tc_sequest.rb +0 -336
data/test/tc_spec.rb +0 -78
data/test/tc_spec_id.rb +0 -201
data/test/tc_spec_id_xml.rb +0 -36
data/test/tc_srf.rb +0 -262

data/lib/spec_id/precision.rb DELETED Viewed

@@ -1,421 +0,0 @@
-require 'optparse'
-require 'ostruct'
-require 'generator'
-require 'roc'
-## silence this bad boy
-tmp = $VERBOSE ; $VERBOSE = nil
-require 'gnuplot'
-$VERBOSE = tmp
-class String
-  def margin
-    self.gsub(/^\s*\|/,'')
-  end
-end
-class Prec ; end
-module Prec::PlotHelper
-  PLOT_TYPE = 'XYData'
-  TITLE = 'Precision vs. Num Hits [ Precision = Positive Predictive Value = TP/(TP+FP) ]'
-  XAXIS = 'Num Hits (excludes known false positives)'
-  EXT = '.toplot'
-  IMAGE_EXT = '.png'
-  def create_to_plot_file(all_arrs, key, files, filename_noext)
-    ## CREATE the PLOT IMAGE:
-    to_plot = filename_noext + EXT
-    png = filename_noext + IMAGE_EXT
-    File.open(to_plot,'w') do |out|
-      out.puts PLOT_TYPE
-      out.puts filename_noext
-      out.puts TITLE
-      out.puts XAXIS
-      out.puts escape_to_gnuplot(y_axis_label(key))
-      files.each_with_index do |file,i|
-        #p key[i]
-        #p all_arrs[i]
-        key[i].each_with_index do |k,j|
-          out.puts(escape_to_gnuplot("#{file}: #{k[1][1]}"))
-          out.puts all_arrs[i][j][0].join(' ')
-          out.puts all_arrs[i][j][1].join(' ')
-        end
-      end
-    end
-  end
-  ## outputs a .toplot file based on filename_noext, creates a png file, and
-  ## writes  html to fh that will load the png file up
-  ## This is a self contained module that can be swapped out for a
-  ## completely different plotting program if desired.
-  def plot_figure(all_arrs, key, files, filename_noext)
-    ## CREATE the PLOT IMAGE:
-    to_plot = filename_noext+'.toplot'
-    png = filename_noext+'.png'
-    tmp = $VERBOSE ; $VERBOSE = nil
-    Gnuplot.open do |gp|
-      Gnuplot::Plot.new( gp ) do |plot|
-        plot.terminal "png noenhanced"
-        plot.output png
-        plot.title TITLE
-        plot.xlabel XAXIS
-        plot.ylabel escape_to_gnuplot(y_axis_label(key))
-        plot.style "line 1 lt 1"
-        plot.style "line 2 lt 12"
-        #plot.style  "line 1 lt 1 lw #{opts.lw} pt 7 ps #{opts.ps}",
-        plot.yrange "[-0.05:#{1.05 + 0.020*files.size}]"
-        files.each_with_index do |file,i|
-          key[i].each_with_index do |k,j|
-            plot.data << Gnuplot::DataSet.new( [ all_arrs[i][j][0], all_arrs[i][j][1] ] ) do |ds|
-              ds.with = "lines"
-              ds.title = escape_to_gnuplot("#{file}: #{k[1][1]}")
-            end
-          end
-        end
-      end
-    end
-    $VERBOSE = tmp
-    ## CREATE the HTML to load the plot:
-    basename_filename_noext = File.basename(filename_noext)
-    output = "<div id=\"plot\"><table class=\"image\" align=\"center\">\n"
-    #output << "<caption align=\"bottom\">Additional views of this data may be obtained by using the <span class=\"code\">plot.rb</span> command on '#{to_plot}' (type <span class=\"code\">plot.rb</span> for more details). Plot generated with command: &nbsp;&nbsp; <span class=\"code\">#{plot_cmd}</span></caption>\n"
-    output << "<tr><td><img src=\"#{basename_filename_noext}.png\" title=\"File #{basename_filename_noext} must be in the same directory as this html.\"/></td></tr>\n"
-    output << "</table></div>\n"
-    output
-  end  # plot_figure
-end
-module Prec::HTML
-  # html and body tags
-  def html
-        "|<html>
-         |#{yield}
-         |</html>\n".margin
-  end
-  def body
-        "|<body>
-         |  #{yield}
-         |</body>\n".margin
-  end
-  def header
-        "|<head>
-         |  #{style}
-         |</head>\n".margin
-  end
-  def td
-        "<td>#{yield}</td>"
-  end
-  def style
-        '
-     <style type="text/css">
-        div#tp_table {
-          text-align: center;
-          margin-top: 50px;
-          margin-bottom: 50px;
-        }
-        span.code {
-        font-family: Courier,Monospace;
-        font-size: 80%;
-        }
-          table {
-              border-width:1px;
-              border-color:#CCCCCC;
-              border-collapse: collapse;
-          }
-          caption {
-            font-size: 90%;
-          }
-          td,th {
-              padding-top: 2px;
-              padding-bottom: 2px;
-              padding-left: 1;
-              padding-right: 1;
-          }
-          th.small {
-            font-size: 80%;
-            font-weight: normal;
-            padding: 1px;
-          }
-          td.redline {
-              background-color: #FF0000;
-              color: #FFFFFF
-          }
-      div#plot {
-        margin: 30px;
-     text-align:center
-      }
-      hr {color: sienna}
-      body { font-size: 8pt; font-family: Arial,Helvetica,Times}
-      </style>
-        '
-  end
-  def table
-        "|<table border=\"1\" align=\"center\" style=\"font-size:100%\">
-         |  #{yield}
-         |</table>\n".margin
-  end
-  def tr
-        "|<tr>
-         |  #{yield}
-         |</tr>\n".margin
-  end
-end # module HTML
-class Prec
-  include Prec::PlotHelper
-  ###########################################################
-  # GLOBAL SETTINGS:
-  DATA_PREC = 4   # decimal places of precision for ppv data
-  STDOUT_JTPLOT_BASE = "ppv"  # if there is no outfile
-  ###########################################################
-  include Prec::HTML
-  ## returns an html string
-  def precision(argv)
-    opt = parse_args(argv)
-    files = argv.to_a
-    out_string = create_precision_data(files, opt)
-    [out_string, opt]
-  end
-  def run_cmd_line(argv)
-    output_string, opt, file_as_decoy = precision(argv)
-    if file_as_decoy
-      puts output_string
-    else
-      ## open file and write to it..
-      if opt.o == 'STDOUT'
-        print output_string
-      else
-        File.open(opt.o,'w') do |fh| fh.print output_string end
-      end
-    end
-  end
-  # returns the outfile with no extension
-  def outfile_noext(opt)
-    if opt == 'STDOUT'
-      "#{STDOUT_JTPLOT_BASE}"
-    else
-      opt.sub(/#{Regexp.escape(File.extname(opt))}$/, '')
-    end
-  end
-  def file_noext(file)
-    file.sub(/#{Regexp.escape(File.extname(file))}$/, '')
-  end
-  def parse_args(argv)
-    opt = OpenStruct.new
-    opt.o = 'STDOUT'
-    opts = OptionParser.new do |op|
-      op.banner = "Usage: #{File.basename(__FILE__)} [options] bioworks.xml|proph-prot.xml ..."
-      op.separator ""
-      op.separator "Abbreviations and Definitions:"
-      op.separator "  TP = True Positives"
-      op.separator "  FP = False Positives"
-      op.separator "  Precision = Positive Predictive Value = [TP/(TP+FP)]"
-      op.separator ""
-      op.separator "Output: "
-      op.separator "  1. Decoy as separate search: PPV to STDOUT"
-      op.separator "  2. Decoy proteins from concatenated database: '.html'"
-      op.separator ""
-      op.separator "Options:"
-      op.on("-f", "--fp_data <prefix_or_file>", "flag -or- decoy FILE") {|v| opt.f = v }
-      op.separator ""
-      op.separator "        If searched with a concatenated DB, give a false flag to decoy proteins."
-      op.separator "        If files have different flags, separate with commas."
-      op.separator "        If searched with a separate decoy DB, give the FILE name of decoy data"
-      op.on("--prefix", "false flag as prefix only") {|v| opt.prefix = v }
-      op.separator ""
-      ## NOT YET FUNCTIONAL: op.on("-e", "--peptides", "do peptides instead of proteins")
-      op.separator ""
-      op.on("-o", "--outfile <file>", "write output to file (def: #{opt.o})") {|v| opt.o = v}
-      op.on("-a", "--area", "output area under the curve instead of the plot") {|v| opt.a = v}
-      op.on("-j", "--plot_file", "output to_plot file") {|v| opt.j = v}
-      op.on_tail("
-Example:
-  For a search on a concatenated database where the decoy proteins have
-  been flagged with the prefix 'INV_' for both Bioworks and ProteinProphet
-  output:
-    #{File.basename(__FILE__)} -f INV_ bioworks.xml proph-prot.xml
-  ")
-    end
-    opts.parse!(argv)
-    if argv.size < 1
-      puts opts
-      exit
-    end
-    opt
-  end
-  ## collapses arrays to one level deep so we can sync them up
-  def arrays_to_one_level_deep(all_arrs)
-    mostly_flat = []
-    all_arrs.each do |per_file|
-      per_file.each do |per_style|
-        mostly_flat << per_style[0]
-        mostly_flat << per_style[1]
-      end
-    end
-    mostly_flat
-  end
-  # prints rows and th for the data
-  def table_cells(all_arrs, key)
-    ## columns specific headings:
-    all_string = ""
-    all_string << tr do
-      line = ""
-      key.each do |per_file|
-        per_file.each do |per_ds|
-          line << "<th class=\"small\">#{per_ds[1][0]}</th><th class=\"small\">#{per_ds[1][1]}</th>"
-        end
-      end
-      line
-    end
-    mostly_flat = arrays_to_one_level_deep(all_arrs)
-    SyncEnumerator.new(*mostly_flat).each do |row|
-      all_string << tr do
-        string = row.map {|it|
-          sty="%d"
-          if it.class == Float ; sty="%.#{DATA_PREC}f" end
-          td{ sprintf(sty,it)}
-        }.join
-      end
-    end
-    all_string
-  end
-  def html_table_output(all_arrs, key, files, filename_noext)
-    num_datasets_per_file = all_arrs.first.size
-    num_cols_per_dataset = 2
-    big_colspan = num_datasets_per_file * num_cols_per_dataset
-    output = table do
-      tr do
-        files.map do |file|
-        "<th colspan=\"#{big_colspan}\">#{file}</th>"
-        end.join
-      end +
-        tr do
-        key.map do |arr|
-          arr.map do |ds|
-        "<th colspan=\"2\">#{ds.first}</th>"
-          end
-        end
-        end +
-          table_cells(all_arrs, key)
-    end
-    "<div id=\"tp_table\">" + output + "</div>"
-  end
-  def y_axis_label(key)
-    ## We only take the keys for the first file, as it's assumed that the major
-    ## labels will be identical for all of them
-    labels = key.first.map {|tp| tp.first }.uniq
-    labels.join "  |  "
-  end
-  # escapes any ' chars
-  def escape_to_gnuplot(string)
-    # long way, but it works.
-    new_string = ""
-    string.split(//).each do |chr|
-      if chr == "'" ; new_string << "\\" end
-      new_string << chr
-    end
-    new_string
-  end
-  # if opt.f, then a prefix is assumed.
-  # if a file =~ /-prot.xml$/ then a precision plot based on probability is
-  # also created
-  def create_precision_data(files, opt)
-    #$stderr.puts "using prefix #{opt.f} ..."
-    if opt.f
-      prefix_arr = SpecID.extend_args(opt.f, files.size)
-    end
-    all_arrs = []
-    key = []
-    out_noext = outfile_noext(opt.o)
-    files.each_with_index do |file,i|
-      all_arrs[i] = []
-      key[i] = []
-      sp = SpecID.new(file)
-      #headers = ["#{file_noext(file)} Precision [TP/(TP+FP)]", "#{file_noext(file)} FPR [FP/(FP+TP)]"]
-      if opt.f
-        (num_hits, ppv) = sp.num_hits_and_ppv_for_prob(prefix_arr[i], opt.prefix)
-        all_arrs[i] << [num_hits,ppv]
-        key[i] << ["Precision",  ["# hits", "Prec (decoy)"]]
-      end
-      if file =~ /-prot\.xml$/
-        ## These are just from protein prophet probabilities:
-        (num_hits, ppv) = sp.num_hits_and_ppv_for_protein_prophet_probabilities
-        all_arrs[i] << [num_hits,ppv]
-        key[i] << ["Precision",  ["# hits", "Prec (prob)"]]
-      end
-    end
-    string = ''
-    if opt.a
-      roc = ROC.new
-      #string << "***********************************************************\n"
-      #string << "AREA UNDER CURVE:\n"
-      key.each_with_index do |file,i|
-        string << "#{files[i]} (area under curve)\n"
-        key[i].each_index do |j|
-          string << "#{key[i][j][0]} [#{ key[i][j][1]}]:\t"
-          num_hits = all_arrs[i][j][0]
-          oth = all_arrs[i][j][1]
-          string << roc.area_under_curve(num_hits, oth).to_s << "\n"
-        end
-      end
-      #string << "***********************************************************\n"
-    else
-      if opt.j
-        create_to_plot_file(all_arrs, key, files, out_noext)
-      end
-      string = html do
-        header +
-          body do
-          plot_figure(all_arrs, key, files, out_noext) +
-            html_table_output(all_arrs, key, files, out_noext)
-          end
-      end
-    end
-    string
-  end
-end # class SpecID

data/lib/toppred.rb DELETED Viewed

@@ -1,18 +0,0 @@
-# reader for the http://bioweb.pasteur.fr/seqanal/interfaces/toppred.html
-# output
-class TopPred
-  attr_accessor :hmmmm
-  def initialize(toppred_out_file=nil)
-    if toppred_out_file
-      from_file(toppred_out_file)
-    end
-  end
-  def from_file(toppred_out_file)
-  end
-end

data/script/filter-peps.rb DELETED Viewed

@@ -1,164 +0,0 @@
-#!/usr/bin/ruby -w
-require 'spec_id'
-require 'optparse'
-require 'ostruct'
-DELIMITER = "\t"
-$opt = OpenStruct.new
-$opt.deltacn = 0.2
-$opt.charge1 = 1.5
-$opt.charge2 = 2.0
-$opt.charge3 = 2.5
-opts = OptionParser.new do |op|
-  op.banner = "usage: #{File.basename(__FILE__)} [options] prefixlist bioworks.xml ..."
-  op.on("-1", "--charge1 <cutoff>", "xcorr <= cutoff for charge (#{$opt.charge1})") { |v| $opt.charge1 = v.to_f }
-  op.on("-2", "--charge2 <cutoff>", "xcorr <= cutoff for charge (#{$opt.charge2})") { |v| $opt.charge2 = v.to_f }
-  op.on("-3", "--charge3 <cutoff>", "xcorr <= cutoff for charge (#{$opt.charge3})") { |v| $opt.charge3 = v.to_f }
-  op.on("-d", "--deltacn <cutoff>", "deltacn >= cutoff (#{$opt.deltacn})") { |v| $opt.deltacn = v.to_f }
-end
-opts.parse!
-if ARGV.size < 2
-  puts opts
-  exit
-end
-prefix_list = ARGV.shift
-prefixes = prefix_list.split ","
-files = ARGV.to_a
-## Fill in the prefix array with the last prefix given
-last_prefix = prefixes.first
-if files.size > prefixes.size
-  files.each_with_index do |file,i|
-    if prefixes[i]
-      last_prefix = prefixes[i]
-    else
-      prefixes[i] = last_prefix
-    end
-  end
-end
-###############################
-#CH1 = 1.0
-#CH2 = 2.0
-#CH3 = 3.0
-#DELTACN = 0.2
-###############################
-def passes(pep)
-  if pep.deltacn <= $opt.deltacn
-    case pep.charge
-    when 1
-      pep.xcorr >= $opt.charge1
-    when 2
-      pep.xcorr >= $opt.charge2
-    when 3
-      pep.xcorr >= $opt.charge3
-    end
-  else
-    false
-  end
-end
-# adds two categories with results from the hash
-def analyze(pep_groups, category, hash)
-  best = best_xcorr(pep_groups)
-  top10 = top10_xcorr(pep_groups)
-  hash[category+"Best"] = filter(best).size
-  hash[category+"Top10"] = filter(top10).size
-end
-# returns a hash containing the number of peptides passing the thresholds
-def number_passing(peps)
-  np = {}
-  np["PepProts"] = filter(peps).size
-  by_scan_charge = peps.hash_by(:base_name, :first_scan, :last_scan, :charge).values
-  analyze(by_scan_charge, "ScanCharge", np)
-  by_scan = peps.hash_by(:base_name, :first_scan, :last_scan).values
-  analyze(by_scan, "Scan", np)
-  by_seq_charge = peps.hash_by(:base_name, :sequence, :charge).values
-  analyze(by_seq_charge, "SeqCharge", np)
-  np
-end
-# key = :symbol, val = [:lt|:gt|:lte|:gte, val]
-def filter(peps)
-  peps.select {|pep| passes(pep)}
-end
-def top10_xcorr(pep_groups)
-  peptides_by_tens = []
-  pep_groups.each do |group|
-    arr = group.sort {|a,b| b.xcorr <=> a.xcorr }.slice(0,10)
-    peptides_by_tens.push(*arr)
-  end
-  peptides_by_tens
-end
-def best_xcorr(pep_groups)
-  min_peptides = pep_groups.collect do |group|
-    group.max {|a,b| a.xcorr <=> b.xcorr }
-  end
-end
-headers = %w(PepProts ScanChargeBest ScanChargeTop10 ScanBest ScanTop10 SeqChargeBest SeqChargeTop10)
-csv_headers = headers.dup
-csv_headers.unshift "FILENAME"
-puts csv_headers.join(DELIMITER)
-files.each_with_index do |file,i|
-  obj = SpecID.new(file)
-  obj.peps = obj.pep_prots
-  obj.peps.each do |pep|
-    pep.charge = pep.charge.to_i
-    pep.xcorr = pep.xcorr.to_f
-    pep.deltacn = pep.deltacn.to_f
-  end
-  re_prefix = /^#{Regexp.escape(prefixes[i])}/
-  prc = proc {|it| it.prots.first.reference =~ re_prefix }
-  #(match, nomatch) = obj.classify(:peps, prc)
-  (fp, tp) = obj.classify(:peps, prc)
-  (fp_pass, tp_pass) = [fp,tp].map {|v| number_passing(v) }
-  # print to file out
-  tp = headers.map do |head|
-    tp_pass[head]
-  end
-  fp = headers.map do |head|
-    fp_pass[head]
-  end
-  diffs = []
-  tp.each_index do |i|
-    diffs << (tp[i] - fp[i])
-  end
-  tp.unshift("TP: " + file)
-  fp.unshift("FP: " + file)
-  diffs.unshift("DIFF: " + file)
-  puts tp.join(DELIMITER)
-  puts fp.join(DELIMITER)
-  puts diffs.join(DELIMITER)
-end

data/test/tc_aa_freqs.rb DELETED Viewed

@@ -1,59 +0,0 @@
-require 'test/unit'
-require 'spec_id/aa_freqs'
-class FastaTest < Test::Unit::TestCase
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @sf = @tfiles + "small.fasta"
-  end
-  def test_basic
-    obj = SpecID::AAFreqs.new(@sf)
-    expect = {:I=>0.0628918621937819, :S=>0.0539719475147049, :D=>0.0526145691939758, :Z=>0.0, :L=>0.102772929998061, :T=>0.0491888048607071, :E=>0.0609527503070261, :O=>0.0, :C=>0.0157714433456144, :K=>0.0471850559110594, :U=>0.0, :Q=>0.0382651412319824, :W=>0.0137030573330748, :A=>0.101997285243359, :M=>0.0294745006786892, :J=>0.0, :G=>0.0811195139292871, :Y=>0.0254670027793937, :X=>0.0, :F=>0.0418201796910348, :R=>0.0546829552065154, :V=>0.0702604873634542, :H=>0.0213302307543145, :B=>0.0, :N=>0.03471010277293, :P=>0.0418201796910348}
-    aaf =  obj.aafreqs
-    expect.each do |k,v|
-      assert(aaf.key?(k))
-      assert_in_delta(v, aaf[k], 0.00000001, "freqs match up")
-    end
-    sum = 0.0
-    aaf.values.each do |v|
-      sum += v
-    end
-    assert_in_delta(1.0, sum, 0.0000000000001, "all freqs add to 1")
-  end
-  def test_probability_of_length_table
-    # p SpecID::AAFreqs.probability_of_length_table(0.01, 4)
-    assert_equal_arrs_in_delta([0.0, 0.01, 0.0199, 0.029701, 0.0394039900000001],  SpecID::AAFreqs.probability_of_length_table(0.01, 4), 0.000000001)
-    assert_equal_arrs_in_delta([0.0, 0.2, 0.36, 0.488, 0.5904], SpecID::AAFreqs.probability_of_length_table(0.2, 4), 0.000000001)
-  end
-  def test_actual_and_expected_number
-    fobj = Fasta.new.read_file(@sf)
-    obj = SpecID::AAFreqs.new
-    obj.aafreqs = obj.calculate_frequencies(fobj)
-    peptide_aaseqs = fobj.prots.map do |prot|
-      prot.aaseq[0..12]
-    end
-    assert_equal(50, peptide_aaseqs.size, 'sanity check')
-    (ac,ex) = obj.actual_and_expected_number(peptide_aaseqs, :C, 1)
-    assert_equal(9, ac)
-    assert_in_delta( 9.33530631238985, ex, 0.0000000001)
-  end
-  private
-  def assert_equal_arrs_in_delta(expect, actual, delta)
-    expect.each_with_index do |v,i|
-      assert_in_delta(v, actual[i], delta)
-    end
-  end
-end