mspire 0.2.4 → 0.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (233) hide show
  1. data/INSTALL +1 -0
  2. data/README +25 -0
  3. data/Rakefile +129 -40
  4. data/bin/{find_aa_freq.rb → aafreqs.rb} +2 -2
  5. data/bin/bioworks_to_pepxml.rb +1 -0
  6. data/bin/fasta_shaker.rb +1 -96
  7. data/bin/filter_and_validate.rb +5 -0
  8. data/bin/{mzxml_to_lmat.rb → ms_to_lmat.rb} +8 -7
  9. data/bin/prob_validate.rb +6 -0
  10. data/bin/raw_to_mzXML.rb +2 -2
  11. data/bin/srf_group.rb +1 -0
  12. data/bin/srf_to_sqt.rb +40 -0
  13. data/changelog.txt +68 -0
  14. data/lib/align/chams.rb +6 -6
  15. data/lib/align.rb +4 -3
  16. data/lib/bsearch.rb +120 -0
  17. data/lib/fasta.rb +318 -86
  18. data/lib/group_by.rb +10 -0
  19. data/lib/index_by.rb +11 -0
  20. data/lib/merge_deep.rb +21 -0
  21. data/lib/{spec → ms/converter}/mzxml.rb +77 -109
  22. data/lib/ms/gradient_program.rb +171 -0
  23. data/lib/ms/msrun.rb +209 -0
  24. data/lib/{spec/msrun.rb → ms/msrun_index.rb} +7 -40
  25. data/lib/ms/parser/mzdata/axml.rb +12 -0
  26. data/lib/ms/parser/mzdata/dom.rb +160 -0
  27. data/lib/ms/parser/mzdata/libxml.rb +7 -0
  28. data/lib/ms/parser/mzdata.rb +25 -0
  29. data/lib/ms/parser/mzxml/axml.rb +11 -0
  30. data/lib/ms/parser/mzxml/dom.rb +159 -0
  31. data/lib/ms/parser/mzxml/hpricot.rb +253 -0
  32. data/lib/ms/parser/mzxml/libxml.rb +15 -0
  33. data/lib/ms/parser/mzxml/regexp.rb +122 -0
  34. data/lib/ms/parser/mzxml/rexml.rb +72 -0
  35. data/lib/ms/parser/mzxml/xmlparser.rb +248 -0
  36. data/lib/ms/parser/mzxml.rb +175 -0
  37. data/lib/ms/parser.rb +108 -0
  38. data/lib/ms/precursor.rb +10 -0
  39. data/lib/ms/scan.rb +81 -0
  40. data/lib/ms/spectrum.rb +193 -0
  41. data/lib/ms.rb +10 -0
  42. data/lib/mspire.rb +4 -0
  43. data/lib/roc.rb +61 -1
  44. data/lib/sample_enzyme.rb +31 -8
  45. data/lib/scan_i.rb +21 -0
  46. data/lib/spec_id/aa_freqs.rb +7 -3
  47. data/lib/spec_id/bioworks.rb +20 -14
  48. data/lib/spec_id/digestor.rb +139 -0
  49. data/lib/spec_id/mass.rb +116 -0
  50. data/lib/spec_id/parser/proph.rb +236 -0
  51. data/lib/spec_id/precision/filter/cmdline.rb +209 -0
  52. data/lib/spec_id/precision/filter/interactive.rb +134 -0
  53. data/lib/spec_id/precision/filter/output.rb +147 -0
  54. data/lib/spec_id/precision/filter.rb +623 -0
  55. data/lib/spec_id/precision/output.rb +60 -0
  56. data/lib/spec_id/precision/prob/cmdline.rb +139 -0
  57. data/lib/spec_id/precision/prob/output.rb +88 -0
  58. data/lib/spec_id/precision/prob.rb +171 -0
  59. data/lib/spec_id/proph/pep_summary.rb +92 -0
  60. data/lib/spec_id/proph/prot_summary.rb +484 -0
  61. data/lib/spec_id/proph.rb +2 -466
  62. data/lib/spec_id/protein_summary.rb +2 -2
  63. data/lib/spec_id/sequest/params.rb +316 -0
  64. data/lib/spec_id/sequest/pepxml.rb +1513 -0
  65. data/lib/spec_id/sequest.rb +2 -1672
  66. data/lib/spec_id/srf.rb +445 -177
  67. data/lib/spec_id.rb +183 -95
  68. data/lib/spec_id_xml.rb +8 -10
  69. data/lib/transmem/phobius.rb +147 -0
  70. data/lib/transmem/toppred.rb +368 -0
  71. data/lib/transmem.rb +157 -0
  72. data/lib/validator/aa.rb +135 -0
  73. data/lib/validator/background.rb +73 -0
  74. data/lib/validator/bias.rb +95 -0
  75. data/lib/validator/cmdline.rb +260 -0
  76. data/lib/validator/decoy.rb +94 -0
  77. data/lib/validator/digestion_based.rb +69 -0
  78. data/lib/validator/probability.rb +48 -0
  79. data/lib/validator/prot_from_pep.rb +234 -0
  80. data/lib/validator/transmem.rb +272 -0
  81. data/lib/validator/true_pos.rb +46 -0
  82. data/lib/validator.rb +214 -0
  83. data/lib/xml.rb +38 -0
  84. data/lib/xml_style_parser.rb +105 -0
  85. data/lib/xmlparser_wrapper.rb +19 -0
  86. data/script/compile_and_plot_smriti_final.rb +97 -0
  87. data/script/extract_gradient_programs.rb +56 -0
  88. data/script/get_apex_values_rexml.rb +44 -0
  89. data/script/mzXML2timeIndex.rb +1 -1
  90. data/script/smriti_final_analysis.rb +103 -0
  91. data/script/toppred_to_yaml.rb +47 -0
  92. data/script/tpp_installer.rb +1 -1
  93. data/{test/tc_align.rb → specs/align_spec.rb} +21 -27
  94. data/{test/tc_bioworks_to_pepxml.rb → specs/bin/bioworks_to_pepxml_spec.rb} +25 -41
  95. data/specs/bin/fasta_shaker_spec.rb +259 -0
  96. data/specs/bin/filter_and_validate__multiple_vals_helper.yaml +202 -0
  97. data/specs/bin/filter_and_validate_spec.rb +124 -0
  98. data/specs/bin/ms_to_lmat_spec.rb +34 -0
  99. data/specs/bin/prob_validate_spec.rb +62 -0
  100. data/specs/bin/protein_summary_spec.rb +10 -0
  101. data/{test/tc_fasta.rb → specs/fasta_spec.rb} +354 -310
  102. data/specs/gi_spec.rb +22 -0
  103. data/specs/load_bin_path.rb +7 -0
  104. data/specs/merge_deep_spec.rb +13 -0
  105. data/specs/ms/gradient_program_spec.rb +77 -0
  106. data/specs/ms/msrun_spec.rb +455 -0
  107. data/specs/ms/parser_spec.rb +92 -0
  108. data/specs/ms/spectrum_spec.rb +89 -0
  109. data/specs/roc_spec.rb +251 -0
  110. data/specs/rspec_autotest.rb +149 -0
  111. data/specs/sample_enzyme_spec.rb +41 -0
  112. data/specs/spec_helper.rb +133 -0
  113. data/specs/spec_id/aa_freqs_spec.rb +52 -0
  114. data/{test/tc_bioworks.rb → specs/spec_id/bioworks_spec.rb} +56 -71
  115. data/specs/spec_id/digestor_spec.rb +75 -0
  116. data/specs/spec_id/precision/filter/cmdline_spec.rb +20 -0
  117. data/specs/spec_id/precision/filter/output_spec.rb +31 -0
  118. data/specs/spec_id/precision/filter_spec.rb +243 -0
  119. data/specs/spec_id/precision/prob_spec.rb +111 -0
  120. data/specs/spec_id/precision/prob_spec_helper.rb +0 -0
  121. data/specs/spec_id/proph/pep_summary_spec.rb +143 -0
  122. data/{test/tc_proph.rb → specs/spec_id/proph/prot_summary_spec.rb} +52 -32
  123. data/{test/tc_protein_summary.rb → specs/spec_id/protein_summary_spec.rb} +85 -0
  124. data/specs/spec_id/sequest/params_spec.rb +68 -0
  125. data/specs/spec_id/sequest/pepxml_spec.rb +452 -0
  126. data/specs/spec_id/sqt_spec.rb +138 -0
  127. data/specs/spec_id/srf_spec.rb +209 -0
  128. data/specs/spec_id/srf_spec_helper.rb +302 -0
  129. data/specs/spec_id_helper.rb +33 -0
  130. data/specs/spec_id_spec.rb +361 -0
  131. data/specs/spec_id_xml_spec.rb +33 -0
  132. data/specs/transmem/phobius_spec.rb +423 -0
  133. data/specs/transmem/toppred_spec.rb +297 -0
  134. data/specs/transmem_spec.rb +60 -0
  135. data/specs/transmem_spec_shared.rb +64 -0
  136. data/specs/validator/aa_spec.rb +107 -0
  137. data/specs/validator/background_spec.rb +51 -0
  138. data/specs/validator/bias_spec.rb +146 -0
  139. data/specs/validator/decoy_spec.rb +51 -0
  140. data/specs/validator/fasta_helper.rb +26 -0
  141. data/specs/validator/prot_from_pep_spec.rb +141 -0
  142. data/specs/validator/transmem_spec.rb +145 -0
  143. data/specs/validator/true_pos_spec.rb +58 -0
  144. data/specs/validator_helper.rb +33 -0
  145. data/specs/xml_spec.rb +12 -0
  146. data/test_files/000_pepxml18_small.xml +206 -0
  147. data/test_files/020a.mzXML.timeIndex +4710 -0
  148. data/test_files/4-03-03_mzXML/000.mzXML.timeIndex +3973 -0
  149. data/test_files/4-03-03_mzXML/020.mzXML.timeIndex +3872 -0
  150. data/test_files/4-03-03_small-prot.xml +321 -0
  151. data/test_files/4-03-03_small.xml +3876 -0
  152. data/test_files/7MIX_STD_110802_1.sequest_params_fragment.srf +0 -0
  153. data/test_files/bioworks-3.3_10prots.xml +5999 -0
  154. data/test_files/bioworks31.params +77 -0
  155. data/test_files/bioworks32.params +62 -0
  156. data/test_files/bioworks33.params +63 -0
  157. data/test_files/bioworks_single_run_small.xml +7237 -0
  158. data/test_files/bioworks_small.fasta +212 -0
  159. data/test_files/bioworks_small.params +63 -0
  160. data/test_files/bioworks_small.phobius +109 -0
  161. data/test_files/bioworks_small.toppred.out +2847 -0
  162. data/test_files/bioworks_small.xml +5610 -0
  163. data/test_files/bioworks_with_INV_small.xml +3753 -0
  164. data/test_files/bioworks_with_SHUFF_small.xml +2503 -0
  165. data/test_files/corrupted_900.srf +0 -0
  166. data/test_files/head_of_7MIX.srf +0 -0
  167. data/test_files/interact-opd1_mods_small-prot.xml +304 -0
  168. data/test_files/messups.fasta +297 -0
  169. data/test_files/opd1/000.my_answer.100lines.xml +101 -0
  170. data/test_files/opd1/000.tpp_1.2.3.first10.xml +115 -0
  171. data/test_files/opd1/000.tpp_2.9.2.first10.xml +126 -0
  172. data/test_files/opd1/000.v2.1.mzXML.timeIndex +3748 -0
  173. data/test_files/opd1/000_020-prot.png +0 -0
  174. data/test_files/opd1/000_020_3prots-prot.mod_initprob.xml +62 -0
  175. data/test_files/opd1/000_020_3prots-prot.xml +62 -0
  176. data/test_files/opd1/opd1_cat_inv_small-prot.xml +139 -0
  177. data/test_files/opd1/sequest.3.1.params +77 -0
  178. data/test_files/opd1/sequest.3.2.params +62 -0
  179. data/test_files/opd1/twenty_scans.mzXML +418 -0
  180. data/test_files/opd1/twenty_scans.v2.1.mzXML +382 -0
  181. data/test_files/opd1/twenty_scans_answ.lmat +0 -0
  182. data/test_files/opd1/twenty_scans_answ.lmata +9 -0
  183. data/test_files/opd1_020_beginning.RAW +0 -0
  184. data/test_files/opd1_2runs_2mods/interact-opd1_mods__small.xml +753 -0
  185. data/test_files/orbitrap_mzData/000_cut.xml +1920 -0
  186. data/test_files/pepproph_small.xml +4691 -0
  187. data/test_files/phobius.small.noheader.txt +50 -0
  188. data/test_files/phobius.small.small.txt +53 -0
  189. data/test_files/s01_anC1_ld020mM.key.txt +25 -0
  190. data/test_files/s01_anC1_ld020mM.meth +0 -0
  191. data/test_files/small.fasta +297 -0
  192. data/test_files/smallraw.RAW +0 -0
  193. data/test_files/tf_bioworks2excel.bioXML +14340 -0
  194. data/test_files/tf_bioworks2excel.txt.actual +1035 -0
  195. data/test_files/toppred.small.out +416 -0
  196. data/test_files/toppred.xml.out +318 -0
  197. data/test_files/validator_hits_separate/bias_bioworks_small_HS.fasta +7 -0
  198. data/test_files/validator_hits_separate/bioworks_small_HS.xml +5651 -0
  199. data/test_files/yeast_gly_small-prot.xml +265 -0
  200. data/test_files/yeast_gly_small.1.0_1.0_1.0.parentTimes +6 -0
  201. data/test_files/yeast_gly_small.xml +3807 -0
  202. data/test_files/yeast_gly_small2.parentTimes +6 -0
  203. metadata +273 -57
  204. data/bin/filter.rb +0 -6
  205. data/bin/precision.rb +0 -5
  206. data/lib/spec/mzdata/parser.rb +0 -108
  207. data/lib/spec/mzdata.rb +0 -48
  208. data/lib/spec/mzxml/parser.rb +0 -449
  209. data/lib/spec/scan.rb +0 -55
  210. data/lib/spec_id/filter.rb +0 -797
  211. data/lib/spec_id/precision.rb +0 -421
  212. data/lib/toppred.rb +0 -18
  213. data/script/filter-peps.rb +0 -164
  214. data/test/tc_aa_freqs.rb +0 -59
  215. data/test/tc_fasta_shaker.rb +0 -149
  216. data/test/tc_filter.rb +0 -203
  217. data/test/tc_filter_peps.rb +0 -46
  218. data/test/tc_gi.rb +0 -17
  219. data/test/tc_id_class_anal.rb +0 -70
  220. data/test/tc_id_precision.rb +0 -89
  221. data/test/tc_msrun.rb +0 -88
  222. data/test/tc_mzxml.rb +0 -88
  223. data/test/tc_mzxml_to_lmat.rb +0 -36
  224. data/test/tc_peptide_parent_times.rb +0 -27
  225. data/test/tc_precision.rb +0 -60
  226. data/test/tc_roc.rb +0 -166
  227. data/test/tc_sample_enzyme.rb +0 -32
  228. data/test/tc_scan.rb +0 -26
  229. data/test/tc_sequest.rb +0 -336
  230. data/test/tc_spec.rb +0 -78
  231. data/test/tc_spec_id.rb +0 -201
  232. data/test/tc_spec_id_xml.rb +0 -36
  233. data/test/tc_srf.rb +0 -262
data/test_files/bioworks31.params ADDED
@@ -0,0 +1,77 @@
1
+ [SEQUEST]
2
+ first_database_name = C:\Xcalibur\database\ecoli_K12.fasta
3
+ second_database_name =
4
+ peptide_mass_tolerance = 1.5000
5
+ ion_series = 0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0
6
+ fragment_ion_tolerance = 0.0000 ; leave at 0.0 unless you have real poor data
7
+ num_output_lines = 10 ; # peptide results to show
8
+ num_results = 500 ; # results to store
9
+ num_description_lines = 5 ; # full protein descriptions to show for top N peptides
10
+ show_fragment_ions = 1 ; 0=no, 1=yes
11
+ print_duplicate_references = 40 ; 0=no, 1=yes
12
+ enzyme_number = 1
13
+ max_num_differential_AA_per_mod = 4 ; max # of modified AA per diff. mod in a peptide
14
+ diff_search_options = 0.0000 S 0.0000 C 0.0000 M 0.0000 X 0.0000 T 0.0000 Y
15
+ term_diff_search_options = 0.0000 0.0000
16
+ nucleotide_reading_frame = 0 ; 0=protein db, 1-6, 7 = forward three, 8-reverse three, 9=all six
17
+ mass_type_parent = 0 ; 0=average masses, 1=monoisotopic masses
18
+ mass_type_fragment = 0 ; 0=average masses, 1=monoisotopic masses
19
+ normalize_xcorr = 0 ; use normalized xcorr values in the out file
20
+ remove_precursor_peak = 0 ; 0=no, 1=yes
21
+ ion_cutoff_percentage = 0.0000 ; prelim. score cutoff % as a decimal number i.e. 0.30 for 30%
22
+ max_num_internal_cleavage_sites = 2 ; maximum value is 5
23
+ protein_mass_filter = 0 0 ; enter protein mass min & max value ( 0 for both = unused)
24
+ match_peak_count = 0 ; number of auto-detected peaks to try matching (max 5)
25
+ match_peak_allowed_error = 1 ; number of allowed errors in matching auto-detected peaks
26
+ match_peak_tolerance = 1.0000 ; mass tolerance for matching auto-detected peaks
27
+ create_output_files = 1 ; 0=no, 1=yes
28
+ partial_sequence =
29
+ sequence_header_filter =
30
+
31
+ add_Cterm_peptide = 0.0000 ; added to each peptide C-terminus
32
+ add_Cterm_protein = 0.0000 ; added to each protein C-terminus
33
+ add_Nterm_peptide = 0.0000 ; added to each peptide N-terminus
34
+ add_Nterm_protein = 0.0000 ; added to each protein N-terminus
35
+ add_G_Glycine = 0.0000 ; added to G - avg. 57.0519, mono. 57.02146
36
+ add_A_Alanine = 0.0000 ; added to A - avg. 71.0788, mono. 71.03711
37
+ add_S_Serine = 0.0000 ; added to S - avg. 87.0782, mono. 87.02303
38
+ add_P_Proline = 0.0000 ; added to P - avg. 97.1167, mono. 97.05276
39
+ add_V_Valine = 0.0000 ; added to V - avg. 99.1326, mono. 99.06841
40
+ add_T_Threonine = 0.0000 ; added to T - avg. 101.1051, mono. 101.04768
41
+ add_C_Cysteine = 0.0000 ; added to C - avg. 103.1388, mono. 103.00919
42
+ add_L_Leucine = 0.0000 ; added to L - avg. 113.1594, mono. 113.08406
43
+ add_I_Isoleucine = 0.0000 ; added to I - avg. 113.1594, mono. 113.08406
44
+ add_X_LorI = 0.0000 ; added to X - avg. 113.1594, mono. 113.08406
45
+ add_N_Asparagine = 0.0000 ; added to N - avg. 114.1038, mono. 114.04293
46
+ add_O_Ornithine = 0.0000 ; added to O - avg. 114.1472, mono 114.07931
47
+ add_B_avg_NandD = 0.0000 ; added to B - avg. 114.5962, mono. 114.53494
48
+ add_D_Aspartic_Acid = 0.0000 ; added to D - avg. 115.0886, mono. 115.02694
49
+ add_Q_Glutamine = 0.0000 ; added to Q - avg. 128.1307, mono. 128.05858
50
+ add_K_Lysine = 0.0000 ; added to K - avg. 128.1741, mono. 128.09496
51
+ add_Z_avg_QandE = 0.0000 ; added to Z - avg. 128.6231, mono. 128.55059
52
+ add_E_Glutamic_Acid = 0.0000 ; added to E - avg. 129.1155, mono. 129.04259
53
+ add_M_Methionine = 0.0000 ; added to M - avg. 131.1926, mono. 131.04049
54
+ add_H_Histidine = 0.0000 ; added to H - avg. 137.1411, mono. 137.05891
55
+ add_F_Phenylalanine = 0.0000 ; added to F - avg. 147.1766, mono. 147.06841
56
+ add_R_Arginine = 0.0000 ; added to R - avg. 156.1875, mono. 156.10111
57
+ add_Y_Tyrosine = 0.0000 ; added to Y - avg. 163.1760, mono. 163.06333
58
+ add_W_Tryptophan = 0.0000 ; added to W - avg. 186.2132, mono. 186.07931
59
+
60
+ [SEQUEST_ENZYME_INFO]
61
+ 0. No_Enzyme 0 - -
62
+ 1. Trypsin 1 KR -
63
+ 2. Trypsin(KRLNH) 1 KRLNH -
64
+ 3. Chymotrypsin 1 FWYL -
65
+ 4. Chymotrypsin(FWY) 1 FWY P
66
+ 5. Clostripain 1 R -
67
+ 6. Cyanogen_Bromide 1 M -
68
+ 7. IodosoBenzoate 1 W -
69
+ 8. Proline_Endopept 1 P -
70
+ 9. Staph_Protease 1 E -
71
+ 10. Trypsin_K 1 K P
72
+ 11. Trypsin_R 1 R P
73
+ 12. GluC 1 ED -
74
+ 13. LysC 1 K -
75
+ 14. AspN 0 D -
76
+ 15. Elastase 1 ALIV P
77
+ 16. Elastase/Tryp/Chymo 1 ALIVKRWFY P
data/test_files/bioworks32.params ADDED
@@ -0,0 +1,62 @@
1
+ [SEQUEST]
2
+ first_database_name = C:\Xcalibur\database\ecoli_K12_ncbi_20060321.fasta
3
+ second_database_name =
4
+ peptide_mass_tolerance = 1.4000
5
+ peptide_mass_units = 0 ; 0=amu, 1=mmu, 2=ppm
6
+ ion_series = 0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0
7
+ fragment_ion_tolerance = 1.0000 ; for trap data leave at 1.0, for accurate mass data use values < 1.0
8
+ num_output_lines = 10 ; # peptide results to show
9
+ num_results = 250 ; # results to store
10
+ num_description_lines = 5 ; # full protein descriptions to show for top N peptides
11
+ show_fragment_ions = 0 ; 0=no, 1=yes
12
+ print_duplicate_references = 40 ; number of duplicate references reported
13
+ enzyme_info = Trypsin(KR/P) 1 1 KR P
14
+ max_num_differential_per_peptide = 1 ; max # of diff. mod in a peptide
15
+ diff_search_options = 0.000000 S 0.000000 C 0.000000 M 0.000000 X 0.000000 T 0.000000 Y
16
+ term_diff_search_options = 0.000000 0.000000
17
+ nucleotide_reading_frame = 0 ; 0=protein db, 1-6, 7 = forward three, 8-reverse three, 9=all six
18
+ mass_type_parent = 0 ; 0=average masses, 1=monoisotopic masses
19
+ mass_type_fragment = 0 ; 0=average masses, 1=monoisotopic masses
20
+ normalize_xcorr = 0 ; use normalized xcorr values in the out file
21
+ remove_precursor_peak = 0 ; 0=no, 1=yes
22
+ ion_cutoff_percentage = 0.0000 ; prelim. score cutoff % as a decimal number i.e. 0.30 for 30%
23
+ max_num_internal_cleavage_sites = 2 ; maximum value is 12
24
+ protein_mass_filter = 0 0 ; enter protein mass min & max value ( 0 for both = unused)
25
+ match_peak_count = 0 ; number of auto-detected peaks to try matching (max 5)
26
+ match_peak_allowed_error = 1 ; number of allowed errors in matching auto-detected peaks
27
+ match_peak_tolerance = 1.0000 ; mass tolerance for matching auto-detected peaks
28
+ partial_sequence =
29
+ sequence_header_filter =
30
+ digest_mass_range = 600.0 3500.0
31
+
32
+ add_Cterm_peptide = 0.0000 ; added to each peptide C-terminus
33
+ add_Cterm_protein = 0.0000 ; added to each protein C-terminus
34
+ add_Nterm_peptide = 0.0000 ; added to each peptide N-terminus
35
+ add_Nterm_protein = 0.0000 ; added to each protein N-terminus
36
+ add_G_Glycine = 0.0000 ; added to G
37
+ add_A_Alanine = 0.0000 ; added to A
38
+ add_S_Serine = 0.0000 ; added to S
39
+ add_P_Proline = 0.0000 ; added to P
40
+ add_V_Valine = 0.0000 ; added to V
41
+ add_T_Threonine = 0.0000 ; added to T
42
+ add_C_Cysteine = 0.0000 ; added to C
43
+ add_L_Leucine = 0.0000 ; added to L
44
+ add_I_Isoleucine = 0.0000 ; added to I
45
+ add_X_LorI = 0.0000 ; added to X
46
+ add_N_Asparagine = 0.0000 ; added to N
47
+ add_O_Ornithine = 0.0000 ; added to O
48
+ add_B_avg_NandD = 0.0000 ; added to B
49
+ add_D_Aspartic_Acid = 0.0000 ; added to D
50
+ add_Q_Glutamine = 0.0000 ; added to Q
51
+ add_K_Lysine = 0.0000 ; added to K
52
+ add_Z_avg_QandE = 0.0000 ; added to Z
53
+ add_E_Glutamic_Acid = 0.0000 ; added to E
54
+ add_M_Methionine = 0.0000 ; added to M
55
+ add_H_Histidine = 0.0000 ; added to H
56
+ add_F_Phenylalanine = 0.0000 ; added to F
57
+ add_R_Arginine = 0.0000 ; added to R
58
+ add_Y_Tyrosine = 0.0000 ; added to Y
59
+ add_W_Tryptophan = 0.0000 ; added to W
60
+ add_J_user_amino_acid = 0.0000 ; added to J
61
+ add_U_user_amino_acid = 0.0000 ; added to U
62
+
data/test_files/bioworks33.params ADDED
@@ -0,0 +1,63 @@
1
+ [SEQUEST]
2
+ first_database_name = C:\Xcalibur\database\yeast.fasta
3
+ second_database_name =
4
+ peptide_mass_tolerance = 2.0000
5
+ peptide_mass_units = 0 ; 0=amu, 1=mmu, 2=ppm
6
+ ion_series = 0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0
7
+ fragment_ion_tolerance = 1.0000 ; for trap data leave at 1.0, for accurate mass data use values < 1.0
8
+ fragment_ion_units = 0 ; 0=amu, 1=mmu
9
+ num_output_lines = 10 ; # peptide results to show
10
+ num_results = 250 ; # results to store
11
+ num_description_lines = 5 ; # full protein descriptions to show for top N peptides
12
+ show_fragment_ions = 0 ; 0=no, 1=yes
13
+ print_duplicate_references = 0 ; number of duplicate references reported
14
+ enzyme_info = Trypsin(KR) 1 1 KR -
15
+ max_num_differential_per_peptide = 3 ; max # of diff. mod in a peptide
16
+ diff_search_options = 0.0000 S 0.0000 C 0.0000 M 0.0000 X 0.0000 T 0.0000 Y
17
+ term_diff_search_options = 0.0000 0.0000
18
+ nucleotide_reading_frame = 0 ; 0=protein db, 1-6, 7 = forward three, 8-reverse three, 9=all six
19
+ mass_type_parent = 1 ; 0=average masses, 1=monoisotopic masses
20
+ mass_type_fragment = 1 ; 0=average masses, 1=monoisotopic masses
21
+ normalize_xcorr = 0 ; use normalized xcorr values in the out file
22
+ remove_precursor_peak = 0 ; 0=no, 1=yes
23
+ ion_cutoff_percentage = 0.0000 ; prelim. score cutoff % as a decimal number i.e. 0.30 for 30%
24
+ max_num_internal_cleavage_sites = 2 ; maximum value is 12
25
+ protein_mass_filter = 0 0 ; enter protein mass min & max value ( 0 for both = unused)
26
+ match_peak_count = 0 ; number of auto-detected peaks to try matching (max 5)
27
+ match_peak_allowed_error = 1 ; number of allowed errors in matching auto-detected peaks
28
+ match_peak_tolerance = 1.0000 ; mass tolerance for matching auto-detected peaks
29
+ partial_sequence =
30
+ sequence_header_filter =
31
+ digest_mass_range = 600.0000 4500.0000
32
+
33
+ add_Cterm_peptide = 0.0000 ; added to each peptide C-terminus
34
+ add_Cterm_protein = 0.0000 ; added to each protein C-terminus
35
+ add_Nterm_peptide = 0.0000 ; added to each peptide N-terminus
36
+ add_Nterm_protein = 0.0000 ; added to each protein N-terminus
37
+ add_G_Glycine = 0.0000 ; added to G
38
+ add_A_Alanine = 0.0000 ; added to A
39
+ add_S_Serine = 0.0000 ; added to S
40
+ add_P_Proline = 0.0000 ; added to P
41
+ add_V_Valine = 0.0000 ; added to V
42
+ add_T_Threonine = 0.0000 ; added to T
43
+ add_C_Cysteine = 0.0000 ; added to C
44
+ add_L_Leucine = 0.0000 ; added to L
45
+ add_I_Isoleucine = 0.0000 ; added to I
46
+ add_X_LorI = 0.0000 ; added to X
47
+ add_N_Asparagine = 0.0000 ; added to N
48
+ add_O_Ornithine = 0.0000 ; added to O
49
+ add_B_avg_NandD = 0.0000 ; added to B
50
+ add_D_Aspartic_Acid = 0.0000 ; added to D
51
+ add_Q_Glutamine = 0.0000 ; added to Q
52
+ add_K_Lysine = 0.0000 ; added to K
53
+ add_Z_avg_QandE = 0.0000 ; added to Z
54
+ add_E_Glutamic_Acid = 0.0000 ; added to E
55
+ add_M_Methionine = 0.0000 ; added to M
56
+ add_H_Histidine = 0.0000 ; added to H
57
+ add_F_Phenylalanine = 0.0000 ; added to F
58
+ add_R_Arginine = 0.0000 ; added to R
59
+ add_Y_Tyrosine = 0.0000 ; added to Y
60
+ add_W_Tryptophan = 0.0000 ; added to W
61
+ add_J_user_amino_acid = 0.0000 ; added to J
62
+ add_U_user_amino_acid = 0.0000 ; added to U
63
+