Mercurial > repos > jjohnson > msfragger

comparison msfragger.xml @ 0:9cbe178a3e3c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author jjohnson
date Tue, 29 Aug 2017 14:30:36 -0400
parents
children a2e41fca9e39
comparison
equal deleted inserted replaced
-1:000000000000 0:9cbe178a3e3c
1 <tool id="msfragger" name="MSFragger" version="1.0.0">
2 <description>search for peptide identifications in mass spectrometry proteomics</description>
3 <command>
4 <![CDATA[
5 #import re
6 ## Is file naming going to be a problem? May need to have a name param
7 #set $param_file = 'fragger.params'
8 cat $fragger_params > '$param_file'
9 ##
10 && echo " " >> '$param_file'
11 && echo "num_threads = \$GALAXY_SLOTS" >> '$param_file'
12 && cat $param_file > '$output_params'
13 && cat /Users/jj/gxt/gxt/database/files/009/dataset_9448.dat > Uniprot.20151009.Hs.revDecoys.fa
14 #if $input.extension == 'mzml':
15 #set $file_ext = 'mzML'
16 #elif $input.extension == 'mzxml':
17 #set $file_ext = 'mzXML'
18 #elif $input.extension == 'mgf':
19 #set $file_ext = 'mgf'
20 #end if
21 #if $input_prefix and len($input_prefix.strip()) > 0:
22 #set $input_path = $input_prefix.__str__ + "_rep" + str($i + 1) + "." + $file_ext
23 #else:
24 #set $input_path = $re.sub('\.[mM]\w+$','',$re.sub('[^-a-zA-Z0-9_.]','_',$input.name)) + "." + $file_ext
25 #end if
26 && ln -s '${input}' '$input_path'
27 && java -Xmx8G -jar $__tool_directory__/MSFragger.jar fragger.params '$input_path'
28 ## && cat *.log
29 >> "$logfile"
30 #if $output_format == 'pepXML':
31 && cat *.pep.xml > $output_pepxml
32 #else
33 && cat *.tsv > $output_tsv
34 #end if
35 ]]>
36 </command>
37 <configfiles>
38 <configfile name="fragger_params"><![CDATA[#slurp
39 #import re
40 database_name = $database ## Uniprot.20151009.Hs.revDecoys.fa
41 ## num_threads = 0 ## 0=poll CPU to set num threads; else specify num threads directly (max 64)
42
43 ## Search Tolerances
44
45 precursor_mass_tolerance = #if str( $search_tolerances.mass.precursor_mass_tolerance ) then $search_tolerances.mass.precursor_mass_tolerance else 500.00#
46 precursor_mass_units = #if $search_tolerances.mass.units == 'Da' then 0 else 1# ## 0=Daltons, 1=ppm
47 precursor_true_tolerance = #if str( $search_tolerances.mass.precursor_true_tolerance ) then $search_tolerances.mass.precursor_true_tolerance else 20.00#
48 precursor_true_units = #if $search_tolerances.mass.units == 'Da' then 0 else 1# ## 0=Daltons, 1=ppm
49 fragment_mass_tolerance = #if str( $search_tolerances.mass.fragment_mass_tolerance ) then $search_tolerances.mass.fragment_mass_tolerance else 20.00#
50 fragment_mass_units = #if $search_tolerances.mass.units == 'Da' then 0 else 1# ## 0=Daltons, 1=ppm
51 isotope_error = $search_tolerances.isotope_error ## 0=off, 0/1/2 (standard C13 error)
52
53 ## digest parameters
54
55 search_enzyme_name = #if $digestion.search_enzyme_name then $digestion.search_enzyme_name else 'Trypsin'# ## Trypsin
56 search_enzyme_cutafter = #if $digestion.search_enzyme_cutafter then $digestion.search_enzyme_cutafter else 'KR'# ##KR
57 search_enzyme_butnotafter = #if $digestion.search_enzyme_butnotafter then $digestion.search_enzyme_butnotafter else 'P'# ##P
58
59 num_enzyme_termini = $digestion.num_enzyme_termini ## 2 for enzymatic, 1 for semi-enzymatic, 0 for nonspecific digestion
60 allowed_missed_cleavage = #if $digestion.allowed_missed_cleavage then $digestion.allowed_missed_cleavage else 1# ## maximum value is 5
61
62 digest_min_length = #if $digestion.digest_min_length then $digestion.digest_min_length else 7#
63 digest_max_length = #if $digestion.digest_max_length then $digestion.digest_max_length else 50#
64 digest_mass_range = #if str( $digestion.digest_mass_range_min ) then $digestion.digest_mass_range_min else 500.0# #if $digestion.digest_mass_range_max is not None then $digestion.digest_mass_range_max else 5000.0# ## MH+ peptide mass range to analyze
65
66
67 ## Variable Modification Parameters
68
69 clip_nTerm_M = $variable_modification.clip_nTerm_M
70
71 ##maximum of 7 mods - amino acid codes, * for any amino acid, [ and ] specifies protein termini, n and c specifies peptide termini
72 ##variable_mod_01 = 15.9949 M
73 ##variable_mod_02 = 42.0106 [*
74 ##variable_mod_03 = 79.96633 STY
75 ##variable_mod_03 = -17.0265 nQnC
76 ##variable_mod_04 = -18.0106 nE
77
78 allow_multiple_variable_mods_on_residue = $variable_modification.allow_multiple_variable_mods_on_residue ## static mods are not considered
79 max_variable_mods_per_mod = #if str( $variable_modification.max_variable_mods_per_mod ) then $variable_modification.max_variable_mods_per_mod else 3# ## maximum of 5
80 max_variable_mods_combinations = #if str( $variable_modification.max_variable_mods_combinations ) then $variable_modification.max_variable_mods_combinations else 1000# ## maximum of 65534, limits number of modified peptides generated from sequence
81
82 #set $vmods = $re.findall('([+-]?\d+[.]\d+\s\S+)',str($variable_modification.variable_mods))
83 #for i,vmod in enumerate($vmods):
84 variable_mod_0${int(i)+1} = $vmod
85 #end for
86
87 ##open search parameters
88 track_zero_topN = #if str( $open_search.track_zero_topN ) then $open_search.track_zero_topN else 0# ## in addition to topN results, keep track of top results in zero bin
89 zero_bin_accept_expect = #if str( $open_search.zero_bin_accept_expect ) then $open_search.zero_bin_accept_expect else 0# ## boost top zero bin entry to top if it has expect under 0.01 - set to 0 to disable
90 zero_bin_mult_expect = #if str( $open_search.zero_bin_mult_expect ) then $open_search.zero_bin_mult_expect else 1# ## disabled if above passes - multiply expect of zero bin for ordering purposes (does not affect reported expect)
91 add_topN_complementary = #if str( $open_search.add_topN_complementary ) then $open_search.add_topN_complementary else 0#
92
93 ## spectral processing
94
95 minimum_peaks = #if str( $spectrum_processing.minimum_peaks ) then $spectrum_processing.minimum_peaks else 15# ## required minimum number of peaks in spectrum to search (default 10)
96 use_topN_peaks = #if str( $spectrum_processing.use_topN_peaks ) then $spectrum_processing.use_topN_peaks else 100#
97
98
99 minimum_ratio = #if str($spectrum_processing.minimum_ratio) then $spectrum_processing.minimum_ratio else 0.01# ## filter peaks below this fraction of strongest peak
100
101 override_charge = $spectrum_processing.precursor.override_charge
102 #if $spectrum_processing.precursor.override_charge == 1
103 precursor_charge = $spectrum_processing.precursor.precursor_charge_min $spectrum_processing.precursor.precursor_charge_max ## precursor charge range to analyze; does not override any existing charge; 0 as 1st entry ignores parameter
104 #end if
105 max_fragment_charge = #if str( $spectrum_processing.max_fragment_charge ) then $spectrum_processing.max_fragment_charge else 2# ## set maximum fragment charge state to analyze (allowed max 5)
106 #if str( $spectrum_processing.clear.clear_mz_range_min ) or str( $spectrum_processing.clear.clear_mz_range_max )
107 clear_mz_range = #if str( $spectrum_processing.clear.clear_mz_range_min ) then $spectrum_processing.clear.clear_mz_range_min else 0.0# #if str( $spectrum_processing.clear.clear_mz_range_max ) then $spectrum_processing.clear.clear_mz_range_max else 0.0#
108 #else
109 clear_mz_range = 0.0 0.0 ## for iTRAQ/TMT type data; will clear out all peaks in the specified m/z range
110 #end if
111
112
113 min_fragments_modelling = #if str( $modeling_output.min_fragments_modelling ) then $modeling_output.min_fragments_modelling else 3#
114 min_matched_fragments = #if str( $modeling_output.min_matched_fragments ) then $modeling_output.min_matched_fragments else 6#
115 output_report_topN = #if $modeling_output.output_report_topN is not None then $modeling_output.output_report_topN else 1#
116 output_max_expect = #if str( $modeling_output.output_max_expect ) then $modeling_output.output_max_expect else 50.0#
117
118 output_file_extension = #if $output_format == 'pepXML' then 'pep.xml' else 'tsv'# ##pepXML
119 output_format = $output_format ##pepXML or tsv
120
121 ## additional modifications
122 static_modification
123 s/^\(add_[^ ]*\) = \([0-9.]*\)/\1 = #if str( $static_modification.\1 ) then $static_modification.\1 else \2#/
124
125 add_Cterm_peptide = #if str( $static_modification.add_Cterm_peptide ) then $static_modification.add_Cterm_peptide else 0.0#
126 add_Nterm_peptide = #if str( $static_modification.add_Nterm_peptide ) then $static_modification.add_Nterm_peptide else 0.0#
127 add_Cterm_protein = #if str( $static_modification.add_Cterm_protein ) then $static_modification.add_Cterm_protein else 0.0#
128 add_Nterm_protein = #if str( $static_modification.add_Nterm_protein ) then $static_modification.add_Nterm_protein else 0.0#
129 add_G_glycine = #if str( $static_modification.add_G_glycine ) then $static_modification.add_G_glycine else 0.0000# ## added to G - avg. 57.0513, mono. 57.02146
130 add_A_alanine = #if str( $static_modification.add_A_alanine ) then $static_modification.add_A_alanine else 0.0000# ## added to A - avg. 71.0779, mono. 71.03711
131 add_S_serine = #if str( $static_modification.add_S_serine ) then $static_modification.add_S_serine else 0.0000# ## added to S - avg. 87.0773, mono. 87.03203
132 add_P_proline = #if str( $static_modification.add_P_proline ) then $static_modification.add_P_proline else 0.0000# ## added to P - avg. 97.1152, mono. 97.05276
133 add_V_valine = #if str( $static_modification.add_V_valine ) then $static_modification.add_V_valine else 0.0000# ## added to V - avg. 99.1311, mono. 99.06841
134 add_T_threonine = #if str( $static_modification.add_T_threonine ) then $static_modification.add_T_threonine else 0.0000# ## added to T - avg. 101.1038, mono. 101.04768
135 add_C_cysteine = #if str( $static_modification.add_C_cysteine ) then $static_modification.add_C_cysteine else 0.0000# ## added to C - avg. 103.1429, mono. 103.00918
136 add_L_leucine = #if str( $static_modification.add_L_leucine ) then $static_modification.add_L_leucine else 0.0000# ## added to L - avg. 113.1576, mono. 113.08406
137 add_I_isoleucine = #if str( $static_modification.add_I_isoleucine ) then $static_modification.add_I_isoleucine else 0.0000# ## added to I - avg. 113.1576, mono. 113.08406
138 add_N_asparagine = #if str( $static_modification.add_N_asparagine ) then $static_modification.add_N_asparagine else 0.0000# ## added to N - avg. 114.1026, mono. 114.04293
139 add_D_aspartic_acid = #if str( $static_modification.add_D_aspartic_acid ) then $static_modification.add_D_aspartic_acid else 0.0000# ## added to D - avg. 115.0874, mono. 115.02694
140 add_Q_glutamine = #if str( $static_modification.add_Q_glutamine ) then $static_modification.add_Q_glutamine else 0.0000# ## added to Q - avg. 128.1292, mono. 128.05858
141 add_K_lysine = #if str( $static_modification.add_K_lysine ) then $static_modification.add_K_lysine else 0.0000# ## added to K - avg. 128.1723, mono. 128.09496
142 add_E_glutamic_acid = #if str( $static_modification.add_E_glutamic_acid ) then $static_modification.add_E_glutamic_acid else 0.0000# ## added to E - avg. 129.1140, mono. 129.04259
143 add_M_methionine = #if str( $static_modification.add_M_methionine ) then $static_modification.add_M_methionine else 0.0000# ## added to M - avg. 131.1961, mono. 131.04048
144 add_H_histidine = #if str( $static_modification.add_H_histidine ) then $static_modification.add_H_histidine else 0.0000# ## added to H - avg. 137.1393, mono. 137.05891
145 add_F_phenylalanine = #if str( $static_modification.add_F_phenylalanine ) then $static_modification.add_F_phenylalanine else 0.0000# ## added to F - avg. 147.1739, mono. 147.06841
146 add_R_arginine = #if str( $static_modification.add_R_arginine ) then $static_modification.add_R_arginine else 0.0000# ## added to R - avg. 156.1857, mono. 156.10111
147 add_Y_tyrosine = #if str( $static_modification.add_Y_tyrosine ) then $static_modification.add_Y_tyrosine else 0.0000# ## added to Y - avg. 163.0633, mono. 163.06333
148 add_W_tryptophan = #if str( $static_modification.add_W_tryptophan ) then $static_modification.add_W_tryptophan else 0.0000# ## added to W - avg. 186.0793, mono. 186.07931
149 #*
150 add_B_user_amino_acid = #if str( $static_modification.add_B_user_amino_acid ) then $static_modification.add_B_user_amino_acid else 0.0000# ## added to B - avg. 0.0000, mono. 0.00000
151 add_J_user_amino_acid = #if str( $static_modification.add_J_user_amino_acid ) then $static_modification.add_J_user_amino_acid else 0.0000# ## added to J - avg. 0.0000, mono. 0.00000
152 add_O_user_amino_acid = #if str( $static_modification.add_O_user_amino_acid ) then $static_modification.add_O_user_amino_acid else 0.0000# ## added to O - avg. 0.0000, mono 0.00000
153 add_U_user_amino_acid = #if str( $static_modification.add_U_user_amino_acid ) then $static_modification.add_U_user_amino_acid else 0.0000# ## added to U - avg. 0.0000, mono. 0.00000
154 add_X_user_amino_acid = #if str( $static_modification.add_X_user_amino_acid ) then $static_modification.add_X_user_amino_acid else 0.0000# ## added to X - avg. 0.0000, mono. 0.00000
155 add_Z_user_amino_acid = #if str( $static_modification.add_Z_user_amino_acid ) then $static_modification.add_Z_user_amino_acid else 0.0000# ## added to Z - avg. 0.0000, mono. 0.00000
156 *#
157 #slurp]]>
158 </configfile>
159 </configfiles>
160
161 <inputs>
162 <param name="input" type="data" format="mzml,mzxml" label="Proteomics Spectrum files in mzML or mzXML format"/>
163 <param name="input_prefix" type="text" value="" optional="true" label="File name prefix" help="Names inputs: prefix_rep#.mzXML Leave blank to use History names of inputs">
164 <validator type="regex" message="">[a-zA-Z][a-zA-Z0-9_-]*</validator>
165 </param>
166 <param name="database" type="data" format="fasta" label="Proteomics Search Database in FASTA format"/>
167 <section name="search_tolerances" expanded="false" title="Search Tolerances">
168 <conditional name="mass">
169 <param name="units" type="select" label="Set Mass tolerances" help="Sets default parameters">
170 <option value="Da">Daltons</option>
171 <option value="ppm">ppm</option>
172 </param>
173 <when value="Da">
174 <!-- Need to get correct defaults for Daltions -->
175 <param name="precursor_mass_tolerance" type="float" value="20" min="1" max="100" optional="true" label="Precursor mass tolerance"
176 help="Precursor mass tolerance (window is +/- this value) Default: 20"/>
177 <param name="precursor_true_tolerance" type="float" value="0" min="1" max="100" optional="true" label="Precursor true tolerance"
178 help="True precursor mass tolerance (window is +/- this value). Used for tie breaker of results (in spectrally ambiguous cases) and zero bin boosting in open searches (0 disables these features). This option is STRONGLY recommended for open searches. Default: 0"/>
179 <param name="fragment_mass_tolerance" type="float" value="20" min="1" max="100" optional="true" label="Fragment mass tolerance"
180 help="Fragment mass tolerance (window is +/- this value) Default: 20"/>
181 </when>
182 <when value="ppm">
183 <!-- Should these be integer for ppm? -->
184 <param name="precursor_mass_tolerance" type="float" value="20" min="1" max="100" optional="true" label="Precursor mass tolerance"
185 help="Precursor mass tolerance (window is +/- this value) Default: 20"/>
186 <param name="precursor_true_tolerance" type="float" value="0.0" min="0.0" max="100" optional="true" label="Precursor true tolerance"
187 help="True precursor mass tolerance (window is +/- this value). Used for tie breaker of results (in spectrally ambiguous cases) and zero bin boosting in open searches (0 disables these features). This option is STRONGLY recommended for open searches. Default: 0"/>
188 <param name="fragment_mass_tolerance" type="float" value="20" min="1" max="100" optional="true" label="Fragment mass tolerance"
189 help="Fragment mass tolerance (window is +/- this value) Default: 20"/>
190 </when>
191 </conditional>
192 <param name="isotope_error" type="select" label="isotope_error">
193 <help>
194 Isotope correction for MS/MS events triggered on isotopic peaks. Should be set to 0 (disabled) for open search or 0/1/2 for correction of narrow window searches. Shifts the precursor mass window to multiples of this value multiplied by the mass of C13-C12.
195 </help>
196 <option value="0">0 - Disabled (for open search)</option>
197 <option value="0/1/2">0/1/2 - (Correction for narrow window searches)</option>
198 </param>
199 </section>
200
201 <section name="digestion" expanded="false" title="In-silico Digestion Parameters">
202 <param name="search_enzyme_name" type="text" value="Trypsin" optional="true"
203 label="Digestion Enzyme" help="Name of enzyme to be written to the pepXML file."/>
204 <param name="search_enzyme_cutafter" type="text" value="" optional="true"
205 label="Residues after which the enzyme cuts" help="search_enzyme_cutafter Residues after which the enzyme cuts Default: KR"/>
206 <param name="search_enzyme_butnotafter" type="text" value="" optional="true"
207 label="Residues that the enzyme will not cut before" help="search_enzyme_butnotafter - (misnomer: should really be called butnotbefore) Default: P"/>
208 <param name="num_enzyme_termini" type="select" label="Number of enzyme termini">
209 <option value="0">0 - non-enzymatic</option>
210 <option value="1">1 - semi-enzymatic</option>
211 <option value="2">2 - fully-enzymatic</option>
212 </param>
213
214 <param name="allowed_missed_cleavage" type="integer" value="2" min="0" max="5" optional="true"
215 label="Allowed number of missed cleavages"/>
216 <param name="digest_min_length" type="integer" value="7" min="1" max="30" optional="true"
217 label="Minimum length of peptides to be generated during in-silico digestion"/>
218 <param name="digest_max_length" type="integer" value="64" min="10" max="100" optional="true"
219 label="Maximum length of peptides to be generated during in-silico digestion"/>
220 <param name="digest_mass_range_min" type="float" value="500.0" min="0.0" optional="true"
221 label="Minimum Mass of peptides to be generated during in-silico digestion in Daltons" />
222 <param name="digest_mass_range_max" type="float" value="5000.0" min="0.0" optional="true"
223 label="Maximum Mass of peptides to be generated during in-silico digestion in Daltons" />
224
225 </section>
226
227 <section name="variable_modification" expanded="false" title="Variable Modifications">
228 <param name="variable_mods" type="text" area="True" size="120x7" value="" optional="true"
229 label="">
230 <help><![CDATA[
231 Sets variable modifications. (variable_mod_01 to variable_mod_07). Space separated values with 1st value being the modification mass and the second being the residues (specified consecutively as a string) it modifies.
232 * is used to represent any amino acid [ is a modifier for protein N-terminal
233 ] is a modifier for protein C-terminal
234 n is a modifier for peptide N-terminal c is a modifier for peptide C-terminal
235 Syntax Examples:
236 15.9949 M (for oxidation on methionine)
237 79.66331 STY (for phosphorylation)
238 -17.0265 nQnC (for pyro-Glu or loss of ammonia at peptide N-terminal)
239 Example (M oxidation and N-terminal acetylation):
240 variable_mod_01 = 15.9949 M variable_mod_02 = 42.0106 [*
241 ]]></help>
242 <!-- regex working in python, but not webform -->
243 <validator type="regex">^(?ms)(([+-]?\d+[.]\d+\s\S+)(\s+[+-]?\d+[.]\d+\s\S+)*)?$</validator>
244 <sanitizer sanitize="False"/>
245 </param>
246 <param name="clip_nTerm_M" type="boolean" truevalue="1" falsevalue="0" checked="false"
247 label="Trim protein N-terminal methionine as a variable modification"/>
248 <param name="allow_multiple_variable_mods_on_residue" type="boolean" truevalue="1" falsevalue="0" checked="true"
249 label="Allow each amino acid to be modified by multiple variable modifications"/>
250 <param name="max_variable_mods_per_mod" type="integer" value="2" min="0" max="5" optional="true"
251 label="Maximum number of residues that can be occupied by each variable modification"/>
252 <param name="max_variable_mods_combinations" type="integer" value="5000" min="0" max="65534" optional="true"
253 label="Maximum allowed number of modified variably modified peptides from each peptide sequence"
254 help="If a greater number than the maximum is generated, only the unmodified peptide is considered."/>
255 </section>
256 <section name="static_modification" expanded="false" title="Static Modifications">
257 <param name="add_Cterm_peptide" type="float" value="" optional="true"
258 label="Statically add mass in Da to C-terminal of peptide Default: 0.0" />
259 <param name="add_Nterm_peptide" type="float" value="" optional="true"
260 label="Statically add mass in Da to N-terminal of peptide Default: 0.0" />
261 <param name="add_Cterm_protein" type="float" value="" optional="true"
262 label="Statically add mass in Da to C-terminal of protein Default: 0.0" />
263 <param name="add_Nterm_protein" type="float" value="" optional="true"
264 label="Statically add mass in Da to N-terminal of protein Default: 0.0" />
265 <param name="add_A_alanine" type="float" value="" optional="true"
266 label="Statically add mass in Da to A (alanine) Default: 0.0" />
267 <param name="add_R_arginine" type="float" value="" optional="true"
268 label="Statically add mass in Da to R (arginine) Default: 0.0" />
269 <param name="add_N_asparagine" type="float" value="" optional="true"
270 label="Statically add mass in Da to N (asparagine) Default: 0.0" />
271 <param name="add_D_aspartic_acid" type="float" value="" optional="true"
272 label="Statically add mass in Da to D (aspartic_acid) Default: 0.0" />
273 <param name="add_C_cysteine" type="float" value="" optional="true"
274 label="Statically add mass in Da to C (cysteine) Default: 0.0" />
275 <param name="add_E_glutamic_acid" type="float" value="" optional="true"
276 label="Statically add mass in Da to E (glutamic_acid) Default: 0.0" />
277 <param name="add_Q_glutamine" type="float" value="" optional="true"
278 label="Statically add mass in Da to Q (glutamine) Default: 0.0" />
279 <param name="add_G_glycine" type="float" value="" optional="true"
280 label="Statically add mass in Da to G (glycine) Default: 0.0" />
281 <param name="add_H_histidine" type="float" value="" optional="true"
282 label="Statically add mass in Da to H (histidine) Default: 0.0" />
283 <param name="add_I_isoleucine" type="float" value="" optional="true"
284 label="Statically add mass in Da to I (isoleucine) Default: 0.0" />
285 <param name="add_L_leucine" type="float" value="" optional="true"
286 label="Statically add mass in Da to L (leucine) Default: 0.0" />
287 <param name="add_K_lysine" type="float" value="" optional="true"
288 label="Statically add mass in Da to K (lysine) Default: 0.0" />
289 <param name="add_M_methionine" type="float" value="" optional="true"
290 label="Statically add mass in Da to M (methionine) Default: 0.0" />
291 <param name="add_F_phenylalanine" type="float" value="" optional="true"
292 label="Statically add mass in Da to F (phenylalanine) Default: 0.0" />
293 <param name="add_P_proline" type="float" value="" optional="true"
294 label="Statically add mass in Da to P (proline) Default: 0.0" />
295 <param name="add_S_serine" type="float" value="" optional="true"
296 label="Statically add mass in Da to S (serine) Default: 0.0" />
297 <param name="add_T_threonine" type="float" value="" optional="true"
298 label="Statically add mass in Da to T (threonine) Default: 0.0" />
299 <param name="add_W_tryptophan" type="float" value="" optional="true"
300 label="Statically add mass in Da to W (tryptophan) Default: 0.0" />
301 <param name="add_Y_tyrosine" type="float" value="" optional="true"
302 label="Statically add mass in Da to Y (tyrosine) Default: 0.0" />
303 <param name="add_V_valine" type="float" value="" optional="true"
304 label="Statically add mass in Da to V (valine) Default: 0.0" />
305 </section>
306 <section name="spectrum_processing" expanded="false" title="Spectrum Processing">
307 <param name="minimum_peaks" type="integer" value="10" min="0" optional="true"
308 label="Minimum number of peaks in experimental spectrum for matching" />
309 <param name="use_topN_peaks" type="integer" value="50" min="0" optional="true"
310 label="Pre-process experimental spectrum to only use top N peaks" />
311 <param name="minimum_ratio" type="float" value="" min="0.0" optional="true"
312 label="Filter peaks by minimum_ratio of base peak"
313 help="Filters out all peaks in experimental spectrum less intense than this multiple of the base peak intensit Default: 0.0" />
314
315 <param name="max_fragment_charge" type="integer" value="2" min="1" max="4" optional="true"
316 label="Maximum charge state for theoretical fragments to match (1-4)" />
317
318 <conditional name="precursor">
319 <param name="override_charge" type="select" label="Precursor Charge">
320 <option value="0">Use precursor charge</option>
321 <option value="1">Ignore precursor charge and set range</option>
322 </param>
323 <when value="0"/>
324 <when value="1">
325 <param name="precursor_charge_min" type="integer" value="1" min="0" max="6"
326 label="Minimum Potential Precursor Charge" />
327 <param name="precursor_charge_max" type="integer" value="4" min="0" max="8"
328 label="Maximum Potential Precursor Charge" />
329 </when>
330 </conditional>
331 <section name="clear" expanded="false" title="Clear mz range for iTRAQ/TMT experiments">
332 <param name="clear_mz_range_min" type="float" value="0.0" min="0.0" optional="true" label="Minimum of m/z range to remove" />
333 <param name="clear_mz_range_max" type="float" value="0.0" min="0.0" optional="true" label="Maximum of m/z range to remove" />
334 </section>
335 </section>
336 <section name="open_search" expanded="false" title="Open Search">
337 <param name="track_zero_topN" type="integer" value="" min="0" optional="true"
338 label="Track top N unmodified peptide results" >
339 <help>
340 Track top N unmodified peptide results separately from main results internally for boosting features.
341 Should be set to a number greater than output_report_topN if zero bin boosting is desired.
342 Default: 0
343 </help>
344 </param>
345 <param name="zero_bin_accept_expect" type="float" value="" min="0.0" optional="true"
346 label="Ranks a zero-bin hit above all non-zero-bin hit if it has expectation less than this value."
347 help="Default: 0.0" />
348 <param name="zero_bin_mult_expect" type="float" value="" min="0.0" optional="true"
349 label="Multiplies expect value of PSMs in the zero-bin during results ordering"
350 help="(set to less than 1 for boosting) Default: 1.0" />
351 <param name="add_topN_complementary" type="integer" value="" min="0" optional="true"
352 label="Insert complementary ions corresponding to the top N most intense fragments in each experimental spectra." >
353 <help>
354 Useful for recovery of modified peptides near C-terminal in open search.
355 Should be set to 0 (disabled) otherwise.
356 Default: 0
357 </help>
358 </param>
359
360 </section>
361 <section name="modeling_output" expanded="false" title="Modeling and Output">
362 <param name="min_fragments_modelling" type="integer" value="3" min="1" optional="true"
363 label="Minimum number of matched peaks in PSM for inclusion in statistical modeling Default:3" />
364 <param name="min_matched_fragments" type="integer" value="4" min="1" optional="true"
365 label="Minimum number of matched peaks for PSM to be reported Default:3"
366 help="recommend a minimum of 4 for narrow window searching and 6 for open searches"/>
367 <param name="output_report_topN" type="integer" value="1" min="1" optional="true"
368 label="Reports top N PSMs per input spectrum Default:1" />
369 <param name="output_max_expect" type="float" value="50.0" min="0.0" optional="true"
370 label="Suppresses reporting of PSM if top hit has expectation greater than this threshold" />
371 </section>
372 <param name="output_format" type="select" label="output format">
373 <option value="pepXML">pepXML</option>
374 <option value="tsv">Tabular</option>
375 </param>
376 </inputs>
377
378 <outputs>
379 <data format="txt" name="output_params" label="${tool.name}.params"/>
380 <data format="txt" name="logfile" label="${tool.name} log"/>
381 <data format="tsv" name="output_tsv" label="${tool.name}.tsv ${on_string}" >
382 <filter>output_format == 'tsv'</filter>
383 </data>
384 <data format="pepxml" name="output_pepxml" label="${tool.name}.pep.xml ${on_string}" >
385 <filter>output_format == 'pepXML'</filter>
386 </data>
387 </outputs>
388 <tests>
389 <test>
390 </test>
391 </tests>
392 <help>
393 <![CDATA[
394 =============
395 **MSFragger**
396 =============
397
398 MSFragger is an ultrafast database search tool for peptide identifications in mass spectrometry-based proteomics. It differs from conventional search engines by computing similarity scores in a fragment-centric fashion using a theoretical fragment index of candidate peptides. The speed of MSFragger makes it particularly suitable for `open' database searches, where the precursor mass tolerance is set to hundreds of Daltons, for the identification of modified peptides. MSFragger is implemented in the cross-platform Java programming language and is compatible with standard proteomics file formats such as MGF/mzXML/mzML/pepXML.
399
400
401 **Common Static Modifications**
402
403 ::
404
405 - methylation of K : 14.015650
406 - oxidation of M : 15.994915
407 - carboxymethyl C : 58.005479
408 - carbamidomethyl C : 57.021464
409 - deamidation of N and Q : 0.984016
410 - propionamide C : 71.037114
411 - phosphorylation of S : 79.966331
412 - phosphorylation of T : 79.966331
413 - phosphorylation of Y : 79.966331
414 - M cleavage from protein n-term : -131.040485
415 - acetylation of protein n-term : 42.010565
416 - methylation of protein n-term : 14.015650
417 - tri-methylation of protein n-term : 42.046950
418 - beta methythiolation of D : 45.987721
419 - methylation of Q : 14.015650
420 - tri-methylation of K : 42.046950
421 - methylation of D : 14.015650
422 - methylation of E : 14.015650
423 - methylation of peptide c-term : 14.015650
424 - tri-deuteromethylation of D : 17.034480
425 - tri-deuteromethylation of E : 17.034480
426 - tri-deuteromethylation of peptide c-term : 17.034480
427 - n-formyl met addition : 159.035399
428 - 2-amino-3-oxo-butanoic acid T : -2.015650
429 - acetylation of K : 42.010565
430 - amidation of peptide c-term : -0.984016
431 - beta-methylthiolation of D (duplicate of 13) : 45.987721
432 - carboxyamidomethylation of K : 57.021464
433 - carboxyamidomethylation of H : 57.021464
434 - carboxyamidomethylation of D : 57.021464
435 - carboxyamidomethylation of E : 57.021464
436 - carbamylation of K : 43.005814
437 - carbamylation of n-term peptide : 43.005814
438 - citrullination of R : 0.984016
439 - oxidation of C to cysteic acid : 47.984744
440 - di-iodination of Y : 251.793296
441 - di-methylation of K : 28.031300
442 - di-methylation of R : 28.031300
443 - di-methylation of peptide n-term : 28.031300
444 - oxidation of F to dihydroxyphenylalanine : 31.989829
445 - gammathiopropionylation of K : 87.998285
446 - gammathiopropionylation of peptide n-term : 87.998285
447 - farnesylation of C : 204.187801
448 - formylation of K : 27.994915
449 - formylation of peptide n-term : 27.994915
450 - oxidation of W to formylkynurenin : 31.989829
451 - fluorophenylalanine : 17.990578
452 - beta-carboxylation of D : 43.989829
453 - gamma-carboxylation of E : 43.989829
454 - geranyl-geranyl : 272.250401
455 - glucuronylation of protein n-term : 176.032088
456 - glutathione disulfide : 305.068156
457 - ubiquitinylation residue : 114.042927
458 - guanidination of K : 42.021798
459 - oxidation of H to N : -23.015984
460 - oxidation of H to D : -22.031969
461 - homoserine : -29.992806
462 - homoserine lactone : -48.003371
463 - oxidation of W to hydroxykynurenin : 19.989829
464 - hydroxylation of D : 15.994915
465 - hydroxylation of K : 15.994915
466 - hydroxylation of N : 15.994915
467 - hydroxylation of P : 15.994915
468 - hydroxylation of F : 15.994915
469 - hydroxylation of Y : 15.994915
470 - iodination of Y : 125.896648
471 - oxidation of W to kynurenin : 3.994915
472 - lipoyl K : 188.032956
473 - methyl ester of peptide c-term (duplicate of 18) : 14.015650
474 - methyl ester of D : 14.015650
475 - methyl ester of E (duplicate of 17) : 14.015650
476 - methyl ester of S : 14.015650
477 - methyl ester of Y : 14.015650
478 - methyl C : 14.015650
479 - methyl H : 14.015650
480 - methyl N : 14.015650
481 - methylation of peptide n-term : 14.015650
482 - methyl R : 14.015650
483 - myristoleylation of G : 208.182715
484 - myristoyl-4H of G : 206.167065
485 - myristoylation of peptide n-term G : 210.198366
486 - myristoylation of K : 210.198366
487 - formylation of protein n-term : 27.994915
488 - NEM C : 125.047679
489 - NIPCAM : 99.068414
490 - oxidation of W to nitro : 44.985078
491 - oxidation of Y to nitro : 44.985078
492 - O18 on peptide n-term : 2.004246
493 - di-O18 on peptide n-term : 4.008490
494 - oxidation of H : 15.994915
495 - oxidation of W : 15.994915
496 - phosphopantetheine S : 340.085794
497 - palmitoylation of C : 238.229666
498 - palmitoylation of K : 238.229666
499 - palmitoylation of S : 238.229666
500 - palmitoylation of T : 238.229666
501 - phosphorylation of S with prompt loss : -18.010565
502 - phosphorylation of T with prompt loss : -18.010565
503 - phosphorylation with prompt loss on Y : -18.010565
504 - phosphorylation with neutral loss on C : 79.966331
505 - phosphorylation with neutral loss on D : 79.966331
506 - phosphorylation with neutral loss on H : 79.966331
507 - propionyl light K : 56.026215
508 - propionyl light on peptide n-term : 56.026215
509 - propionyl heavy K : 59.036279
510 - propionyl heavy peptide n-term : 59.036279
511 - pyridyl K : 119.037114
512 - pyridyl peptide n-term : 119.037114
513 - pyro-cmC : -17.026549
514 - pyro-glu from n-term E : -18.010565
515 - pyro-glu from n-term Q : -17.026549
516 - oxidation of P to pyroglutamic acid : 13.979265
517 - s-pyridylethylation of C : 105.057849
518 - SeMet : 47.944449
519 - sulfation of Y : 79.956815
520 - sulphone of M : 31.989829
521 - tri-iodination of Y : 377.689944
522 - tri-methylation of R : 42.046950
523 - n-acyl diglyceride cysteine : 788.725777
524 - ICAT light : 227.126991
525 - ICAT heavy : 236.157185
526 - CAMthiopropanoyl K : 145.019749
527 - phosphorylation with neutral loss on S : 79.966331
528 - phosphorylation with neutral loss on T : 79.966331
529 - phosphorylation of S with ETD loss : 79.966331
530 - phosphorylation of T with ETD loss : 79.966331
531 - heavy arginine-13C6 : 6.020129
532 - heavy arginine-13C6-15N4 : 10.008269
533 - heavy lysine-13C6 : 6.020129
534 - PNGasF in O18 water : 2.988261
535 - beta elimination of S : -18.010565
536 - beta elimination of T : -18.010565
537 - oxidation of C to sulfinic acid : 31.989829
538 - arginine to ornithine : -42.021798
539 - dehydro of S and T : -18.010565
540 - carboxykynurenin of W : 47.984744
541 - sumoylation of K : 484.228200
542 - iTRAQ114 on nterm : 144.105918
543 - iTRAQ114 on K : 144.105918
544 - iTRAQ114 on Y : 144.105918
545 - iTRAQ115 on nterm : 144.099599
546 - iTRAQ115 on K : 144.099599
547 - iTRAQ115 on Y : 144.099599
548 - iTRAQ116 on nterm : 144.102063
549 - iTRAQ116 on K : 144.102063
550 - iTRAQ116 on Y : 144.102063
551 - iTRAQ117 on nterm : 144.102063
552 - iTRAQ117 on K : 144.102063
553 - iTRAQ117 on Y : 144.102063
554 - MMTS on C : 45.987721
555 - heavy lysine - 2H4 : 4.025107
556 - heavy lysine - 13C6 15N2 : 8.014199
557 - Asparagine HexNAc : 203.079373
558 - Asparagine dHexHexNAc : 349.137281
559 - Serine HexNAc : 203.079373
560 - Threonine HexNAc : 203.079373
561 - palmitoleyl of S : 236.214016
562 - palmitoleyl of C : 236.214016
563 - palmitoleyl of T : 236.214016
564 - CHD2-di-methylation of K : 32.056407
565 - CHD2-di-methylation of peptide n-term : 32.056407
566 - Maleimide-PEO2-Biotin of C : 525.225719
567 - phosphorylation of H : 79.966331
568 - oxidation of C : 15.994915
569 - oxidation of Y (duplicate of 64) : 15.994915
570 - Uniblue A on K : 484.039891
571 - deamidation of N : 0.984016
572 - trideuteration of L (SILAC) : 3.018830
573 - TMT duplex on K : 225.155833
574 - TMT duplex on n-term peptide : 225.155833
575 - TMT 6-plex on K : 229.162932
576 - TMT 6-plex on n-term peptide : 229.162932
577 - iTRAQ8plex:13C(7)15N(1) on nterm : 304.205360
578 - iTRAQ8plex:13C(7)15N(1) on K : 304.205360
579 - iTRAQ8plex:13C(7)15N(1) on Y : 304.205360
580 - iTRAQ8plex:13C(6)15N(2) on nterm : 304.199040
581 - iTRAQ8plex:13C(6)15N(2) on K : 304.199040
582 - iTRAQ8plex:13C(6)15N(2) on Y : 304.199040
583 - selenocysteine : 47.944449
584 - carboxymethylated selenocysteine : 105.949928
585
586 ]]>
587 </help>
588 </tool>