|
5
|
1 <tool id="SAINT_preprocessing_v5" name="SAINT pre-processing">
|
|
|
2 <description></description>
|
|
|
3 <command interpreter="python">
|
|
60
|
4 #if (str($type_select.type) == 'Scaffold'):
|
|
62
|
5 SAINT_preprocessing.py $type_select.input $type_select.preybool $type_select.fasta_db $Inter_file $Prey_file
|
|
5
|
6 "
|
|
|
7 #for $ba in $bait
|
|
|
8 ${ba.bait1}
|
|
|
9 ${ba.assign}
|
|
|
10 ${ba.T_C}
|
|
|
11 #end for
|
|
|
12 "
|
|
62
|
13 $Bait_file \$INSTALL_RUN_PATH/ $type_select.bait_bool $type_select.bait_file_in
|
|
60
|
14 #elif (str($type_select.type) == 'MaxQuant'):
|
|
62
|
15 SAINT_preprocessing_mq_pep.py $type_select.input $type_select.preybool $type_select.fasta_db $Inter_file $Prey_file
|
|
5
|
16 "
|
|
|
17 #for $ba in $bait
|
|
|
18 ${ba.bait1}
|
|
|
19 ${ba.assign}
|
|
|
20 ${ba.T_C}
|
|
|
21 #end for
|
|
|
22 "
|
|
62
|
23 $Bait_file \$INSTALL_RUN_PATH/ $type_select.bait_bool $type_select.bait_file_in
|
|
60
|
24 #elif (str($type_select.type) == 'Peptideshaker'):
|
|
62
|
25 Protein_report_processing.py "$type_select.input" $Bait_file $type_select.use_metric $type_select.fasta_db $type_select.preybool
|
|
55
|
26 "
|
|
|
27 #for $ba in $bait
|
|
|
28 ${ba.bait1}
|
|
|
29 ${ba.assign}
|
|
|
30 ${ba.T_C}
|
|
|
31 #end for
|
|
|
32 "
|
|
62
|
33 \$INSTALL_RUN_PATH/ $type_select.bait_bool $type_select.bait_file_in $Inter_file $Prey_file
|
|
5
|
34 #end if
|
|
|
35 </command>
|
|
|
36 <requirements>
|
|
|
37 <requirement type="set_environment">INSTALL_RUN_PATH</requirement>
|
|
|
38 </requirements>
|
|
|
39 <inputs>
|
|
55
|
40 <conditional name="type_select">
|
|
60
|
41 <param type="select" name="type" label="Data Source">
|
|
55
|
42 <option value="MaxQuant">MaxQuant</option>
|
|
|
43 <option value="Scaffold">Scaffold</option>
|
|
|
44 <option value="Peptideshaker">Peptideshaker</option>
|
|
|
45 </param>
|
|
|
46 <when value="MaxQuant">
|
|
|
47 <param format="dat" name="input" type="data" label="MaxQuant peptides Output"/>
|
|
|
48 <param type="boolean" name="preybool" checked="true" label="Create Prey File"/>
|
|
|
49 <param type="data" name="fasta_db" format="fasta" label="Provide Uniprot Fasta database" optional="true"/>
|
|
|
50 <param name="bait_bool" type="boolean" checked="true" label="Are You Providing Your Own bait file?"/>
|
|
|
51 <param type="data" format="dat" name="bait_file_in" label="Bait File" optional="true"/>
|
|
59
|
52 </when>
|
|
55
|
53 <when value="Scaffold">
|
|
|
54 <param format="dat" name="input" type="data" label="Scaffold Output"/>
|
|
|
55 <param type="boolean" name="preybool" checked="true" label="Create Prey File"/>
|
|
|
56 <param type="data" name="fasta_db" format="fasta" label="Provide Uniprot Fasta database" optional="true"/>
|
|
|
57 <param name="bait_bool" type="boolean" checked="true" label="Are You Providing Your Own bait file?"/>
|
|
|
58 <param type="data" format="dat" name="bait_file_in" label="Bait File" optional="true"/>
|
|
|
59 </when>
|
|
|
60 <when value="Peptideshaker">
|
|
|
61 <param format="dat" name="input" type="data" label="Peptideshaker Output" multiple="true"/>
|
|
|
62 <param type="select" name="use_metric" label="Select Report File Value for Quantification">
|
|
|
63 <option value="Validated_Peptides">#Validated Peptides</option>
|
|
|
64 <option value="Peptides">#Peptides</option>
|
|
|
65 <option value="Unique">#Unique</option>
|
|
|
66 <option value="Validated_PSMs">#Validated PSMs</option>
|
|
|
67 <option value="PSMs">#PSMs</option>
|
|
|
68 </param>
|
|
|
69 <param type="boolean" name="preybool" checked="true" label="Create Prey File"/>
|
|
|
70 <param type="data" name="fasta_db" format="fasta" label="Provide Uniprot Fasta database" optional="true"/>
|
|
|
71 <param name="bait_bool" type="boolean" checked="true" label="Are You Providing Your Own bait file?"/>
|
|
|
72 <param type="data" format="dat" name="bait_file_in" label="Bait File" optional="true"/>
|
|
|
73 </when>
|
|
|
74 </conditional>
|
|
61
|
75 <repeat name="bait" title="Bait Create">
|
|
|
76 <param name="bait1" type="text" size="100" label="Bait"/>
|
|
|
77 <param name="assign" type="text" size="100" label="Group Assignment"/>
|
|
|
78 <param name="T_C" type="boolean" checked="true" label="Is this a Control?"/>
|
|
|
79 </repeat>
|
|
5
|
80 </inputs>
|
|
|
81 <outputs>
|
|
|
82 <data format="txt" name="Inter_file" label="Inter File"/>
|
|
|
83 <data format="txt" name="Prey_file" label="Prey File" />
|
|
|
84 <data format="txt" name="Bait_file" label="Bait File" />
|
|
|
85 </outputs>
|
|
|
86 <stdio>
|
|
52
|
87 <regex match="Error: bad bait"
|
|
|
88 source="stdout"
|
|
|
89 level="fatal"
|
|
|
90 description="Error: bad bait"/>
|
|
|
91 <regex match="IOError: [Errno 2] No such file or directory: './tukeys_output.txt'"
|
|
|
92 source="stderr"
|
|
|
93 level="fatal"
|
|
|
94 description="Error: Scaffold/MaxQuant mismatch. Check job settings."/>
|
|
|
95 <regex match="bait_temp_file = open(sys.argv[10], 'r')"
|
|
|
96 source="stderr"
|
|
|
97 level="fatal"
|
|
|
98 description="Error: Bait create settings mismatch. Check job settings."/>
|
|
5
|
99 <regex match="Error|error"
|
|
|
100 source="stdout"
|
|
|
101 level="fatal"
|
|
|
102 description="Unknown error"/>
|
|
|
103 <regex match="Error|error"
|
|
|
104 source="stderr"
|
|
|
105 level="fatal"
|
|
|
106 description="Unknown error"/>
|
|
|
107 </stdio>
|
|
|
108
|
|
|
109 <tests>
|
|
|
110 <test>
|
|
|
111 <param name="input" value="fa_gc_content_input.fa"/>
|
|
|
112 <output name="out_file1" file="fa_gc_content_output.txt"/>
|
|
|
113 </test>
|
|
|
114 </tests>
|
|
|
115 <help>
|
|
21
|
116 Pre-Processing
|
|
25
|
117 ^^^^^^^^^^^^^^
|
|
20
|
118
|
|
21
|
119 This tool will read in a Scaffold *Samples Report* file (tab-delimited
|
|
55
|
120 txt file), multiple Peptideshaker *Protein Report* files or a MaxQuant
|
|
|
121 *peptides.txt* file and process them to generate a *Bait File, Prey
|
|
|
122 File,* and *Inter File* for SAINTexpress analysis.
|
|
20
|
123
|
|
25
|
124 --------------
|
|
|
125
|
|
27
|
126 **1) MaxQuant or Scaffold**
|
|
20
|
127
|
|
21
|
128 APOSTL is able to recognize either a Scaffold *Samples Report* file
|
|
|
129 (tab-delimited txt file) or the *peptides.txt* file output in the
|
|
|
130 MaxQuant *txt* output folder. No modifications should be made to these
|
|
|
131 files. Please designate which one is being provided.
|
|
20
|
132
|
|
27
|
133 **2) Scaffold or MaxQuant File Input**
|
|
20
|
134
|
|
21
|
135 Select the corresponding *Samples Report* or *peptides.txt* here.
|
|
|
136
|
|
27
|
137 **3) Create Prey File**
|
|
5
|
138
|
|
20
|
139 Select whether or not you would like APOSTL to generate a prey file.
|
|
|
140
|
|
21
|
141 When making a prey file, APOSTL queries a user provided FASTA database
|
|
|
142 (see below) in order to extract protein amino acid lengths and gene
|
|
|
143 names. This may take several minutes depending on your computer and if
|
|
|
144 your Galaxy distribution is cluster enabled. Some users may want to run
|
|
|
145 SAINTexpress using the same data set while changing which baits are
|
|
|
146 considered test or control. It is useful to toggle **Create Prey File**
|
|
|
147 off in order to save time by circumventing this step as the same prey
|
|
|
148 file can be used for both SAINTexpress runs.
|
|
20
|
149
|
|
27
|
150 **4) Provide Uniprot FASTA database**
|
|
20
|
151
|
|
21
|
152 Please specify a FASTA file containing the protein sequence. You can
|
|
|
153 download the latest release of Uniprot's reviewed sequences (Swiss-Prot)
|
|
24
|
154 http://www.uniprot.org/downloads. For computing efficiency,
|
|
21
|
155 please limit your FASTA file to your species of interest. It is
|
|
|
156 generally advised to use the same FASTA database that was used for your
|
|
|
157 database searches during peptide and protein ID.
|
|
5
|
158
|
|
27
|
159 **5) Are You Providing Your Own Bait File?**
|
|
20
|
160
|
|
21
|
161 Users have two options for providing a *Bait* file. If you would like to
|
|
|
162 create your own *Bait* file, select Yes and designate the file below. If
|
|
|
163 you would like to use the **Bait Create** tool to create a *Bait* file
|
|
|
164 within Galaxy, please select No and proceed to the **Bait Create** tool.
|
|
20
|
165
|
|
27
|
166 **6) Bait File**
|
|
21
|
167
|
|
|
168 If you selected Yes above, please specify the *Bait* file you would like
|
|
|
169 to provide. If you selected No above, ignore this argument and proceed
|
|
|
170 to the **Bait Create** tool.
|
|
5
|
171
|
|
21
|
172 **Note:** Individual bait names must match to the sample names
|
|
|
173 within your Scaffold or MaxQuant output exactly and must contain no
|
|
|
174 whitespace characters (e.g. spaces) or dashes.
|
|
59
|
175
|
|
55
|
176 **Note:** When using Peptideshaker output the baits in the baitfile
|
|
|
177 need to be in the same order as the files selected.
|
|
5
|
178
|
|
27
|
179 **7) Bait Create**
|
|
21
|
180
|
|
|
181 Using the **Bait Create** tool, you can create your *bait.txt* file.
|
|
20
|
182
|
|
21
|
183 **Note:** Individual bait names must match to the sample names
|
|
|
184 within your Scaffold or MaxQuant output exactly and must contain no
|
|
|
185 whitespace characters (e.g. spaces) or dashes.
|
|
5
|
186
|
|
21
|
187 APOSTL uses this bait file to find the user's baits of interest within a
|
|
|
188 *Samples Report* or *peptides.txt* file and when preparing the
|
|
|
189 *inter.txt* file.
|
|
20
|
190
|
|
21
|
191 --------------
|
|
20
|
192
|
|
21
|
193 Once your parameters have been finalized, please press the Execute
|
|
|
194 button to start processing. This may take a few minutes. Once your
|
|
|
195 process has been completed, you will see your *Bait File, Prey File,*
|
|
|
196 and *Inter File* on the right hand side of your panel highlighted in
|
|
|
197 green.
|
|
5
|
198 </help>
|
|
|
199 </tool>
|
