annotate SAINT_preprocessing.xml @ 62:81db20bfc349 draft

Uploaded
author bornea
date Sat, 27 Aug 2016 21:42:13 -0400
parents 0b4450bdc6a9
children 1972ccdbeb16
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
1 <tool id="SAINT_preprocessing_v5" name="SAINT pre-processing">
3953103b56f9 Uploaded
bornea
parents:
diff changeset
2 <description></description>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
3 <command interpreter="python">
60
3c0ed536029e Uploaded
bornea
parents: 59
diff changeset
4 #if (str($type_select.type) == 'Scaffold'):
62
81db20bfc349 Uploaded
bornea
parents: 61
diff changeset
5 SAINT_preprocessing.py $type_select.input $type_select.preybool $type_select.fasta_db $Inter_file $Prey_file
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
6 "
3953103b56f9 Uploaded
bornea
parents:
diff changeset
7 #for $ba in $bait
3953103b56f9 Uploaded
bornea
parents:
diff changeset
8 ${ba.bait1}
3953103b56f9 Uploaded
bornea
parents:
diff changeset
9 ${ba.assign}
3953103b56f9 Uploaded
bornea
parents:
diff changeset
10 ${ba.T_C}
3953103b56f9 Uploaded
bornea
parents:
diff changeset
11 #end for
3953103b56f9 Uploaded
bornea
parents:
diff changeset
12 "
62
81db20bfc349 Uploaded
bornea
parents: 61
diff changeset
13 $Bait_file \$INSTALL_RUN_PATH/ $type_select.bait_bool $type_select.bait_file_in
60
3c0ed536029e Uploaded
bornea
parents: 59
diff changeset
14 #elif (str($type_select.type) == 'MaxQuant'):
62
81db20bfc349 Uploaded
bornea
parents: 61
diff changeset
15 SAINT_preprocessing_mq_pep.py $type_select.input $type_select.preybool $type_select.fasta_db $Inter_file $Prey_file
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
16 "
3953103b56f9 Uploaded
bornea
parents:
diff changeset
17 #for $ba in $bait
3953103b56f9 Uploaded
bornea
parents:
diff changeset
18 ${ba.bait1}
3953103b56f9 Uploaded
bornea
parents:
diff changeset
19 ${ba.assign}
3953103b56f9 Uploaded
bornea
parents:
diff changeset
20 ${ba.T_C}
3953103b56f9 Uploaded
bornea
parents:
diff changeset
21 #end for
3953103b56f9 Uploaded
bornea
parents:
diff changeset
22 "
62
81db20bfc349 Uploaded
bornea
parents: 61
diff changeset
23 $Bait_file \$INSTALL_RUN_PATH/ $type_select.bait_bool $type_select.bait_file_in
60
3c0ed536029e Uploaded
bornea
parents: 59
diff changeset
24 #elif (str($type_select.type) == 'Peptideshaker'):
62
81db20bfc349 Uploaded
bornea
parents: 61
diff changeset
25 Protein_report_processing.py "$type_select.input" $Bait_file $type_select.use_metric $type_select.fasta_db $type_select.preybool
55
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
26 "
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
27 #for $ba in $bait
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
28 ${ba.bait1}
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
29 ${ba.assign}
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
30 ${ba.T_C}
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
31 #end for
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
32 "
62
81db20bfc349 Uploaded
bornea
parents: 61
diff changeset
33 \$INSTALL_RUN_PATH/ $type_select.bait_bool $type_select.bait_file_in $Inter_file $Prey_file
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
34 #end if
3953103b56f9 Uploaded
bornea
parents:
diff changeset
35 </command>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
36 <requirements>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
37 <requirement type="set_environment">INSTALL_RUN_PATH</requirement>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
38 </requirements>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
39 <inputs>
55
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
40 <conditional name="type_select">
60
3c0ed536029e Uploaded
bornea
parents: 59
diff changeset
41 <param type="select" name="type" label="Data Source">
55
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
42 <option value="MaxQuant">MaxQuant</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
43 <option value="Scaffold">Scaffold</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
44 <option value="Peptideshaker">Peptideshaker</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
45 </param>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
46 <when value="MaxQuant">
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
47 <param format="dat" name="input" type="data" label="MaxQuant peptides Output"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
48 <param type="boolean" name="preybool" checked="true" label="Create Prey File"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
49 <param type="data" name="fasta_db" format="fasta" label="Provide Uniprot Fasta database" optional="true"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
50 <param name="bait_bool" type="boolean" checked="true" label="Are You Providing Your Own bait file?"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
51 <param type="data" format="dat" name="bait_file_in" label="Bait File" optional="true"/>
59
5ad68d3a11cc Uploaded
bornea
parents: 55
diff changeset
52 </when>
55
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
53 <when value="Scaffold">
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
54 <param format="dat" name="input" type="data" label="Scaffold Output"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
55 <param type="boolean" name="preybool" checked="true" label="Create Prey File"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
56 <param type="data" name="fasta_db" format="fasta" label="Provide Uniprot Fasta database" optional="true"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
57 <param name="bait_bool" type="boolean" checked="true" label="Are You Providing Your Own bait file?"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
58 <param type="data" format="dat" name="bait_file_in" label="Bait File" optional="true"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
59 </when>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
60 <when value="Peptideshaker">
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
61 <param format="dat" name="input" type="data" label="Peptideshaker Output" multiple="true"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
62 <param type="select" name="use_metric" label="Select Report File Value for Quantification">
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
63 <option value="Validated_Peptides">#Validated Peptides</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
64 <option value="Peptides">#Peptides</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
65 <option value="Unique">#Unique</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
66 <option value="Validated_PSMs">#Validated PSMs</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
67 <option value="PSMs">#PSMs</option>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
68 </param>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
69 <param type="boolean" name="preybool" checked="true" label="Create Prey File"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
70 <param type="data" name="fasta_db" format="fasta" label="Provide Uniprot Fasta database" optional="true"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
71 <param name="bait_bool" type="boolean" checked="true" label="Are You Providing Your Own bait file?"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
72 <param type="data" format="dat" name="bait_file_in" label="Bait File" optional="true"/>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
73 </when>
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
74 </conditional>
61
0b4450bdc6a9 Uploaded
bornea
parents: 60
diff changeset
75 <repeat name="bait" title="Bait Create">
0b4450bdc6a9 Uploaded
bornea
parents: 60
diff changeset
76 <param name="bait1" type="text" size="100" label="Bait"/>
0b4450bdc6a9 Uploaded
bornea
parents: 60
diff changeset
77 <param name="assign" type="text" size="100" label="Group Assignment"/>
0b4450bdc6a9 Uploaded
bornea
parents: 60
diff changeset
78 <param name="T_C" type="boolean" checked="true" label="Is this a Control?"/>
0b4450bdc6a9 Uploaded
bornea
parents: 60
diff changeset
79 </repeat>
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
80 </inputs>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
81 <outputs>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
82 <data format="txt" name="Inter_file" label="Inter File"/>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
83 <data format="txt" name="Prey_file" label="Prey File" />
3953103b56f9 Uploaded
bornea
parents:
diff changeset
84 <data format="txt" name="Bait_file" label="Bait File" />
3953103b56f9 Uploaded
bornea
parents:
diff changeset
85 </outputs>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
86 <stdio>
52
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
87 <regex match="Error: bad bait"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
88 source="stdout"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
89 level="fatal"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
90 description="Error: bad bait"/>
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
91 <regex match="IOError: [Errno 2] No such file or directory: './tukeys_output.txt'"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
92 source="stderr"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
93 level="fatal"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
94 description="Error: Scaffold/MaxQuant mismatch. Check job settings."/>
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
95 <regex match="bait_temp_file = open(sys.argv[10], 'r')"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
96 source="stderr"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
97 level="fatal"
8031a47f67c6 Uploaded
bornea
parents: 27
diff changeset
98 description="Error: Bait create settings mismatch. Check job settings."/>
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
99 <regex match="Error|error"
3953103b56f9 Uploaded
bornea
parents:
diff changeset
100 source="stdout"
3953103b56f9 Uploaded
bornea
parents:
diff changeset
101 level="fatal"
3953103b56f9 Uploaded
bornea
parents:
diff changeset
102 description="Unknown error"/>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
103 <regex match="Error|error"
3953103b56f9 Uploaded
bornea
parents:
diff changeset
104 source="stderr"
3953103b56f9 Uploaded
bornea
parents:
diff changeset
105 level="fatal"
3953103b56f9 Uploaded
bornea
parents:
diff changeset
106 description="Unknown error"/>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
107 </stdio>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
108
3953103b56f9 Uploaded
bornea
parents:
diff changeset
109 <tests>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
110 <test>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
111 <param name="input" value="fa_gc_content_input.fa"/>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
112 <output name="out_file1" file="fa_gc_content_output.txt"/>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
113 </test>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
114 </tests>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
115 <help>
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
116 Pre-Processing
25
9a110e634afe Uploaded
bornea
parents: 24
diff changeset
117 ^^^^^^^^^^^^^^
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
118
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
119 This tool will read in a Scaffold *Samples Report* file (tab-delimited
55
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
120 txt file), multiple Peptideshaker *Protein Report* files or a MaxQuant
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
121 *peptides.txt* file and process them to generate a *Bait File, Prey
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
122 File,* and *Inter File* for SAINTexpress analysis.
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
123
25
9a110e634afe Uploaded
bornea
parents: 24
diff changeset
124 --------------
9a110e634afe Uploaded
bornea
parents: 24
diff changeset
125
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
126 **1) MaxQuant or Scaffold**
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
127
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
128 APOSTL is able to recognize either a Scaffold *Samples Report* file
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
129 (tab-delimited txt file) or the *peptides.txt* file output in the
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
130 MaxQuant *txt* output folder. No modifications should be made to these
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
131 files. Please designate which one is being provided.
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
132
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
133 **2) Scaffold or MaxQuant File Input**
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
134
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
135 Select the corresponding *Samples Report* or *peptides.txt* here.
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
136
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
137 **3) Create Prey File**
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
138
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
139 Select whether or not you would like APOSTL to generate a prey file.
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
140
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
141 When making a prey file, APOSTL queries a user provided FASTA database
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
142 (see below) in order to extract protein amino acid lengths and gene
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
143 names. This may take several minutes depending on your computer and if
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
144 your Galaxy distribution is cluster enabled. Some users may want to run
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
145 SAINTexpress using the same data set while changing which baits are
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
146 considered test or control. It is useful to toggle **Create Prey File**
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
147 off in order to save time by circumventing this step as the same prey
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
148 file can be used for both SAINTexpress runs.
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
149
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
150 **4) Provide Uniprot FASTA database**
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
151
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
152 Please specify a FASTA file containing the protein sequence. You can
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
153 download the latest release of Uniprot's reviewed sequences (Swiss-Prot)
24
85c19ee579d6 Uploaded
bornea
parents: 23
diff changeset
154 http://www.uniprot.org/downloads. For computing efficiency,
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
155 please limit your FASTA file to your species of interest. It is
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
156 generally advised to use the same FASTA database that was used for your
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
157 database searches during peptide and protein ID.
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
158
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
159 **5) Are You Providing Your Own Bait File?**
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
160
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
161 Users have two options for providing a *Bait* file. If you would like to
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
162 create your own *Bait* file, select Yes and designate the file below. If
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
163 you would like to use the **Bait Create** tool to create a *Bait* file
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
164 within Galaxy, please select No and proceed to the **Bait Create** tool.
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
165
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
166 **6) Bait File**
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
167
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
168 If you selected Yes above, please specify the *Bait* file you would like
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
169 to provide. If you selected No above, ignore this argument and proceed
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
170 to the **Bait Create** tool.
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
171
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
172 **Note:** Individual bait names must match to the sample names
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
173 within your Scaffold or MaxQuant output exactly and must contain no
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
174 whitespace characters (e.g. spaces) or dashes.
59
5ad68d3a11cc Uploaded
bornea
parents: 55
diff changeset
175
55
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
176 **Note:** When using Peptideshaker output the baits in the baitfile
340cc5988c31 Uploaded
bornea
parents: 52
diff changeset
177 need to be in the same order as the files selected.
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
178
27
2d78642361c3 Uploaded
bornea
parents: 26
diff changeset
179 **7) Bait Create**
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
180
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
181 Using the **Bait Create** tool, you can create your *bait.txt* file.
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
182
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
183 **Note:** Individual bait names must match to the sample names
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
184 within your Scaffold or MaxQuant output exactly and must contain no
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
185 whitespace characters (e.g. spaces) or dashes.
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
186
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
187 APOSTL uses this bait file to find the user's baits of interest within a
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
188 *Samples Report* or *peptides.txt* file and when preparing the
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
189 *inter.txt* file.
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
190
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
191 --------------
20
0ac97a6298c2 Uploaded
bornea
parents: 5
diff changeset
192
21
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
193 Once your parameters have been finalized, please press the Execute
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
194 button to start processing. This may take a few minutes. Once your
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
195 process has been completed, you will see your *Bait File, Prey File,*
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
196 and *Inter File* on the right hand side of your panel highlighted in
d9592cc1df99 Uploaded
bornea
parents: 20
diff changeset
197 green.
5
3953103b56f9 Uploaded
bornea
parents:
diff changeset
198 </help>
3953103b56f9 Uploaded
bornea
parents:
diff changeset
199 </tool>