1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
// --------------------------------------------------------------------------
// OpenMS -- Open-Source Mass Spectrometry
// --------------------------------------------------------------------------
// Copyright The OpenMS Team -- Eberhard Karls University Tuebingen,
// ETH Zurich, and Freie Universitaet Berlin 2002-2013.
//
// This software is released under a three-clause BSD license:
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
// * Neither the name of any author or any participating institution
// may be used to endorse or promote products derived from this software
// without specific prior written permission.
// For a full list of authors, refer to the file AUTHORS.
// --------------------------------------------------------------------------
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
// ARE DISCLAIMED. IN NO EVENT SHALL ANY OF THE AUTHORS OR THE CONTRIBUTING
// INSTITUTIONS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
// OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
// ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// --------------------------------------------------------------------------
// $Maintainer: Chris Bielow $
// $Authors: Andreas Bertsch $
// --------------------------------------------------------------------------
#include <OpenMS/APPLICATIONS/TOPPBase.h>
#include <OpenMS/ANALYSIS/ID/FalseDiscoveryRate.h>
#include <OpenMS/KERNEL/StandardTypes.h>
#include <OpenMS/FORMAT/IdXMLFile.h>
using namespace OpenMS;
using namespace std;
/**
@page TOPP_FalseDiscoveryRate FalseDiscoveryRate
@brief Tool to estimate the false discovery rate on peptide and protein level
<CENTER>
<table>
<tr>
<td ALIGN = "center" BGCOLOR="#EBEBEB"> pot. predecessor tools </td>
<td VALIGN="middle" ROWSPAN=3> \f$ \longrightarrow \f$ FalseDiscoveryRate \f$ \longrightarrow \f$</td>
<td ALIGN = "center" BGCOLOR="#EBEBEB"> pot. successor tools </td>
</tr>
<tr>
<td VALIGN="middle" ALIGN = "center" ROWSPAN=1> @ref TOPP_MascotAdapter (or other ID engines) </td>
<td VALIGN="middle" ALIGN = "center" ROWSPAN=2> @ref TOPP_IDFilter </td>
</tr>
<tr>
<td VALIGN="middle" ALIGN = "center" ROWSPAN=1> @ref TOPP_PeptideIndexer </td>
</tr>
</table>
</CENTER>
This TOPP tool can calculate the false discovery rate (FDR) given a forward and
backward search (or one run on a combined database).
Most useful is this on protein level, however, it also can be applied to peptides.
The false discovery rate is defined as the number of false discoveries (the hits
in the reversed search) over the number of false and correct discoveries (the hits
in both databases) with a score better than a given threshold.
Prerequisites:
- When using a combined database of forward and reverse hits (thus only using one search run per ID engine), then use @ref TOPP_PeptideIndexer to index an idXML file generated by a search engine adapter, e.g. @ref TOPP_MascotAdapter.
This will allow us to discern which peptides are from the target vs. decoy database.
@Note When no decoy hits were found you will get a warning saying something like:<br>
"FalseDiscoveryRate: #decoy sequences is zero! Setting all target sequences to q-value/FDR 0!"<br>
This should be a serious concern, since the target/decoy annotation in a previous step has probably a misconfigured database (see @ref TOPP_PeptideIndexer).
<B>The command line parameters of this tool are:</B>
@verbinclude TOPP_FalseDiscoveryRate.cli
<B>INI file documentation of this tool:</B>
@htmlinclude TOPP_FalseDiscoveryRate.html
*/
// We do not want this class to show up in the docu:
/// @cond TOPPCLASSES
class TOPPFalseDiscoveryRate :
public TOPPBase
{
public:
TOPPFalseDiscoveryRate() :
TOPPBase("FalseDiscoveryRate", "Estimates the false discovery rate on peptide and protein level using decoy searches.")
{
}
protected:
Param getSubsectionDefaults_(const String & /*section*/) const
{
return FalseDiscoveryRate().getDefaults();
}
void registerOptionsAndFlags_()
{
registerInputFile_("in", "<file>", "", "Identification input file which contains a search against "
"a concatenated sequence database. "
"Either specify '-in' alone or 'fwd_in' together with 'rev_in' as input.", false);
setValidFormats_("in", StringList::create("idXML"));
registerInputFile_("fwd_in", "<file>", "", "Identification input to estimate FDR, forward run.", false);
setValidFormats_("fwd_in", StringList::create("idXML"));
registerInputFile_("rev_in", "<file>", "", "Identification input to estimate FDR, decoy run.", false);
setValidFormats_("rev_in", StringList::create("idXML"));
registerOutputFile_("out", "<file>", "", "Identification output with annotated FDR");
setValidFormats_("out", StringList::create("idXML"));
registerFlag_("proteins_only", "If set, the FDR of the proteins only is calculated");
registerFlag_("peptides_only", "If set, the FDR of the peptides only is calculated");
registerSubsection_("algorithm", "Parameter section for the FDR calculation algorithm");
addEmptyLine_();
}
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
Param alg_param = getParam_().copy("algorithm:", true);
FalseDiscoveryRate fdr;
if (!alg_param.empty())
{
fdr.setParameters(alg_param);
writeDebug_("Parameters passed to FalseDiscoveryRate", alg_param, 3);
}
//input/output files
// either fwd_in and rev_in must be given or just the in which contains results of a search against a concatenated target decoy sequence db
String fwd_in(getStringOption_("fwd_in")), rev_in(getStringOption_("rev_in")), in(getStringOption_("in"));
bool combined(false);
if (fwd_in != "" && rev_in != "")
{
if (in != "")
{
writeLog_("Error, either 'fwd_in' and 'rev_in' must be given or 'in', but not both");
return ILLEGAL_PARAMETERS;
}
}
else
{
if (in != "")
{
combined = true;
}
else
{
writeLog_("Error, at least 'fwd_in' and 'rev_in' or 'in' must be given");
return ILLEGAL_PARAMETERS;
}
}
String out(getStringOption_("out"));
bool proteins_only(getFlag_("proteins_only"));
bool peptides_only(getFlag_("peptides_only"));
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
if (combined) // -in was given
{
vector<PeptideIdentification> pep_ids;
vector<ProteinIdentification> prot_ids;
IdXMLFile().load(in, prot_ids, pep_ids);
try
{
if (!proteins_only) fdr.apply(pep_ids);
if (!peptides_only) fdr.apply(prot_ids);
}
catch (Exception::MissingInformation)
{
LOG_FATAL_ERROR << "FalseDiscoveryRate failed due to missing information (see above).\n";
return INCOMPATIBLE_INPUT_DATA;
}
for (vector<ProteinIdentification>::iterator it = prot_ids.begin(); it != prot_ids.end(); ++it)
{
it->assignRanks();
}
for (vector<PeptideIdentification>::iterator it = pep_ids.begin(); it != pep_ids.end(); ++it)
{
it->assignRanks();
}
IdXMLFile().store(out, prot_ids, pep_ids);
}
else // -fw_in & rev_in given
{
vector<PeptideIdentification> fwd_pep, rev_pep;
vector<ProteinIdentification> fwd_prot, rev_prot;
IdXMLFile().load(fwd_in, fwd_prot, fwd_pep);
IdXMLFile().load(rev_in, rev_prot, rev_pep);
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
writeDebug_("Starting calculations", 1);
if (!proteins_only)
{
fdr.apply(fwd_pep, rev_pep);
}
if (!peptides_only)
{
fdr.apply(fwd_prot, rev_prot);
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
IdXMLFile().store(out, fwd_prot, fwd_pep);
}
return EXECUTION_OK;
}
};
int main(int argc, const char ** argv)
{
TOPPFalseDiscoveryRate tool;
return tool.main(argc, argv);
}
/// @endcond
|
