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
|
// -*- Mode: C++; tab-width: 2; -*-
// vi: set ts=2:
//
#include <BALL/FORMAT/commandlineParser.h>
#include <BALL/QSAR/registry.h>
#include <BALL/QSAR/featureSelection.h>
#include <BALL/QSAR/configIO.h>
#include <fstream>
#include "version.h"
using namespace BALL::QSAR;
using namespace BALL;
using namespace std;
void startFeatureSelection(FeatureSelectionConfiguration& conf, QSARData* q, String* data_filename);
void startFeatureSelection(ifstream& in, QSARData* q, String* data_filename)
{
FeatureSelectionConfiguration conf = ConfigIO::readFeatureSelectionConfiguration(&in);
if(conf.done) return; // stop processing this section
startFeatureSelection(conf, q, data_filename);
}
void startFeatureSelection(FeatureSelectionConfiguration& conf, QSARData* q, String* data_filename)
{
bool created_data_object=0;
if(q==NULL || data_filename==NULL || conf.data_file!=*data_filename)
{
if(q==NULL)
{
q = new QSARData;
created_data_object=1;
}
q->readFromFile(conf.data_file);
if(data_filename) *data_filename = conf.data_file;
}
else
{
Log.level(2)<<"[FeatureSelector debug-info:] QSARData object for file "<<conf.data_file<<" already in memory; not reading it again."<<endl;
}
Registry reg;
Model* m;
String model_type;
ifstream model_input(conf.model.c_str()); // read model-abbreviation
if(!model_input)
{
Log.error()<<"Error: Model-file '"<<conf.model<<"' does not exist!!"<<endl;
return;
}
getline(model_input,model_type);
getline(model_input,model_type);
model_type = model_type.getField(0,"\t");
model_input.close();
RegistryEntry* entry = reg.getEntry(model_type);
if(!entry->kernel)
{
m = (*entry->create)(*q);
}
else
{
// parameters irrelevant; will be overwritten by those read from file
m = (*entry->createKernel1)(*q,1,1, -1);
}
if(conf.statistic>0)
{
Log.level(3)<<" using "<<conf.statistic_name<<" to assess qualitiy of the model ... "<<endl;
m->model_val->selectStat(conf.statistic);
}
m->readFromFile(conf.model.c_str());
FeatureSelection fs(*m);
if(conf.quality_increase_cutoff!=-1)
{
fs.setQualityIncreaseCutoff(conf.quality_increase_cutoff);
}
if(conf.remove_correlated || conf.feat_type==0)
{
fs.removeHighlyCorrelatedFeatures(conf.cor_threshold);
}
if(conf.feat_type==1)
{
fs.forwardSelection(conf.k_fold,conf.opt);
}
else if(conf.feat_type==2)
{
fs.backwardSelection(conf.k_fold,conf.opt);
}
else if(conf.feat_type==3)
{
fs.stepwiseSelection(conf.k_fold,conf.opt);
}
else if(conf.feat_type==4)
{
fs.removeLowResponseCorrelation(conf.cor_threshold);
}
else if(conf.feat_type==6)
{
fs.twinScan(conf.k_fold,conf.opt);
}
if(conf.opt_model_after_fs)
{
m->optimizeParameters(conf.opt_k_fold);
}
KernelModel* km = dynamic_cast<KernelModel*>(m);
if(km && conf.opt_kernel_after_fs)
{
/// search locally around current kernel parameters
try
{
// specifing start-values for grid search now obsolete; grid search will automatically search locally around current kernel parameter(s)
km->kernel->gridSearch(conf.grid_search_stepwidth, conf.grid_search_steps,conf.grid_search_recursions,conf.opt_k_fold,conf.opt/*,start_par1,start_par2*/);
}
catch(BALL::Exception::GeneralException e)
{
Log.error()<<e.getName()<<" : "<<e.getMessage()<<endl;
return;
}
}
m->readTrainingData();
m->train();
m->saveToFile(conf.output);
if(created_data_object) delete q;
delete m;
}
#ifndef EXT_MAIN
int main(int argc, char* argv[])
{
CommandlineParser par("FeatureSelector","run feature-selection on a QSAR model", VERSION, String(__DATE__), "QuEasy (QSAR)");
par.registerMandatoryInputFile("i","input mod-file");
par.registerMandatoryInputFile("dat","data-file");
par.registerMandatoryOutputFile("o","output mod-file");
par.registerMandatoryStringParameter("type","feature-selection type");
String man = "FeatureSelector runs a feature-selection for a given QSAR model.\n\nThe type of feature-selection to be done is specified by '-type'. Input of this tool is a data file as generated by InputReader containing the training data for feature-selection and a QSAR model file as generated by ModelCreator (or this tool itself). Note that you can apply several feature-selection methods in succession by using the output of one call of this tool as input for the next call.\nModel- and kernel-parameters (if any) will be automatically optimized by cross-validation after applying the desired feature-selection.\n\nOutput of this tool is a model-file that can be used by other QuEasy tools (e.g. Validator).";
list<String> restr;
restr.push_back("remove_correlated");
restr.push_back("forward_selection");
restr.push_back("backward_selection");
restr.push_back("stepwise_selection");
restr.push_back("twinscan");
restr.push_back("removeLowResponseCorrelation");
par.setParameterRestrictions("type", restr);
par.setToolManual(man);
par.setSupportedFormats("i","mod");
par.setSupportedFormats("dat","dat");
par.setSupportedFormats("o","mod");
par.parse(argc,argv);
Registry reg;
FeatureSelectionConfiguration conf;
conf.model = par.get("i");
conf.data_file = par.get("dat");
conf.output = par.get("o");
conf.opt_model_after_fs = true;
conf.opt_kernel_after_fs = true;
conf.opt = false;
conf.k_fold = reg.default_k;
conf.opt_k_fold = reg.default_k;
conf.grid_search_recursions = reg.default_gridsearch_recursion;
conf.grid_search_stepwidth = reg.default_gridsearch_stepwidth;
conf.grid_search_steps = reg.default_gridsearch_steps;
conf.cor_threshold = 0.95;
String type = par.get("type");
if(type=="remove_correlated")
{
conf.feat_type = 0;
}
else if(type=="forward_selection")
{
conf.feat_type = 1;
}
else if(type=="backward_selection")
{
conf.feat_type = 2;
}
else if(type=="stepwise_selection")
{
conf.feat_type = 3;
}
else if(type=="twinscan")
{
conf.feat_type = 6;
}
else if(type=="removeLowResponseCorrelation")
{
conf.feat_type = 4;
}
else
{
cerr << "Feature-selection type '"<<type<<"' unknown, possible choices are: remove_correlated, forward_selection, stepwise_selection, twinscan, removeLowResponseCorrelation"<<endl;
exit(1);
}
startFeatureSelection(conf,0,0);
}
#endif
|
