2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2014 Christian M. Zmasek
6 // Copyright (C) 2014 Sanford-Burnham Medical Research Institute
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
25 package org.forester.application;
28 import java.io.FileInputStream;
29 import java.util.ArrayList;
30 import java.util.List;
32 import org.forester.io.parsers.FastaParser;
33 import org.forester.io.parsers.GeneralMsaParser;
34 import org.forester.msa.DeleteableMsa;
35 import org.forester.msa.Msa.MSA_FORMAT;
36 import org.forester.msa.MsaInferrer;
37 import org.forester.msa.MsaMethods;
38 import org.forester.msa_compactor.MsaCompactor;
39 import org.forester.util.CommandLineArguments;
40 import org.forester.util.DescriptiveStatistics;
41 import org.forester.util.ForesterUtil;
43 public class msa_compactor {
45 final static private String HELP_OPTION_1 = "help";
46 final static private String HELP_OPTION_2 = "h";
47 final static private String REMOVE_WORST_OFFENDERS_OPTION = "r";
48 final static private String AV_GAPINESS_OPTION = "g";
49 final static private String STEP_OPTION = "s";
50 final static private String LENGTH_OPTION = "l";
51 final static private String REALIGN_OPTION = "a";
53 final static private String STEP_FOR_DIAGNOSTICS_OPTION = "sd";
54 final static private String MIN_LENGTH_OPTION = "ml";
55 final static private String GAP_RATIO_LENGTH_OPTION = "gr";
56 final static private String REPORT_ALN_MEAN_IDENTITY = "q";
57 final static private String OUTPUT_FORMAT_PHYLIP_OPTION = "f";
58 final static private String OUTPUT_REMOVED_SEQS_OPTION = "ro";
59 final static private String MAFFT_OPTIONS = "mo";
61 final static private String PATH_TO_MAFFT_OPTION = "mafft";
62 final static private String DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION = "nn";
63 final static private String PRG_NAME = "msa_compactor";
64 final static private String PRG_DESC = "multiple sequence aligment compactor";
65 final static private String PRG_VERSION = "0.02";
66 final static private String PRG_DATE = "140316";
67 final static private String E_MAIL = "czmasek@sanfordburham.org";
68 final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester";
70 public static void main( final String args[] ) {
72 final CommandLineArguments cla = new CommandLineArguments( args );
73 if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 )
74 || ( ( cla.getNumberOfNames() < 1 ) || ( cla.getNumberOfNames() > 2 ) ) ) {
78 final File in = cla.getFile( 0 );
80 if ( cla.getNumberOfNames() > 1 ) {
81 out = cla.getFile( 1 );
83 int worst_remove = -1;
87 boolean realign = false;
89 String path_to_mafft = null;
90 int step_for_diagnostics = -1;
92 double gap_ratio = -1;
93 boolean report_aln_mean_identity = false;
94 MSA_FORMAT output_format = MSA_FORMAT.FASTA;
95 File removed_seqs_out_base = null;
96 String mafft_options = "--auto";
97 final List<String> allowed_options = new ArrayList<String>();
98 allowed_options.add( REMOVE_WORST_OFFENDERS_OPTION );
99 allowed_options.add( AV_GAPINESS_OPTION );
100 allowed_options.add( LENGTH_OPTION );
101 allowed_options.add( REALIGN_OPTION );
102 allowed_options.add( DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION );
103 allowed_options.add( STEP_OPTION );
104 allowed_options.add( PATH_TO_MAFFT_OPTION );
105 allowed_options.add( STEP_FOR_DIAGNOSTICS_OPTION );
106 allowed_options.add( MIN_LENGTH_OPTION );
107 allowed_options.add( GAP_RATIO_LENGTH_OPTION );
108 allowed_options.add( REPORT_ALN_MEAN_IDENTITY );
109 allowed_options.add( OUTPUT_FORMAT_PHYLIP_OPTION );
110 allowed_options.add( OUTPUT_REMOVED_SEQS_OPTION );
111 allowed_options.add( MAFFT_OPTIONS );
112 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
113 if ( dissallowed_options.length() > 0 ) {
114 ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
116 DeleteableMsa msa = null;
117 final FileInputStream is = new FileInputStream( in );
118 if ( FastaParser.isLikelyFasta( in ) ) {
119 msa = DeleteableMsa.createInstance( FastaParser.parseMsa( is ) );
122 msa = DeleteableMsa.createInstance( GeneralMsaParser.parse( is ) );
124 final DescriptiveStatistics initial_msa_stats = MsaMethods.calculateEffectiveLengthStatistics( msa );
125 System.out.println( initial_msa_stats.toString() );
126 if ( cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) ) {
127 worst_remove = cla.getOptionValueAsInt( REMOVE_WORST_OFFENDERS_OPTION );
128 if ( ( worst_remove < 1 ) || ( worst_remove >= msa.getNumberOfSequences() - 1 ) ) {
129 ForesterUtil.fatalError( PRG_NAME, "number of worst offender sequences to remove is out of range: "
133 if ( cla.isOptionSet( AV_GAPINESS_OPTION ) ) {
134 if ( cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) ) {
138 av_gap = cla.getOptionValueAsDouble( AV_GAPINESS_OPTION );
139 if ( ( av_gap < 0 ) || ( av_gap >= 1 ) ) {
140 ForesterUtil.fatalError( PRG_NAME, "target gap-ratio is out of range: " + av_gap );
143 if ( cla.isOptionSet( LENGTH_OPTION ) ) {
144 if ( cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) || cla.isOptionSet( AV_GAPINESS_OPTION ) ) {
148 length = cla.getOptionValueAsInt( LENGTH_OPTION );
149 if ( ( length < 2 ) || ( length >= msa.getLength() ) ) {
150 ForesterUtil.fatalError( PRG_NAME, "target length is out of range: " + length );
153 if ( cla.isOptionSet( STEP_OPTION ) ) {
154 step = cla.getOptionValueAsInt( STEP_OPTION );
156 || ( ( step > msa.getNumberOfSequences() ) || ( ( worst_remove > 0 ) && ( step > worst_remove ) ) ) ) {
157 ForesterUtil.fatalError( PRG_NAME, "value for step is out of range: " + step );
160 if ( cla.isOptionSet( REALIGN_OPTION ) ) {
163 if ( cla.isOptionSet( PATH_TO_MAFFT_OPTION ) ) {
165 ForesterUtil.fatalError( PRG_NAME, "no need to indicate path to MAFFT without realigning" );
167 path_to_mafft = cla.getOptionValueAsCleanString( PATH_TO_MAFFT_OPTION );
169 if ( cla.isOptionSet( DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION ) ) {
173 if ( cla.isOptionSet( STEP_FOR_DIAGNOSTICS_OPTION ) ) {
174 step_for_diagnostics = cla.getOptionValueAsInt( STEP_FOR_DIAGNOSTICS_OPTION );
175 if ( ( step_for_diagnostics < 1 )
176 || ( ( step_for_diagnostics > msa.getNumberOfSequences() ) || ( ( worst_remove > 0 ) && ( step_for_diagnostics > worst_remove ) ) ) ) {
177 ForesterUtil.fatalError( PRG_NAME, "value for diagnostic step is out of range: "
178 + step_for_diagnostics );
181 if ( cla.isOptionSet( MIN_LENGTH_OPTION ) ) {
182 min_length = cla.getOptionValueAsInt( MIN_LENGTH_OPTION );
183 if ( ( min_length < 2 ) || ( min_length > initial_msa_stats.getMax() ) ) {
184 ForesterUtil.fatalError( PRG_NAME, "value for minimal sequence length is out of range: "
188 if ( cla.isOptionSet( MIN_LENGTH_OPTION ) ) {
189 gap_ratio = cla.getOptionValueAsDouble( GAP_RATIO_LENGTH_OPTION );
190 if ( ( gap_ratio < 0 ) || ( gap_ratio > 1 ) ) {
191 ForesterUtil.fatalError( PRG_NAME, "gap ratio is out of range: " + gap_ratio );
194 if ( cla.isOptionSet( REPORT_ALN_MEAN_IDENTITY ) ) {
195 report_aln_mean_identity = true;
197 if ( cla.isOptionSet( OUTPUT_FORMAT_PHYLIP_OPTION ) ) {
198 output_format = MSA_FORMAT.PHYLIP;
200 if ( cla.isOptionSet( OUTPUT_REMOVED_SEQS_OPTION ) ) {
201 String s = cla.getOptionValueAsCleanString( OUTPUT_REMOVED_SEQS_OPTION );
202 removed_seqs_out_base = new File( s );
205 if ( ForesterUtil.isEmpty( path_to_mafft ) ) {
206 path_to_mafft = MsaCompactor.guessPathToMafft();
208 checkPathToMafft( path_to_mafft );
209 if ( cla.isOptionSet( MAFFT_OPTIONS ) ) {
210 mafft_options = cla.getOptionValueAsCleanString( MAFFT_OPTIONS );
211 if ( ForesterUtil.isEmpty( mafft_options ) || mafft_options.length() < 3 ) {
212 ForesterUtil.fatalError( PRG_NAME, "gap ratio is out of range: " + gap_ratio );
216 ForesterUtil.printProgramInformation( PRG_NAME,
222 ForesterUtil.getForesterLibraryInformation() );
224 System.out.println( "Input MSA : " + in );
226 System.out.println( "Output : " + out );
229 System.out.println( "Output : n/a" );
231 if ( removed_seqs_out_base != null ) {
232 System.out.println( "Write removed sequences to : " + removed_seqs_out_base );
234 if ( worst_remove > 0 ) {
235 System.out.println( "Number of worst offenders to remove : " + worst_remove );
237 else if ( av_gap > 0 ) {
238 System.out.println( "Target gap-ratio : " + av_gap );
240 else if ( length > 0 ) {
241 System.out.println( "Target MSA length : " + length );
244 System.out.println( "Chart and diagnostics only : true" );
246 if ( out != null || removed_seqs_out_base != null ) {
247 System.out.println( "Output format : "
248 + ( output_format == MSA_FORMAT.FASTA ? "fasta" : "phylip" ) );
250 System.out.println( "Step for output and re-aligning) : " + step );
251 System.out.println( "Step for diagnostics reports : " + step_for_diagnostics );
252 System.out.println( "Report mean identity (\"MSA quality\") : " + report_aln_mean_identity );
254 System.out.println( "Normalize : " + norm );
256 System.out.println( "Realign : " + realign );
258 System.out.println( "MAFFT options : " + mafft_options );
260 if ( min_length > -1 ) {
261 System.out.println( "Minimal effective sequence length : " + min_length );
263 if ( gap_ratio > -1 ) {
264 System.out.println( "Maximum allowed gap ratio per column : " + gap_ratio );
266 System.out.println();
268 if ( worst_remove > 0 ) {
269 MsaCompactor.removeWorstOffenders( msa, worst_remove, step, realign, norm, path_to_mafft, out );
271 else if ( av_gap > 0 ) {
272 MsaCompactor.reduceGapAverage( msa, av_gap, step, realign, norm, path_to_mafft, out );
274 else if ( length > 0 ) {
275 // TODO if < shortest seq -> error
276 MsaCompactor.reduceLength( msa, length, step, realign, norm, path_to_mafft, out );
279 MsaCompactor.chart( msa, step, realign, norm, path_to_mafft );
282 catch ( final Exception e ) {
284 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
288 private static void checkPathToMafft( final String path_to_mafft ) {
289 if ( !ForesterUtil.isEmpty( path_to_mafft ) && MsaInferrer.isInstalled( path_to_mafft ) ) {
290 ForesterUtil.programMessage( PRG_NAME, "using MAFFT at \"" + path_to_mafft + "\"" );
293 if ( ForesterUtil.isEmpty( path_to_mafft ) ) {
294 ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable found, use -\"" + PATH_TO_MAFFT_OPTION
295 + "=<path to MAFFT>\" option" );
298 ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable at \"" + path_to_mafft + "\"" );
303 private static void printHelp() {
304 ForesterUtil.printProgramInformation( PRG_NAME,
310 ForesterUtil.getForesterLibraryInformation() );
311 final String path_to_mafft = MsaCompactor.guessPathToMafft();
312 String mafft_comment;
313 if ( !ForesterUtil.isEmpty( path_to_mafft ) ) {
314 mafft_comment = " (using " + path_to_mafft + ")";
317 mafft_comment = " (no path to MAFFT found, use -\"" + PATH_TO_MAFFT_OPTION + "=<path to MAFFT>\" option";
319 System.out.println( "Usage:" );
320 System.out.println();
321 System.out.println( PRG_NAME + " <options> <msa input file> <output file>" );
322 System.out.println();
323 System.out.println( " options: " );
324 System.out.println();
325 System.out.println( " -" + REMOVE_WORST_OFFENDERS_OPTION
326 + "=<integer> number of worst offender sequences to remove" );
327 System.out.println( " -" + LENGTH_OPTION + "=<integer> target MSA length" );
328 System.out.println( " -" + AV_GAPINESS_OPTION + "=<decimal> target gap-ratio (0.0-1.0)" );
329 System.out.println( " -" + STEP_OPTION + "=<integer> step for output and re-aligning (default: 1)" );
330 System.out.println( " -" + REALIGN_OPTION + " to realign using MAFFT" + mafft_comment );
331 System.out.println( " -" + MAFFT_OPTIONS + "=<string> options for MAFFT (default: --auto)" );
332 System.out.println( " -" + STEP_FOR_DIAGNOSTICS_OPTION
333 + "=<integer> step for diagnostics reports (default: 1)" );
334 System.out.println( " -" + MIN_LENGTH_OPTION
335 + "=<integer> minimal effecive sequence length (for deleting of shorter sequences)" );
336 System.out.println( " -" + GAP_RATIO_LENGTH_OPTION
337 + "=<decimal> maximal allowed gap ratio per column (for deleting of columms) (0.0-1.0)" );
338 System.out.println( " -" + REPORT_ALN_MEAN_IDENTITY
339 + " to report mean identity diagnostic (not recommended for very large alignments)" );
340 System.out.println( " -" + OUTPUT_FORMAT_PHYLIP_OPTION
341 + " to write output alignments in phylip format instead of fasta" );
342 System.out.println( " -" + OUTPUT_REMOVED_SEQS_OPTION + "=<file> to output the removed sequences" );
343 System.out.println();
344 System.out.println();
345 System.out.println();