import org.forester.io.parsers.GeneralMsaParser;
import org.forester.msa.Msa;
import org.forester.msa.Msa.MSA_FORMAT;
+import org.forester.msa.MsaInferrer;
import org.forester.msa_compactor.MsaCompactor;
-import org.forester.msa.MsaMethods;
import org.forester.util.CommandLineArguments;
import org.forester.util.ForesterUtil;
final static private String HELP_OPTION_1 = "help";
final static private String HELP_OPTION_2 = "h";
- final static private String REMOVE_WORST_OFFENDERS_OPTION = "w";
- final static private String AV_GAPINESS_OPTION = "a";
+ final static private String REMOVE_WORST_OFFENDERS_OPTION = "r";
+ final static private String AV_GAPINESS_OPTION = "g";
final static private String STEP_OPTION = "s";
final static private String LENGTH_OPTION = "l";
- final static private String REALIGN_OPTION = "r";
+ final static private String REALIGN_OPTION = "a";
+ final static private String PATH_TO_MAFFT_OPTION = "mafft";
final static private String DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION = "nn";
final static private String PRG_NAME = "msa_compactor";
final static private String PRG_DESC = "multiple sequnce aligment compactor";
final static private String PRG_VERSION = "0.01";
- final static private String PRG_DATE = "140221";
+ final static private String PRG_DATE = "140314";
final static private String E_MAIL = "phylosoft@gmail.com";
final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester";
int step = 1;
boolean realign = false;
boolean norm = true;
+ String path_to_mafft = null;
final List<String> allowed_options = new ArrayList<String>();
allowed_options.add( REMOVE_WORST_OFFENDERS_OPTION );
allowed_options.add( AV_GAPINESS_OPTION );
allowed_options.add( REALIGN_OPTION );
allowed_options.add( DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION );
allowed_options.add( STEP_OPTION );
+ allowed_options.add( PATH_TO_MAFFT_OPTION );
final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
if ( dissallowed_options.length() > 0 ) {
ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
if ( cla.isOptionSet( REALIGN_OPTION ) ) {
realign = true;
}
+ if ( cla.isOptionSet( PATH_TO_MAFFT_OPTION ) ) {
+ if ( !realign ) {
+ ForesterUtil.fatalError( PRG_NAME, "no need to indicate path to MAFFT without realigning" );
+ }
+ path_to_mafft = cla.getOptionValueAsCleanString( PATH_TO_MAFFT_OPTION );
+ }
if ( cla.isOptionSet( DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION ) ) {
norm = false;
}
// printHelp();
// System.exit( 0 );
// }
+ if ( realign ) {
+ if ( ForesterUtil.isEmpty( path_to_mafft ) ) {
+ path_to_mafft = MsaCompactor.guessPathToMafft();
+ }
+ checkPathToMafft( path_to_mafft );
+ }
Msa msa = null;
final FileInputStream is = new FileInputStream( in );
if ( FastaParser.isLikelyFasta( in ) ) {
}
MsaCompactor mc = null;
if ( worst_remove > 0 ) {
- mc = MsaCompactor.removeWorstOffenders( msa, worst_remove, realign, norm );
+ mc = MsaCompactor.removeWorstOffenders( msa, worst_remove, realign, norm, path_to_mafft );
}
else if ( av > 0 ) {
- mc = MsaCompactor.reduceGapAverage( msa, av, step, realign, out, 50 );
+ mc = MsaCompactor.reduceGapAverage( msa, av, step, realign, out, 50, path_to_mafft );
}
else if ( length > 0 ) {
- mc = MsaCompactor.reduceLength( msa, length, step, realign );
- }
- System.out.println( MsaMethods.calcGapRatio( mc.getMsa() ) );
- for( final String id : mc.getRemovedSeqIds() ) {
- System.out.println( id );
+ mc = MsaCompactor.reduceLength( msa, length, step, realign, path_to_mafft );
}
+ //System.out.println( MsaMethods.calcGapRatio( mc.getMsa() ) );
+ // for( final String id : mc.getRemovedSeqIds() ) {
+ // System.out.println( id );
+ //}
mc.writeMsa( out, MSA_FORMAT.PHYLIP, ".aln" );
}
catch ( final Exception e ) {
}
}
+ private static void checkPathToMafft( final String path_to_mafft ) {
+ if ( !ForesterUtil.isEmpty( path_to_mafft ) && MsaInferrer.isInstalled( path_to_mafft ) ) {
+ ForesterUtil.programMessage( PRG_NAME, "using MAFFT at \"" + path_to_mafft + "\"" );
+ }
+ else {
+ if ( ForesterUtil.isEmpty( path_to_mafft ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable found, use -\"" + PATH_TO_MAFFT_OPTION
+ + "=<path to MAFFT>\" option" );
+ }
+ else {
+ ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable at \"" + path_to_mafft + "\"" );
+ }
+ }
+ }
+
private static void printHelp() {
ForesterUtil.printProgramInformation( PRG_NAME,
PRG_DESC,
E_MAIL,
WWW,
ForesterUtil.getForesterLibraryInformation() );
+ final String path_to_mafft = MsaCompactor.guessPathToMafft();
+ String mafft_comment;
+ if ( !ForesterUtil.isEmpty( path_to_mafft ) ) {
+ mafft_comment = " (using " + path_to_mafft + ")";
+ }
+ else {
+ mafft_comment = " (no path to MAFFT found, use -\"" + PATH_TO_MAFFT_OPTION + "=<path to MAFFT>\" option";
+ }
System.out.println( "Usage:" );
System.out.println();
- System.out.println( PRG_NAME + " <options> <msa input file>" );
+ System.out.println( PRG_NAME + " <options> <msa input file> <output file>" );
System.out.println();
System.out.println( " options: " );
System.out.println();
- System.out.println( " -" + REMOVE_WORST_OFFENDERS_OPTION + "=<integer>: step size (msa columns)" );
+ System.out.println( " -" + REMOVE_WORST_OFFENDERS_OPTION
+ + "=<integer> number of worst offender sequences to remove" );
+ System.out.println( " -" + REALIGN_OPTION + " to realign using MAFFT" + mafft_comment );
System.out.println();
System.out.println();
System.out.println();