X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fmsa_compactor.java;h=4230ce05b90766104a62613f7fc2e55db8a1b82a;hb=14375b2b2837d1ae5a2d0bb44f8aae9f1916281a;hp=0f1b961e19ba3c7ccdb1f1aec66fab934a428dc1;hpb=b1a74bd076c917d428002284a53a2c6f390226fb;p=jalview.git diff --git a/forester/java/src/org/forester/application/msa_compactor.java b/forester/java/src/org/forester/application/msa_compactor.java index 0f1b961..4230ce0 100644 --- a/forester/java/src/org/forester/application/msa_compactor.java +++ b/forester/java/src/org/forester/application/msa_compactor.java @@ -9,47 +9,53 @@ import java.util.List; import org.forester.io.parsers.FastaParser; import org.forester.io.parsers.GeneralMsaParser; import org.forester.msa.Msa; -import org.forester.msa.MsaCompactor; -import org.forester.msa.MsaMethods; +import org.forester.msa.MsaInferrer; +import org.forester.msa_compactor.MsaCompactor; import org.forester.util.CommandLineArguments; import org.forester.util.ForesterUtil; public class msa_compactor { - 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 LENGTH_OPTION = "l"; - final static private String REALIGN_OPTION = "r"; - final static private String PRG_NAME = "msa_compactor"; - final static private String PRG_DESC = "multiple sequnce aligment compactor"; - final static private String PRG_VERSION = "0.90"; - final static private String PRG_DATE = "2012.07.11"; - final static private String E_MAIL = "phylosoft@gmail.com"; - final static private String WWW = "www.phylosoft.org/forester/"; + final static private String HELP_OPTION_1 = "help"; + final static private String HELP_OPTION_2 = "h"; + 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 = "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 = "140314"; + final static private String E_MAIL = "phylosoft@gmail.com"; + final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester"; public static void main( final String args[] ) { try { final CommandLineArguments cla = new CommandLineArguments( args ); - if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) ) { + if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( cla.getNumberOfNames() != 2 ) ) { printHelp(); System.exit( 0 ); } final File in = cla.getFile( 0 ); + final File out = cla.getFile( 1 ); int worst_remove = -1; double av = -1; int length = -1; - final int step = 5; + int step = 1; boolean realign = false; - // int to = 0; - // int window = 0; - // int step = 0; + boolean norm = true; + String path_to_mafft = null; final List allowed_options = new ArrayList(); allowed_options.add( REMOVE_WORST_OFFENDERS_OPTION ); allowed_options.add( AV_GAPINESS_OPTION ); allowed_options.add( LENGTH_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 ); @@ -63,9 +69,21 @@ public class msa_compactor { if ( cla.isOptionSet( LENGTH_OPTION ) ) { length = cla.getOptionValueAsInt( LENGTH_OPTION ); } + if ( cla.isOptionSet( STEP_OPTION ) ) { + step = cla.getOptionValueAsInt( STEP_OPTION ); + } 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; + } // else if ( cla.isOptionSet( STEP_OPTION ) && cla.isOptionSet( WINDOW_OPTION ) ) { // step = cla.getOptionValueAsInt( STEP_OPTION ); // window = cla.getOptionValueAsInt( WINDOW_OPTION ); @@ -74,6 +92,12 @@ public class msa_compactor { // 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 ) ) { @@ -82,23 +106,26 @@ public class msa_compactor { else { msa = GeneralMsaParser.parse( is ); } - System.out.println( msa.toString() ); - System.out.println( MsaMethods.calcBasicGapinessStatistics( msa ).arithmeticMean() ); MsaCompactor mc = null; if ( worst_remove > 0 ) { - mc = MsaCompactor.removeWorstOffenders( msa, worst_remove, realign ); + mc = MsaCompactor.removeWorstOffenders( msa, worst_remove, step, realign, norm, path_to_mafft, out ); } else if ( av > 0 ) { - mc = MsaCompactor.reduceGapAverage( msa, av, step, realign ); + mc = MsaCompactor.reduceGapAverage( msa, av, step, realign, norm, path_to_mafft, out ); } else if ( length > 0 ) { - mc = MsaCompactor.reduceLength( msa, length, step, realign ); - } - System.out.println( mc.getMsa().toString() ); - System.out.println( MsaMethods.calcBasicGapinessStatistics( mc.getMsa() ).arithmeticMean() ); - for( final String id : mc.getRemovedSeqIds() ) { - System.out.println( id ); + if ( length >= msa.getLength() ) { + ForesterUtil.fatalError( PRG_NAME, "target MSA length (" + length + + ") is greater than or equal to MSA original length (" + msa.getLength() + ")" ); + } + // TODO if < shortest seq -> error + mc = MsaCompactor.reduceLength( msa, length, step, realign, norm, path_to_mafft, out ); } + //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 ) { e.printStackTrace(); @@ -106,6 +133,21 @@ public class msa_compactor { } } + 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 + + "=\" option" ); + } + else { + ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable at \"" + path_to_mafft + "\"" ); + } + } + } + private static void printHelp() { ForesterUtil.printProgramInformation( PRG_NAME, PRG_DESC, @@ -114,17 +156,26 @@ public class msa_compactor { 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 + "=\" option"; + } System.out.println( "Usage:" ); System.out.println(); - System.out.println( PRG_NAME + " " ); + System.out.println( PRG_NAME + " " ); System.out.println(); System.out.println( " options: " ); System.out.println(); - // System.out.println( " -" + FROM_OPTION + "=: from (msa column)" ); - // System.out.println( " -" + TO_OPTION + "=: to (msa column)" ); - // System.out.println( " or" ); - // System.out.println( " -" + WINDOW_OPTION + "=: window size (msa columns)" ); - System.out.println( " -" + REMOVE_WORST_OFFENDERS_OPTION + "=: step size (msa columns)" ); + System.out.println( " -" + REMOVE_WORST_OFFENDERS_OPTION + + "= number of worst offender sequences to remove" ); + System.out.println( " -" + LENGTH_OPTION + "= target MSA length" ); + System.out.println( " -" + AV_GAPINESS_OPTION + "= gap %" ); + System.out.println( " -" + STEP_OPTION + "= step" ); + System.out.println( " -" + REALIGN_OPTION + " to realign using MAFFT" + mafft_comment ); System.out.println(); System.out.println(); System.out.println();