X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fmsa_compactor.java;h=fd035fe11f6837f6b0e79b7b89b2c6b8be70f39e;hb=c36fa98db6cc30c2e5d7ace0a6ec01c9b3df165b;hp=c385ca94d760097c503a993f5f89b1cc6567d9eb;hpb=d261d45fb4105fb12b0158d05311394b14ec014c;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 c385ca9..fd035fe 100644 --- a/forester/java/src/org/forester/application/msa_compactor.java +++ b/forester/java/src/org/forester/application/msa_compactor.java @@ -9,9 +9,8 @@ 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.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; @@ -19,16 +18,17 @@ 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 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_DESC = "multiple sequence aligment compactor"; final static private String PRG_VERSION = "0.01"; - final static private String PRG_DATE = "140221"; + final static private String PRG_DATE = "140316"; final static private String E_MAIL = "phylosoft@gmail.com"; final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester"; @@ -47,6 +47,7 @@ public class msa_compactor { int step = 1; boolean realign = false; 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 ); @@ -54,6 +55,7 @@ public class msa_compactor { 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 ); @@ -73,17 +75,21 @@ public class msa_compactor { 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 ); - // } - // else { - // 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 ) ) { @@ -94,19 +100,19 @@ public class msa_compactor { } MsaCompactor mc = null; if ( worst_remove > 0 ) { - mc = MsaCompactor.removeWorstOffenders( msa, worst_remove, realign, norm ); + mc = MsaCompactor.removeWorstOffenders( msa, worst_remove, step, realign, norm, path_to_mafft, out ); } else if ( av > 0 ) { - mc = MsaCompactor.reduceGapAverage( msa, av, step, realign, out, 50 ); + 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( MsaMethods.calcGapRatio( mc.getMsa() ) ); - 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 ); } - mc.writeMsa( out, MSA_FORMAT.PHYLIP, ".aln" ); } catch ( final Exception e ) { e.printStackTrace(); @@ -114,6 +120,21 @@ 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, @@ -122,13 +143,26 @@ 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( " -" + 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 + "= target gap-ratio (0.0-1.0)" ); + System.out.println( " -" + STEP_OPTION + "= step (for output and re-aligning)" ); + System.out.println( " -" + REALIGN_OPTION + " to realign using MAFFT" + mafft_comment ); System.out.println(); System.out.println(); System.out.println();