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=bf04e121d1c5c549d4850b43e3b298c062363e6c;hpb=35f27e4a3dec02b6496faa17bd89d880d398747a;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 bf04e12..4230ce0 100644 --- a/forester/java/src/org/forester/application/msa_compactor.java +++ b/forester/java/src/org/forester/application/msa_compactor.java @@ -10,8 +10,6 @@ import org.forester.io.parsers.FastaParser; import org.forester.io.parsers.GeneralMsaParser; import org.forester.msa.Msa; import org.forester.msa.MsaInferrer; -import org.forester.msa.Msa.MSA_FORMAT; -import org.forester.msa.MsaMethods; import org.forester.msa_compactor.MsaCompactor; import org.forester.util.CommandLineArguments; import org.forester.util.ForesterUtil; @@ -20,11 +18,11 @@ 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"; @@ -94,6 +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 ) ) { @@ -102,39 +106,26 @@ public class msa_compactor { else { msa = GeneralMsaParser.parse( is ); } - - if ( realign ) { - if ( ForesterUtil.isEmpty( path_to_mafft ) ) { - path_to_mafft = MsaCompactor.guessPathToMafft(); - } - 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 + "\"" ); - } - } - } - 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 ); - } - mc.writeMsa( out, MSA_FORMAT.PHYLIP, ".aln" ); + 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(); @@ -142,6 +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, @@ -153,20 +159,23 @@ public class msa_compactor { final String path_to_mafft = MsaCompactor.guessPathToMafft(); String mafft_comment; if ( !ForesterUtil.isEmpty( path_to_mafft ) ) { - mafft_comment = " (" + 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 + "= number of sequences to remove" ); - System.out.println( " -" + REALIGN_OPTION + " to realign using MAFFT" + mafft_comment ); + 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();