From c36fa98db6cc30c2e5d7ace0a6ec01c9b3df165b Mon Sep 17 00:00:00 2001 From: "cmzmasek@gmail.com" Date: Thu, 17 Apr 2014 02:57:48 +0000 Subject: [PATCH] inprogress --- .../org/forester/application/msa_compactor.java | 21 ++----- .../org/forester/msa_compactor/MsaCompactor.java | 59 +------------------- 2 files changed, 6 insertions(+), 74 deletions(-) diff --git a/forester/java/src/org/forester/application/msa_compactor.java b/forester/java/src/org/forester/application/msa_compactor.java index 4230ce0..fd035fe 100644 --- a/forester/java/src/org/forester/application/msa_compactor.java +++ b/forester/java/src/org/forester/application/msa_compactor.java @@ -26,9 +26,9 @@ public class msa_compactor { 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 = "140314"; + 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"; @@ -84,14 +84,6 @@ public class msa_compactor { 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(); @@ -121,11 +113,6 @@ public class msa_compactor { // 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(); @@ -173,8 +160,8 @@ public class msa_compactor { 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( " -" + 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(); diff --git a/forester/java/src/org/forester/msa_compactor/MsaCompactor.java b/forester/java/src/org/forester/msa_compactor/MsaCompactor.java index 2a5c5b1..3092060 100644 --- a/forester/java/src/org/forester/msa_compactor/MsaCompactor.java +++ b/forester/java/src/org/forester/msa_compactor/MsaCompactor.java @@ -35,9 +35,8 @@ import org.forester.util.ForesterUtil; public class MsaCompactor { - final private static NumberFormat NF_3 = new DecimalFormat( "#.###" ); - final private static NumberFormat NF_4 = new DecimalFormat( "#.####" ); - private static final boolean VERBOSE = false; + final private static NumberFormat NF_3 = new DecimalFormat( "#.###" ); + final private static NumberFormat NF_4 = new DecimalFormat( "#.####" ); private Msa _msa; private File _out_file_base; private String _path_to_mafft; @@ -123,20 +122,6 @@ public class MsaCompactor { final private GapContribution[] calcGapContribtionsStats( final boolean norm ) { final GapContribution stats[] = calcGapContribtions( norm ); Arrays.sort( stats ); - // for( final GapContribution stat : stats ) { - // final StringBuilder sb = new StringBuilder(); - // sb.append( stat.getId() ); - // sb.append( "\t" ); - // sb.append( NF_4.format( stat.getValue() ) ); - // sb.append( "\t" ); - // sb.append( NF_4.format( stat.median() ) ); - // sb.append( "\t" ); - // sb.append( NF_4.format( stat.getMin() ) ); - // sb.append( "\t" ); - // sb.append( NF_4.format( stat.getMax() ) ); - //sb.append( "\t" ); - //System.out.println( sb ); - // } return stats; } @@ -248,46 +233,6 @@ public class MsaCompactor { } } - final private void removeViaGapAverageOLD( final double mean_gapiness, - final int step, - final boolean realign, - final File outfile, - final int minimal_effective_length ) throws IOException, - InterruptedException { - if ( step < 1 ) { - throw new IllegalArgumentException( "step cannot be less than 1" ); - } - if ( mean_gapiness < 0 ) { - throw new IllegalArgumentException( "target average gap ratio cannot be less than 0" ); - } - if ( VERBOSE ) { - System.out.println( "orig: " + msaStatsAsSB() ); - } - if ( minimal_effective_length > 1 ) { - _msa = MsaMethods.removeSequencesByMinimalLength( _msa, minimal_effective_length ); - if ( VERBOSE ) { - System.out.println( "short seq removal: " + msaStatsAsSB() ); - } - } - int counter = step; - double gr; - do { - removeWorstOffenders( step, 1, false, false, false ); - if ( realign ) { - realignWithMafft(); - } - gr = MsaMethods.calcGapRatio( _msa ); - if ( VERBOSE ) { - System.out.println( counter + ": " + msaStatsAsSB() ); - } - // write( outfile, gr ); - counter += step; - } while ( gr > mean_gapiness ); - if ( VERBOSE ) { - System.out.println( "final: " + msaStatsAsSB() ); - } - } - final private void removeViaLength( final int length, final int step, final boolean realign, -- 1.7.10.2