X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fmsa_compactor.java;h=19d5caf03ab28b601ff2f5c45f7a24dfb0fcf2ad;hb=327fc7c7a9a46cbe8983b0ca2a54cc6f45cd1695;hp=996ccf3c55d950a152cf35be4cd1e649b34dcc0c;hpb=7c0f14dccfa95a3f709da6eff6ebe635390d1841;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 996ccf3..19d5caf 100644 --- a/forester/java/src/org/forester/application/msa_compactor.java +++ b/forester/java/src/org/forester/application/msa_compactor.java @@ -63,17 +63,18 @@ public class msa_compactor { final static private String STEP_FOR_DIAGNOSTICS_OPTION = "sd"; final static private String MIN_LENGTH_OPTION = "ml"; final static private String GAP_RATIO_LENGTH_OPTION = "gr"; - final static private String REPORT_ALN_MEAN_IDENTITY = "q"; + final static private String REPORT_ENTROPY = "e"; final static private String OUTPUT_FORMAT_PHYLIP_OPTION = "p"; final static private String OUTPUT_REMOVED_SEQS_OPTION = "ro"; final static private String MAFFT_OPTIONS = "mo"; + final static private String PERFORM_PHYLOGENETIC_INFERENCE = "t"; // 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 sequence aligment compactor"; - final static private String PRG_VERSION = "0.2"; - final static private String PRG_DATE = "140428"; + final static private String PRG_VERSION = "0.3"; + final static private String PRG_DATE = "140508"; final static private String E_MAIL = "czmasek@sanfordburham.org"; final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester"; @@ -100,10 +101,11 @@ public class msa_compactor { int step_for_diagnostics = 1; int min_length = -1; double gap_ratio = -1; - boolean report_aln_mean_identity = false; + boolean report_entropy = false; MSA_FORMAT output_format = MSA_FORMAT.FASTA; File removed_seqs_out_base = null; String mafft_options = "--auto"; + boolean perform_phylogenetic_inference = false; final List allowed_options = new ArrayList(); allowed_options.add( REMOVE_WORST_OFFENDERS_OPTION ); allowed_options.add( AV_GAPINESS_OPTION ); @@ -115,10 +117,11 @@ public class msa_compactor { allowed_options.add( STEP_FOR_DIAGNOSTICS_OPTION ); allowed_options.add( MIN_LENGTH_OPTION ); allowed_options.add( GAP_RATIO_LENGTH_OPTION ); - allowed_options.add( REPORT_ALN_MEAN_IDENTITY ); + allowed_options.add( REPORT_ENTROPY ); allowed_options.add( OUTPUT_FORMAT_PHYLIP_OPTION ); allowed_options.add( OUTPUT_REMOVED_SEQS_OPTION ); allowed_options.add( MAFFT_OPTIONS ); + allowed_options.add( PERFORM_PHYLOGENETIC_INFERENCE ); final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options ); if ( dissallowed_options.length() > 0 ) { ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options ); @@ -132,9 +135,10 @@ public class msa_compactor { msa = DeleteableMsa.createInstance( GeneralMsaParser.parse( is ) ); } final DescriptiveStatistics initial_msa_stats = MsaMethods.calculateEffectiveLengthStatistics( msa ); - //System.out.println( initial_msa_stats.toString() ); - if ( ( cla.isOptionSet( LENGTH_OPTION ) || cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) || cla - .isOptionSet( AV_GAPINESS_OPTION ) ) && ( out == null ) ) { + final boolean chart_only = ( !cla.isOptionSet( LENGTH_OPTION ) ) + && ( !cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) ) + && ( !cla.isOptionSet( AV_GAPINESS_OPTION ) ); + if ( !chart_only && ( out == null ) ) { ForesterUtil.fatalError( PRG_NAME, "outfile file missing" ); } if ( cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) ) { @@ -211,8 +215,8 @@ public class msa_compactor { ForesterUtil.fatalError( PRG_NAME, "gap ratio is out of range: " + gap_ratio ); } } - if ( cla.isOptionSet( REPORT_ALN_MEAN_IDENTITY ) ) { - report_aln_mean_identity = true; + if ( cla.isOptionSet( REPORT_ENTROPY ) ) { + report_entropy = true; } if ( cla.isOptionSet( OUTPUT_FORMAT_PHYLIP_OPTION ) ) { output_format = MSA_FORMAT.PHYLIP; @@ -229,14 +233,33 @@ public class msa_compactor { if ( cla.isOptionSet( MAFFT_OPTIONS ) ) { mafft_options = cla.getOptionValueAsCleanString( MAFFT_OPTIONS ); if ( ForesterUtil.isEmpty( mafft_options ) || ( mafft_options.length() < 3 ) ) { - ForesterUtil.fatalError( PRG_NAME, "gap ratio is out of range: " + gap_ratio ); + ForesterUtil.fatalError( PRG_NAME, "illegal or empty MAFFT options: " + mafft_options ); } } } - if ( ( !cla.isOptionSet( LENGTH_OPTION ) && !cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) && !cla - .isOptionSet( AV_GAPINESS_OPTION ) ) && ( ( out != null ) || ( removed_seqs_out_base != null ) ) ) { - ForesterUtil.fatalError( PRG_NAME, - "chart only, no outfile(s) produced (no need to indicate output file(s))" ); + else if ( cla.isOptionSet( MAFFT_OPTIONS ) ) { + ForesterUtil.fatalError( PRG_NAME, "no need to indicate MAFFT options without realigning" ); + } + if ( cla.isOptionSet( PERFORM_PHYLOGENETIC_INFERENCE ) ) { + perform_phylogenetic_inference = true; + } + if ( chart_only ) { + if ( ( out != null ) || ( removed_seqs_out_base != null ) ) { + ForesterUtil + .fatalError( PRG_NAME, + "chart only, no outfile(s) produced, thus no need to indicate output file(s)" ); + } + if ( !realign && cla.isOptionSet( STEP_OPTION ) ) { + ForesterUtil.fatalError( PRG_NAME, + "chart only, no re-aligning, thus no need to use step for output and re-aligning; use -" + + STEP_FOR_DIAGNOSTICS_OPTION + " instead" ); + } + } + if ( perform_phylogenetic_inference ) { + if ( step_for_diagnostics != 1 ) { + ForesterUtil.fatalError( PRG_NAME, + "step for diagnostics reports needs to be set to 1 for tree calculation" ); + } } ForesterUtil.printProgramInformation( PRG_NAME, PRG_DESC, @@ -253,7 +276,7 @@ public class msa_compactor { + NF_1.format( initial_msa_stats.arithmeticMean() ) ); System.out.println( " Max sequence length : " + ( ( int ) initial_msa_stats.getMax() ) ); System.out.println( " Min sequence length : " + ( ( int ) initial_msa_stats.getMin() ) ); - if ( out != null ) { + if ( !chart_only ) { System.out.println( "Output : " + out ); } else { @@ -265,22 +288,35 @@ public class msa_compactor { if ( worst_remove > 0 ) { System.out.println( "Number of worst offenders to remove : " + worst_remove ); } - else if ( av_gap > 0 ) { + if ( av_gap > 0 ) { System.out.println( "Target gap-ratio : " + av_gap ); } - else if ( length > 0 ) { + if ( length > 0 ) { System.out.println( "Target MSA length : " + length ); } - else { - System.out.println( "Chart and diagnostics only : true" ); + if ( min_length > 1 ) { + System.out.println( "Minimal effective sequence length : " + min_length ); + } + if ( gap_ratio > -1 ) { + System.out.println( "Maximum allowed gap ratio per column : " + gap_ratio ); } if ( ( out != null ) || ( removed_seqs_out_base != null ) ) { System.out.println( "Output format : " + ( output_format == MSA_FORMAT.FASTA ? "fasta" : "phylip" ) ); } - System.out.println( "Step for output and re-aligning : " + step ); + if ( chart_only && !realign ) { + System.out.println( "Step for output and re-aligning : n/a" ); + } + else { + if ( chart_only ) { + System.out.println( "Step for re-aligning : " + step ); + } + else { + System.out.println( "Step for output and re-aligning : " + step ); + } + } System.out.println( "Step for diagnostics reports : " + step_for_diagnostics ); - System.out.println( "Calculate mean identity : " + report_aln_mean_identity ); + System.out.println( "Calculate normalized Shannon Entropy : " + report_entropy ); if ( !norm ) { System.out.println( "Normalize : " + norm ); } @@ -288,87 +324,46 @@ public class msa_compactor { if ( realign ) { System.out.println( "MAFFT options : " + mafft_options ); } - if ( min_length > -1 ) { - System.out.println( "Minimal effective sequence length : " + min_length ); - } - if ( gap_ratio > -1 ) { - System.out.println( "Maximum allowed gap ratio per column : " + gap_ratio ); - } + System.out.println( "Simple tree (Kimura distances, NJ) : " + perform_phylogenetic_inference ); System.out.println(); - // - // final int initial_number_of_seqs = msa.getNumberOfSequences(); List msa_props = null; - if ( worst_remove > 0 ) { - final MsaCompactor mc = new MsaCompactor( msa ); - mc.setRealign( realign ); + final MsaCompactor mc = new MsaCompactor( msa ); + mc.setInfileName( in.getName() ); + mc.setNorm( norm ); + mc.setRealign( realign ); + if ( realign ) { + mc.setPathToMafft( path_to_mafft ); + mc.setMafftOptions( mafft_options ); + } + mc.setStep( step ); + mc.setStepForDiagnostics( step_for_diagnostics ); + mc.setCalculateNormalizedShannonEntropy( report_entropy ); + mc.setPeformPhylogenticInference( perform_phylogenetic_inference ); + if ( ( worst_remove > 0 ) || ( av_gap > 0 ) || ( length > 0 ) ) { mc.setOutputFormat( output_format ); - if ( realign ) { - mc.setPathToMafft( path_to_mafft ); - mc.setMafftOptions( mafft_options ); - } - mc.setNorm( norm ); - mc.setReportAlnMeanIdentity( report_aln_mean_identity ); mc.setOutFileBase( out ); if ( removed_seqs_out_base != null ) { mc.setRemovedSeqsOutBase( removed_seqs_out_base ); } - mc.setStep( step ); - mc.setStepForDiagnostics( step_for_diagnostics ); + } + if ( min_length > 1 ) { + mc.removeSequencesByMinimalLength( min_length ); + mc.writeMsa( new File( "removed" ) ); + } + if ( worst_remove > 0 ) { msa_props = mc.removeWorstOffenders( worst_remove ); } else if ( av_gap > 0 ) { - final MsaCompactor mc = new MsaCompactor( msa ); - mc.setRealign( realign ); - mc.setOutputFormat( output_format ); - if ( realign ) { - mc.setPathToMafft( path_to_mafft ); - mc.setMafftOptions( mafft_options ); - } - mc.setNorm( norm ); - mc.setReportAlnMeanIdentity( report_aln_mean_identity ); - mc.setOutFileBase( out ); - if ( removed_seqs_out_base != null ) { - mc.setRemovedSeqsOutBase( removed_seqs_out_base ); - } - mc.setStep( step ); - mc.setStepForDiagnostics( step_for_diagnostics ); msa_props = mc.removeViaGapAverage( av_gap ); } else if ( length > 0 ) { - final MsaCompactor mc = new MsaCompactor( msa ); - mc.setRealign( realign ); - mc.setOutputFormat( output_format ); - if ( realign ) { - mc.setPathToMafft( path_to_mafft ); - mc.setMafftOptions( mafft_options ); - } - mc.setNorm( norm ); - mc.setReportAlnMeanIdentity( report_aln_mean_identity ); - mc.setOutFileBase( out ); - if ( removed_seqs_out_base != null ) { - mc.setRemovedSeqsOutBase( removed_seqs_out_base ); - } - mc.setStep( step ); - mc.setStepForDiagnostics( step_for_diagnostics ); msa_props = mc.removeViaLength( length ); } else { - //MsaCompactor.chart( msa, step, realign, norm, path_to_mafft ); - final MsaCompactor mc = new MsaCompactor( msa ); - mc.setRealign( realign ); - if ( realign ) { - mc.setPathToMafft( path_to_mafft ); - mc.setMafftOptions( mafft_options ); - } - mc.setNorm( norm ); - mc.setReportAlnMeanIdentity( report_aln_mean_identity ); - mc.setOutFileBase( out ); - mc.setStep( step ); - mc.setStepForDiagnostics( step_for_diagnostics ); msa_props = mc.chart( step, realign, norm ); } - Chart.display( msa_props, initial_number_of_seqs, report_aln_mean_identity, in.toString() ); + Chart.display( msa_props, initial_number_of_seqs, report_entropy, in.getName() ); } catch ( final IllegalArgumentException iae ) { // iae.printStackTrace(); //TODO remove me @@ -428,17 +423,17 @@ public class msa_compactor { System.out.println( " -" + STEP_OPTION + "= step for output and re-aligning (default: 1)" ); System.out.println( " -" + STEP_FOR_DIAGNOSTICS_OPTION + "= step for diagnostics reports (default: 1)" ); - // System.out.println( " -" + MIN_LENGTH_OPTION - // + "= minimal effecive sequence length (for deleting of shorter sequences)" ); - // System.out.println( " -" + GAP_RATIO_LENGTH_OPTION - // + "= maximal allowed gap ratio per column (for deleting of columms) (0.0-1.0)" ); - System.out - .println( " -" - + REPORT_ALN_MEAN_IDENTITY - + " to calculate mean MSA column identity (\"MSA quality\") (not recommended for very large alignments)" ); + System.out.println( " -" + REPORT_ENTROPY + + " to calculate normalized Shannon Entropy (not recommended for very large alignments)" ); System.out.println( " -" + OUTPUT_FORMAT_PHYLIP_OPTION + " to write output alignments in phylip format instead of fasta" ); System.out.println( " -" + OUTPUT_REMOVED_SEQS_OPTION + "= to output the removed sequences" ); + System.out.println( " -" + MIN_LENGTH_OPTION + + "= minimal effecive sequence length (for deleting of shorter sequences)" ); + System.out.println( " -" + GAP_RATIO_LENGTH_OPTION + + "= maximal allowed gap ratio per column (for deleting of columms) (0.0-1.0)" ); + System.out.println( " -" + PERFORM_PHYLOGENETIC_INFERENCE + + " to calculate a simple phylogenetic tree (Kimura distances, NJ)" ); System.out.println(); System.out.println(); System.out.println();