import org.forester.util.DescriptiveStatistics;
import org.forester.util.ForesterUtil;
+
+/*
+java -cp C:\Users\czmasek\SOFTWARE_DEV\ECLIPSE\forester\java\fo
+rester.jar org.forester.application.msa_compactor Bcl-2_e1_20_mafft -t
+*/
+
public class msa_compactor {
- final private static NumberFormat NF_1 = new DecimalFormat( "#.0" );
+ final private static NumberFormat NF_1 = new DecimalFormat( "0.#" );
+ final private static NumberFormat NF_4 = new DecimalFormat( "0.####" );
static {
NF_1.setRoundingMode( RoundingMode.HALF_UP );
+ NF_4.setRoundingMode( RoundingMode.HALF_UP );
}
final static private String HELP_OPTION_1 = "help";
final static private String HELP_OPTION_2 = "h";
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 INFO_ONLY_OPTION = "i";
//
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 OUTPUT_FORMAT_PHYLIP_OPTION = "p";
+ final static private String REPORT_ENTROPY = "e";
+ final static private String OUTPUT_FORMAT_OPTION = "f";
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";
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";
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( OUTPUT_FORMAT_PHYLIP_OPTION );
+ allowed_options.add( REPORT_ENTROPY );
+ allowed_options.add( OUTPUT_FORMAT_OPTION );
allowed_options.add( OUTPUT_REMOVED_SEQS_OPTION );
allowed_options.add( MAFFT_OPTIONS );
allowed_options.add( PERFORM_PHYLOGENETIC_INFERENCE );
+ allowed_options.add( INFO_ONLY_OPTION );
final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
if ( dissallowed_options.length() > 0 ) {
ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
msa = DeleteableMsa.createInstance( GeneralMsaParser.parse( is ) );
}
final DescriptiveStatistics initial_msa_stats = MsaMethods.calculateEffectiveLengthStatistics( msa );
+ if (cla.isOptionSet( INFO_ONLY_OPTION ) ) {
+ printInfo( in, msa, initial_msa_stats );
+ System.exit( 0 );
+ }
+
final boolean chart_only = ( !cla.isOptionSet( LENGTH_OPTION ) )
&& ( !cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) )
- && ( !cla.isOptionSet( AV_GAPINESS_OPTION ) );
+ && ( !cla.isOptionSet( AV_GAPINESS_OPTION ) && ( !cla.isOptionSet( MIN_LENGTH_OPTION ) ) );
if ( !chart_only && ( out == null ) ) {
ForesterUtil.fatalError( PRG_NAME, "outfile file missing" );
}
if ( cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION ) ) {
worst_remove = cla.getOptionValueAsInt( REMOVE_WORST_OFFENDERS_OPTION );
- if ( ( worst_remove < 1 ) || ( worst_remove >= msa.getNumberOfSequences() - 1 ) ) {
+ if ( ( worst_remove < 1 ) || ( worst_remove >= ( msa.getNumberOfSequences() - 1 ) ) ) {
ForesterUtil.fatalError( PRG_NAME, "number of worst offender sequences to remove is out of range: "
+ worst_remove );
}
if ( length >= msa.getLength() ) {
ForesterUtil.fatalError( PRG_NAME,
"target length is out of range [longer than MSA (" + msa.getLength()
- + ")]: " + length );
+ + ")]: " + length );
}
else if ( length < initial_msa_stats.getMin() ) {
ForesterUtil.fatalError( PRG_NAME,
+ initial_msa_stats.getMin() + ") ]: " + length );
}
}
+ if ( cla.isOptionSet( MIN_LENGTH_OPTION ) ) {
+ if ( cla.isOptionSet( LENGTH_OPTION ) || cla.isOptionSet( REMOVE_WORST_OFFENDERS_OPTION )
+ || cla.isOptionSet( AV_GAPINESS_OPTION ) || cla.isOptionSet( STEP_OPTION )
+ || cla.isOptionSet( REALIGN_OPTION ) || cla.isOptionSet( PATH_TO_MAFFT_OPTION )
+ || cla.isOptionSet( STEP_FOR_DIAGNOSTICS_OPTION ) || cla.isOptionSet( REPORT_ENTROPY )
+ || cla.isOptionSet( OUTPUT_REMOVED_SEQS_OPTION )
+ || cla.isOptionSet( PERFORM_PHYLOGENETIC_INFERENCE ) ) {
+ printHelp();
+ System.exit( 0 );
+ }
+ min_length = cla.getOptionValueAsInt( MIN_LENGTH_OPTION );
+ if ( ( min_length < 2 ) || ( min_length > initial_msa_stats.getMax() ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "value for minimal sequence length is out of range: "
+ + min_length );
+ }
+ }
if ( cla.isOptionSet( STEP_OPTION ) ) {
step = cla.getOptionValueAsInt( STEP_OPTION );
if ( ( step < 1 )
+ step_for_diagnostics );
}
}
- if ( cla.isOptionSet( MIN_LENGTH_OPTION ) ) {
- min_length = cla.getOptionValueAsInt( MIN_LENGTH_OPTION );
- if ( ( min_length < 2 ) || ( min_length > initial_msa_stats.getMax() ) ) {
- ForesterUtil.fatalError( PRG_NAME, "value for minimal sequence length is out of range: "
- + min_length );
- }
- }
if ( cla.isOptionSet( GAP_RATIO_LENGTH_OPTION ) ) {
gap_ratio = cla.getOptionValueAsDouble( GAP_RATIO_LENGTH_OPTION );
if ( ( gap_ratio < 0 ) || ( gap_ratio > 1 ) ) {
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;
+ if ( cla.isOptionSet( OUTPUT_FORMAT_OPTION ) ) {
+ final String fs = cla.getOptionValueAsCleanString( OUTPUT_FORMAT_OPTION );
+ if ( fs.equalsIgnoreCase( "p" ) ) {
+ output_format = MSA_FORMAT.PHYLIP;
+ }
+ else if ( fs.equalsIgnoreCase( "f" ) ) {
+ output_format = MSA_FORMAT.FASTA;
+ }
+ else if ( fs.equalsIgnoreCase( "n" ) ) {
+ output_format = MSA_FORMAT.NEXUS;
+ }
+ else {
+ ForesterUtil.fatalError( PRG_NAME, "illegal or empty output format option: " + fs );
+ }
}
if ( cla.isOptionSet( OUTPUT_REMOVED_SEQS_OPTION ) ) {
final String s = cla.getOptionValueAsCleanString( OUTPUT_REMOVED_SEQS_OPTION );
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)" );
+ .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,
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,
- PRG_VERSION,
- PRG_DATE,
- E_MAIL,
- WWW,
- ForesterUtil.getForesterLibraryInformation() );
- System.out.println( "Input MSA : " + in );
- System.out.println( " MSA length : " + msa.getLength() );
- System.out.println( " Number of sequences : " + msa.getNumberOfSequences() );
- System.out.println( " Median sequence length : " + NF_1.format( initial_msa_stats.median() ) );
- System.out.println( " Mean sequence length : "
- + 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() ) );
+ "step for diagnostics reports needs to be set to 1 for tree calculation" );
+ }
+ }
+ printInfo( in, msa, initial_msa_stats );
if ( !chart_only ) {
System.out.println( "Output : " + out );
}
- else {
- System.out.println( "Output : n/a" );
- }
+
if ( removed_seqs_out_base != null ) {
System.out.println( "Write removed sequences to : " + removed_seqs_out_base );
}
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" ) );
- }
- if ( chart_only && !realign ) {
- System.out.println( "Step for output and re-aligning : n/a" );
+ System.out.print( "Output format : " );
+ if ( output_format == MSA_FORMAT.FASTA ) {
+ System.out.println( "fasta" );
+ }
+ else if ( output_format == MSA_FORMAT.PHYLIP ) {
+ System.out.println( "phylip" );
+ }
+ else if ( output_format == MSA_FORMAT.NEXUS ) {
+ System.out.println( "nexus" );
+ }
}
- else {
- if ( chart_only ) {
- System.out.println( "Step for re-aligning : " + step );
+ if ( min_length == -1 ) {
+ if ( chart_only && !realign ) {
+ System.out.println( "Step for output and re-aligning : n/a" );
}
else {
- System.out.println( "Step for output and re-aligning : " + step );
+ 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 normalized Shannon Entropy : " + report_entropy );
+ if ( !norm ) {
+ System.out.println( "Normalize : " + norm );
+ }
+ System.out.println( "Realign with MAFFT : " + realign );
+ if ( realign ) {
+ System.out.println( "MAFFT options : " + mafft_options );
+ }
+ System.out.println( "Simple tree (Kimura distances, NJ) : " + perform_phylogenetic_inference );
}
- System.out.println( "Step for diagnostics reports : " + step_for_diagnostics );
- System.out.println( "Calculate mean identity : " + report_aln_mean_identity );
- if ( !norm ) {
- System.out.println( "Normalize : " + norm );
- }
- System.out.println( "Realign with MAFFT : " + realign );
- if ( realign ) {
- System.out.println( "MAFFT options : " + mafft_options );
- }
- System.out.println( "Simple tree (Kimura distances, NJ) : " + perform_phylogenetic_inference );
System.out.println();
final int initial_number_of_seqs = msa.getNumberOfSequences();
List<MsaProperties> msa_props = null;
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.setReportAlnMeanIdentity( report_aln_mean_identity );
- mc.setPeformPhylogenticInference( perform_phylogenetic_inference );
- if ( ( worst_remove > 0 ) || ( av_gap > 0 ) || ( length > 0 ) ) {
+ if ( ( worst_remove > 0 ) || ( av_gap > 0 ) || ( length > 0 ) || ( min_length != -1 ) ) {
mc.setOutputFormat( output_format );
mc.setOutFileBase( out );
- if ( removed_seqs_out_base != null ) {
- mc.setRemovedSeqsOutBase( removed_seqs_out_base );
- }
}
- if ( min_length > 1 ) {
+ 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 ) {
- msa_props = mc.removeViaGapAverage( av_gap );
- }
- else if ( length > 0 ) {
- msa_props = mc.removeViaLength( length );
}
else {
- msa_props = mc.chart( step, realign, norm );
+ mc.setPeformPhylogenticInference( perform_phylogenetic_inference );
+ if ( removed_seqs_out_base != null ) {
+ mc.setRemovedSeqsOutBase( removed_seqs_out_base );
+ }
+ 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 );
+ if ( worst_remove > 0 ) {
+ msa_props = mc.removeWorstOffenders( worst_remove );
+ }
+ else if ( av_gap > 0 ) {
+ msa_props = mc.removeViaGapAverage( av_gap );
+ }
+ else if ( length > 0 ) {
+ msa_props = mc.removeViaLength( length );
+ }
+ else {
+ msa_props = mc.chart( step, realign, norm );
+ }
+ Chart.display( msa_props, initial_number_of_seqs, report_entropy, in.getName() );
+ System.out.println();
+ System.out.println( "Final MSA properties" );
+ printMsaInfo( msa, MsaMethods.calculateEffectiveLengthStatistics( msa ));
}
- Chart.display( msa_props, initial_number_of_seqs, report_aln_mean_identity, in.getName() );
}
catch ( final IllegalArgumentException iae ) {
// iae.printStackTrace(); //TODO remove me
}
}
+ private static void printInfo( final File in, DeleteableMsa msa, final DescriptiveStatistics initial_msa_stats ) {
+ ForesterUtil.printProgramInformation( PRG_NAME,
+ PRG_DESC,
+ PRG_VERSION,
+ PRG_DATE,
+ E_MAIL,
+ WWW,
+ ForesterUtil.getForesterLibraryInformation() );
+ System.out.println( "Input MSA : " + in );
+ printMsaInfo( msa, initial_msa_stats );
+ }
+
+ private static void printMsaInfo( DeleteableMsa msa, final DescriptiveStatistics msa_stats ) {
+ System.out.println( "MSA length : " + msa.getLength() );
+ System.out.println( "Number of sequences : " + msa.getNumberOfSequences() );
+ System.out.println( "Median sequence length : " + NF_1.format( msa_stats.median() ) );
+ System.out.println( "Mean sequence length : "
+ + NF_1.format( msa_stats.arithmeticMean() ) );
+ System.out.println( "Max sequence length : " + ( ( int ) msa_stats.getMax() ) );
+ System.out.println( "Min sequence length : " + ( ( int ) msa_stats.getMin() ) );
+ System.out.println( "Gap ratio : "
+ + NF_4.format( MsaMethods.calcGapRatio( msa ) ) );
+ System.out.println( "Mean gap count per sequence : "
+ + NF_1.format( MsaMethods.calcNumberOfGapsStats( msa ).arithmeticMean() ) );
+ System.out.println( "Normalized Shannon Entropy (entn7) : "
+ + NF_4.format( MsaMethods.calcNormalizedShannonsEntropy( 7, msa ) ) );
+ System.out.println( "Normalized Shannon Entropy (entn21) : "
+ + NF_4.format( MsaMethods.calcNormalizedShannonsEntropy( 21, msa ) ) );
+ }
+
private static void checkPathToMafft( final String path_to_mafft ) {
if ( !ForesterUtil.isEmpty( path_to_mafft ) && MsaInferrer.isInstalled( path_to_mafft ) ) {
}
else {
if ( ForesterUtil.isEmpty( path_to_mafft ) ) {
ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable found, use -\"" + PATH_TO_MAFFT_OPTION
- + "=<path to MAFFT>\" option" );
+ + "=<path to MAFFT>\" option" );
}
else {
ForesterUtil.fatalError( PRG_NAME, "no MAFFT executable at \"" + path_to_mafft + "\"" );
}
System.out.println( "Usage:" );
System.out.println();
- System.out.println( PRG_NAME + " <options> <msa input file> <output file base>" );
+ System.out.println( PRG_NAME + " [options] <msa input file> [output file base]" );
System.out.println();
System.out.println( " options: " );
System.out.println();
+ System.out.println( " -" + INFO_ONLY_OPTION
+ + " to only display same basic information about the MSA" );
System.out.println( " -" + REMOVE_WORST_OFFENDERS_OPTION
- + "=<integer> number of worst offender sequences to remove" );
+ + "=<integer> number of worst offender sequences to remove" );
System.out.println( " -" + LENGTH_OPTION + "=<integer> target MSA length" );
System.out.println( " -" + AV_GAPINESS_OPTION + "=<decimal> target gap-ratio (0.0-1.0)" );
System.out.println( " -" + REALIGN_OPTION + " to realign using MAFFT" + mafft_comment );
System.out.println( " -" + MAFFT_OPTIONS + "=<string> options for MAFFT (default: --auto)" );
System.out.println( " -" + STEP_OPTION + "=<integer> step for output and re-aligning (default: 1)" );
System.out.println( " -" + STEP_FOR_DIAGNOSTICS_OPTION
- + "=<integer> step for diagnostics reports (default: 1)" );
- System.out
- .println( " -"
- + REPORT_ALN_MEAN_IDENTITY
- + " to calculate mean MSA column identity (\"MSA quality\") (not recommended for very large alignments)" );
- System.out.println( " -" + OUTPUT_FORMAT_PHYLIP_OPTION
- + " to write output alignments in phylip format instead of fasta" );
+ + "=<integer> step for diagnostics reports (default: 1)" );
+ System.out.println( " -" + REPORT_ENTROPY
+ + " to calculate normalized Shannon Entropy (not recommended for very large alignments)" );
+ System.out.println( " -" + OUTPUT_FORMAT_OPTION
+ + "=<f|p|n> format for output alignments: f for fasta (default), p for phylip, or n for nexus" );
System.out.println( " -" + OUTPUT_REMOVED_SEQS_OPTION + "=<file> to output the removed sequences" );
System.out.println( " -" + MIN_LENGTH_OPTION
- + "=<integer> minimal effecive sequence length (for deleting of shorter sequences)" );
+ + "=<integer> minimal effecive sequence length (for deleting of shorter sequences)" );
System.out.println( " -" + GAP_RATIO_LENGTH_OPTION
- + "=<decimal> maximal allowed gap ratio per column (for deleting of columms) (0.0-1.0)" );
+ + "=<decimal> 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)" );
+ + " to calculate a simple phylogenetic tree (Kimura distances, NJ)" );
System.out.println();
System.out.println();
System.out.println();