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 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 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";
int length = -1;
int step = 1;
boolean realign = false;
- boolean norm = true;
+ boolean normalize_for_effective_seq_length = true;
String path_to_mafft = null;
int step_for_diagnostics = 1;
int min_length = -1;
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( MIN_LENGTH_OPTION ) ) );
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,
path_to_mafft = cla.getOptionValueAsCleanString( PATH_TO_MAFFT_OPTION );
}
if ( cla.isOptionSet( DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION ) ) {
- norm = false;
+ normalize_for_effective_seq_length = false;
}
if ( cla.isOptionSet( STEP_FOR_DIAGNOSTICS_OPTION ) ) {
step_for_diagnostics = cla.getOptionValueAsInt( STEP_FOR_DIAGNOSTICS_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() ) );
- System.out.println( " Gap ratio : "
- + NF_4.format( MsaMethods.calcGapRatio( msa ) ) );
- System.out.println( " Normalized Shannon Entropy (entn21): "
- + NF_4.format( MsaMethods.calcNormalizedShannonsEntropy( 21, msa ) ) );
+ "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( "Step for diagnostics reports : " + step_for_diagnostics );
System.out.println( "Calculate normalized Shannon Entropy : " + report_entropy );
- if ( !norm ) {
- System.out.println( "Normalize : " + norm );
+ if ( normalize_for_effective_seq_length ) {
+ System.out.println( "Normalize : with individual, effective sequence lenghts" );
+ }
+ else {
+ System.out.println( "Normalize : with MSA length" );
}
System.out.println( "Realign with MAFFT : " + realign );
if ( realign ) {
if ( removed_seqs_out_base != null ) {
mc.setRemovedSeqsOutBase( removed_seqs_out_base );
}
- mc.setNorm( norm );
+ mc.setNorm( normalize_for_effective_seq_length );
mc.setRealign( realign );
if ( realign ) {
mc.setPathToMafft( path_to_mafft );
msa_props = mc.removeViaLength( length );
}
else {
- msa_props = mc.chart( step, realign, norm );
+ msa_props = mc.chart( step, realign, normalize_for_effective_seq_length );
}
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 ));
}
}
catch ( final IllegalArgumentException iae ) {
}
}
+ 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)" );
+ + "=<integer> step for diagnostics reports (default: 1)" );
System.out.println( " -" + REPORT_ENTROPY
- + " to calculate normalized Shannon Entropy (not recommended for very large alignments)" );
+ + " 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" );
+ + "=<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( " -" + DO_NOT_NORMALIZE_FOR_EFF_LENGTH_OPTION
+ + " to normalize gap-contributions with MSA length, instead of individual effective sequence lenghts" );
+
System.out.println();
System.out.println();
System.out.println();
git://source.jalview.org / jalview.git / blobdiff