import java.util.ArrayList;
import java.util.List;
import java.util.SortedMap;
-import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;
import org.forester.io.parsers.PhylogenyParser;
import org.forester.io.parsers.util.ParserUtils;
import org.forester.phylogeny.Phylogeny;
-import org.forester.phylogeny.PhylogenyNode;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
-import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.util.BasicTable;
import org.forester.util.BasicTableParser;
import org.forester.util.CommandLineArguments;
import org.forester.util.EasyWriter;
import org.forester.util.ForesterUtil;
+import org.forester.util.UserException;
public final class cladinator {
- final static private String PRG_NAME = "cladinator";
- final static private String PRG_VERSION = "1.01";
- final static private String PRG_DATE = "170906";
- final static private String PRG_DESC = "clades within clades of annotated labels -- analysis of pplacer-type outputs";
- final static private String E_MAIL = "phyloxml@gmail.com";
- final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester";
- final static private String HELP_OPTION_1 = "help";
- final static private String HELP_OPTION_2 = "h";
- final static private String SEP_OPTION = "s";
- final static private String QUERY_PATTERN_OPTION = "q";
- final static private String SPECIFICS_CUTOFF_OPTION = "c";
- final static private String MAPPING_FILE_OPTION = "m";
- final static private double SPECIFICS_CUTOFF_DEFAULT = 0.8;
- final static private String SEP_DEFAULT = ".";
- final static private Pattern QUERY_PATTERN_DEFAULT = AnalysisMulti.DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE;
- private final static DecimalFormat df = new DecimalFormat( "0.0#######" );
+ final static private String PRG_NAME = "cladinator";
+ final static private String PRG_VERSION = "1.04";
+ final static private String PRG_DATE = "170915";
+ final static private String PRG_DESC = "clades within clades of annotated labels -- analysis of pplacer-type outputs";
+ final static private String E_MAIL = "phyloxml@gmail.com";
+ final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester";
+ final static private String HELP_OPTION_1 = "help";
+ final static private String HELP_OPTION_2 = "h";
+ final static private String SEP_OPTION = "s";
+ final static private String QUERY_PATTERN_OPTION = "q";
+ final static private String SPECIFICS_CUTOFF_OPTION = "c";
+ final static private String MAPPING_FILE_OPTION = "m";
+ final static private String EXTRA_PROCESSING_OPTION1 = "x";
+ final static private String EXTRA_PROCESSING1_SEP_OPTION = "xs";
+ final static private String EXTRA_PROCESSING1_KEEP_EXTRA_OPTION = "xk";
+ final static private String QUIET_OPTION = "Q";
+ final static private String VERBOSE_OPTION = "v";
+ final static private double SPECIFICS_CUTOFF_DEFAULT = 0.8;
+ final static private String SEP_DEFAULT = ".";
+ final static private Pattern QUERY_PATTERN_DEFAULT = AnalysisMulti.DEFAULT_QUERY_PATTERN_FOR_PPLACER_TYPE;
+ final static private String EXTRA_PROCESSING1_SEP_DEFAULT = "|";
+ final static private boolean EXTRA_PROCESSING1_KEEP_EXTRA_DEFAULT = false;
+ private final static DecimalFormat df = new DecimalFormat( "0.0###" );
public static void main( final String args[] ) {
try {
allowed_options.add( QUERY_PATTERN_OPTION );
allowed_options.add( SPECIFICS_CUTOFF_OPTION );
allowed_options.add( MAPPING_FILE_OPTION );
+ allowed_options.add( EXTRA_PROCESSING_OPTION1 );
+ allowed_options.add( EXTRA_PROCESSING1_SEP_OPTION );
+ allowed_options.add( EXTRA_PROCESSING1_KEEP_EXTRA_OPTION );
+ allowed_options.add( VERBOSE_OPTION );
+ allowed_options.add( QUIET_OPTION );
final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
if ( dissallowed_options.length() > 0 ) {
ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
t = null;
map = null;
}
+ final boolean extra_processing1;
+ if ( cla.isOptionSet( EXTRA_PROCESSING_OPTION1 ) ) {
+ extra_processing1 = true;
+ }
+ else {
+ extra_processing1 = false;
+ }
+ String extra_processing1_sep = EXTRA_PROCESSING1_SEP_DEFAULT;
+ if ( cla.isOptionSet( EXTRA_PROCESSING1_SEP_OPTION ) ) {
+ if ( !extra_processing1 ) {
+ ForesterUtil.fatalError( PRG_NAME,
+ "extra processing is not enabled, cannot set -"
+ + EXTRA_PROCESSING1_SEP_OPTION + " option" );
+ }
+ if ( cla.isOptionValueSet( EXTRA_PROCESSING1_SEP_OPTION ) ) {
+ extra_processing1_sep = cla.getOptionValue( EXTRA_PROCESSING1_SEP_OPTION );
+ }
+ else {
+ ForesterUtil.fatalError( PRG_NAME, "no value for extra processing separator" );
+ }
+ }
+ if ( ( extra_processing1_sep != null ) && extra_processing1_sep.equals( separator ) ) {
+ ForesterUtil.fatalError( PRG_NAME,
+ "extra processing separator must not be the same the annotation-separator" );
+ }
+ boolean extra_processing1_keep = EXTRA_PROCESSING1_KEEP_EXTRA_DEFAULT;
+ if ( cla.isOptionSet( EXTRA_PROCESSING1_KEEP_EXTRA_OPTION ) ) {
+ if ( !extra_processing1 ) {
+ ForesterUtil.fatalError( PRG_NAME,
+ "extra processing is not enabled, cannot set -"
+ + EXTRA_PROCESSING1_KEEP_EXTRA_OPTION + " option" );
+ }
+ extra_processing1_keep = true;
+ }
+ final boolean verbose;
+ if ( cla.isOptionSet( VERBOSE_OPTION ) ) {
+ verbose = true;
+ }
+ else {
+ verbose = false;
+ }
+ final boolean quit;
+ if ( cla.isOptionSet( QUIET_OPTION ) ) {
+ quit = true;
+ }
+ else {
+ quit = false;
+ }
System.out.println( "Input tree : " + intreefile );
System.out.println( "Specific-hit support cutoff: " + cutoff_specifics );
if ( mapping_file != null ) {
}
System.out.println( "Annotation-separator : " + separator );
System.out.println( "Query pattern : " + pattern );
+ System.out.println( "Extra processing : " + extra_processing1 );
+ if ( extra_processing1 ) {
+ System.out.println( "Extra processing separator : " + extra_processing1_sep );
+ System.out.println( "Keep extra annotations : " + extra_processing1_keep );
+ }
if ( outtablefile != null ) {
System.out.println( "Output table : " + outtablefile );
}
- Phylogeny p = null;
+ Phylogeny phys[] = null;
try {
final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( intreefile, true );
- p = factory.create( intreefile, pp )[ 0 ];
+ phys = factory.create( intreefile, pp );
}
catch ( final IOException e ) {
ForesterUtil.fatalError( PRG_NAME, "Could not read \"" + intreefile + "\" [" + e.getMessage() + "]" );
- System.exit( -1 );
}
- System.out.println( "Ext. nodes in input tree : " + p.getNumberOfExternalNodes() );
- if ( map != null ) {
- performMapping( pattern, map, p );
+ if ( phys.length == 0 ) {
+ ForesterUtil.fatalError( PRG_NAME, "\"" + intreefile + "\" does not contain any trees" );
}
- final ResultMulti res = AnalysisMulti.execute( p, pattern, separator, cutoff_specifics );
- printResult( res );
+ System.out.println( "Number of input trees : " + phys.length );
+ if ( phys.length == 1 ) {
+ System.out.println( "Ext. nodes in input tree : " + phys[ 0 ].getNumberOfExternalNodes() );
+ }
+ else {
+ System.out.println( "Ext. nodes in input tree 1 : " + phys[ 0 ].getNumberOfExternalNodes() );
+ }
+ final EasyWriter outtable_writer;
if ( outtablefile != null ) {
- writeResultToTable( res, outtablefile );
+ outtable_writer = ForesterUtil.createEasyWriter( outtablefile );
+ }
+ else {
+ outtable_writer = null;
+ }
+ int counter = 0;
+ for( final Phylogeny phy : phys ) {
+ if ( map != null ) {
+ AnalysisMulti.performMapping( pattern, map, phy, verbose );
+ }
+ if ( extra_processing1 ) {
+ AnalysisMulti.performExtraProcessing1( pattern,
+ phy,
+ extra_processing1_sep,
+ extra_processing1_keep,
+ separator,
+ verbose );
+ }
+ final ResultMulti res = AnalysisMulti.execute( phy, pattern, separator, cutoff_specifics );
+ if ( !quit ) {
+ if ( phys.length == 1 ) {
+ printResult( res, -1 );
+ }
+ else {
+ printResult( res, counter );
+ }
+ }
+ if ( outtable_writer != null ) {
+ writeResultToTable( res, outtable_writer );
+ outtable_writer.flush();
+ }
+ ++counter;
+ }
+ if ( outtable_writer != null ) {
+ outtable_writer.flush();
+ outtable_writer.close();
}
}
- catch ( final IllegalArgumentException e ) {
+ catch ( final UserException e ) {
ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
}
catch ( final IOException e ) {
}
}
- private final static void performMapping( final Pattern pattern,
- final SortedMap<String, String> map,
- Phylogeny p ) {
- final PhylogenyNodeIterator it = p.iteratorExternalForward();
- while ( it.hasNext() ) {
- final PhylogenyNode node = it.next();
- final String name = node.getName();
- if ( ForesterUtil.isEmpty( name ) ) {
- ForesterUtil.fatalError( PRG_NAME, "external node with empty name found" );
- }
- final Matcher m = pattern.matcher( name );
- if ( !m.find() ) {
- if ( !map.containsKey( name ) ) {
- ForesterUtil.fatalError( PRG_NAME, "no mapping for \"" + name + "\" found" );
- }
- node.setName( map.get( name ) );
- }
- }
- }
-
- private final static void printResult( final ResultMulti res ) {
- System.out.println();
- System.out.println( "Result:" );
+ private final static void printResult( final ResultMulti res, final int counter ) {
System.out.println();
+ if ( counter == -1 ) {
+ System.out.println( "Result for " + res.getQueryNamePrefix() );
+ }
+ else {
+ System.out.println( "Result for " + res.getQueryNamePrefix() + " [tree " + counter + "]" );
+ }
if ( ( res.getAllMultiHitPrefixes() == null ) | ( res.getAllMultiHitPrefixes().size() < 1 ) ) {
- System.out.println( "No match to query pattern!" );
+ System.out.println( " No match to query pattern!" );
}
else {
- System.out.println( "Matching Clade(s):" );
+ System.out.println( " Matching Clade(s):" );
for( final Prefix prefix : res.getCollapsedMultiHitPrefixes() ) {
- System.out.println( prefix );
+ System.out.println( " " + prefix );
}
if ( res.isHasSpecificMultiHitsPrefixes() ) {
System.out.println();
- System.out.println( "Specific-hit(s):" );
+ System.out.println( " Specific-hit(s):" );
for( final Prefix prefix : res.getSpecificMultiHitPrefixes() ) {
- System.out.println( prefix );
+ System.out.println( " " + prefix );
}
System.out.println();
- System.out.println( "Matching Clade(s) with Specific-hit(s):" );
+ System.out.println( " Matching Clade(s) with Specific-hit(s):" );
for( final Prefix prefix : res.getCollapsedMultiHitPrefixes() ) {
- System.out.println( prefix );
+ System.out.println( " " + prefix );
for( final Prefix spec : res.getSpecificMultiHitPrefixes() ) {
if ( spec.getPrefix().startsWith( prefix.getPrefix() ) ) {
- System.out.println( " " + spec );
+ System.out.println( " " + spec );
}
}
}
}
if ( !ForesterUtil.isEmpty( res.getAllMultiHitPrefixesDown() ) ) {
System.out.println();
- System.out.println( "Matching Down-tree Bracketing Clade(s):" );
+ System.out.println( " Matching Down-tree Bracketing Clade(s):" );
for( final Prefix prefix : res.getCollapsedMultiHitPrefixesDown() ) {
- System.out.println( prefix );
+ System.out.println( " " + prefix );
}
}
if ( !ForesterUtil.isEmpty( res.getAllMultiHitPrefixesUp() ) ) {
System.out.println();
- System.out.println( "Matching Up-tree Bracketing Clade(s):" );
+ System.out.println( " Matching Up-tree Bracketing Clade(s):" );
for( final Prefix prefix : res.getCollapsedMultiHitPrefixesUp() ) {
- System.out.println( prefix );
+ System.out.println( " " + prefix );
}
}
+ System.out.println();
+ System.out.println( " Total Number of Matches: " + res.getNumberOfMatches() + "/"
+ + res.getReferenceTreeNumberOfExternalNodes() );
}
System.out.println();
}
- private final static void writeResultToTable( final ResultMulti res, final File outtablefile ) throws IOException {
- final EasyWriter w = ForesterUtil.createEasyWriter( outtablefile );
+ private final static void writeResultToTable( final ResultMulti res, final EasyWriter w ) throws IOException {
if ( ( res.getAllMultiHitPrefixes() == null ) | ( res.getAllMultiHitPrefixes().size() < 1 ) ) {
+ w.print( res.getQueryNamePrefix() );
+ w.print( "\t" );
w.println( "No match to query pattern!" );
}
else {
for( final Prefix prefix : res.getCollapsedMultiHitPrefixes() ) {
+ w.print( res.getQueryNamePrefix() );
+ w.print( "\t" );
w.print( "Matching Clades" );
w.print( "\t" );
w.print( prefix.getPrefix() );
w.print( "\t" );
w.print( df.format( prefix.getConfidence() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getNumberOfMatches() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getReferenceTreeNumberOfExternalNodes() ) );
w.println();
}
if ( res.isHasSpecificMultiHitsPrefixes() ) {
for( final Prefix prefix : res.getSpecificMultiHitPrefixes() ) {
+ w.print( res.getQueryNamePrefix() );
+ w.print( "\t" );
w.print( "Specific-hits" );
w.print( "\t" );
w.print( prefix.getPrefix() );
w.print( "\t" );
w.print( df.format( prefix.getConfidence() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getNumberOfMatches() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getReferenceTreeNumberOfExternalNodes() ) );
w.println();
}
}
if ( !ForesterUtil.isEmpty( res.getAllMultiHitPrefixesDown() ) ) {
for( final Prefix prefix : res.getCollapsedMultiHitPrefixesDown() ) {
+ w.print( res.getQueryNamePrefix() );
+ w.print( "\t" );
w.print( "Matching Down-tree Bracketing Clades" );
w.print( "\t" );
w.print( prefix.getPrefix() );
w.print( "\t" );
w.print( df.format( prefix.getConfidence() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getNumberOfMatches() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getReferenceTreeNumberOfExternalNodes() ) );
w.println();
}
}
if ( !ForesterUtil.isEmpty( res.getAllMultiHitPrefixesUp() ) ) {
for( final Prefix prefix : res.getCollapsedMultiHitPrefixesUp() ) {
+ w.print( res.getQueryNamePrefix() );
+ w.print( "\t" );
w.print( "Matching Up-tree Bracketing Clades" );
w.print( "\t" );
w.print( prefix.getPrefix() );
w.print( "\t" );
w.print( df.format( prefix.getConfidence() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getNumberOfMatches() ) );
+ w.print( "\t" );
+ w.print( String.valueOf( res.getReferenceTreeNumberOfExternalNodes() ) );
w.println();
}
}
}
- w.flush();
- w.close();
}
private final static void print_help() {
System.out.println( "Usage:" );
System.out.println();
- System.out.println( PRG_NAME + " [options] <input tree file> [output table file]" );
+ System.out.println( PRG_NAME + " [options] <input tree(s) file> [output table file]" );
System.out.println();
System.out.println( " options:" );
System.out.println( " -" + SPECIFICS_CUTOFF_OPTION
- + "=<double>: the cutoff for \"specific-hit\" support values (default: " + SPECIFICS_CUTOFF_DEFAULT
- + ")" );
- System.out.println( " -" + SEP_OPTION + "=<separator>: the annotation-separator to be used (default: "
+ + "=<double> : the cutoff for \"specific-hit\" support values (default: "
+ + SPECIFICS_CUTOFF_DEFAULT + ")" );
+ System.out.println( " -" + SEP_OPTION + "=<separator> : the annotation-separator to be used (default: "
+ SEP_DEFAULT + ")" );
System.out.println( " -" + MAPPING_FILE_OPTION
- + "=<mapping table>: to map node names to appropriate annotations (tab-separated, two columns) (default: no mapping)" );
- System.out.println( " -" + QUERY_PATTERN_OPTION
+ + "=<mapping table> : to map node names to appropriate annotations (tab-separated, two columns) (default: no mapping)" );
+ System.out.println( " -" + EXTRA_PROCESSING_OPTION1
+ + " : to enable extra processing of annotations (e.g. \"Q16611|A.1.1\" becomes \"A.1.1\")" );
+ System.out.println( " -" + EXTRA_PROCESSING1_SEP_OPTION
+ + "=<separator> : the separator for extra annotations (default: \"" + EXTRA_PROCESSING1_SEP_DEFAULT
+ + "\")" );
+ System.out.println( " -" + EXTRA_PROCESSING1_KEEP_EXTRA_OPTION
+ + " : to keep extra annotations (e.g. \"Q16611|A.1.1\" becomes \"A.1.1.Q16611\")" );
+ System.out.println( " -" + VERBOSE_OPTION + " : verbose" );
+ System.out.println( " --" + QUERY_PATTERN_OPTION
+ "=<query pattern>: the regular expression for the query (default: \"" + QUERY_PATTERN_DEFAULT
+ "\" for pplacer output)" );
System.out.println();
System.out.println( " " + PRG_NAME + " my_tree.nh result.tsv" );
System.out.println( " " + PRG_NAME + " -c=0.5 -s=. my_tree.nh result.tsv" );
System.out.println( " " + PRG_NAME + " -c=0.9 -s=_ -m=map.tsv my_tree.nh result.tsv" );
+ System.out.println( " " + PRG_NAME + " -x -xs=& -xk my_tree.nh result.tsv" );
+ System.out.println( " " + PRG_NAME + " -x -xs=\"|\" my_tree.nh result.tsv" );
+ System.out.println( " " + PRG_NAME + " -x -xk -m=map.tsv pplacer_out_trees.sing.tre result.tsv" );
System.out.println();
}
}
git://source.jalview.org / jalview.git / blobdiff