import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
-import java.util.SortedSet;
-import java.util.TreeSet;
import org.forester.datastructures.IntMatrix;
import org.forester.io.parsers.phyloxml.PhyloXmlParser;
import org.forester.phylogeny.Phylogeny;
-import org.forester.phylogeny.PhylogenyNode;
-import org.forester.phylogeny.data.Taxonomy;
+import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
import org.forester.rio.RIO;
+import org.forester.rio.RIO.REROOTING;
import org.forester.rio.RIOException;
-import org.forester.sdi.SDI.ALGORITHM;
import org.forester.sdi.SDIException;
+import org.forester.sdi.SDIutil.ALGORITHM;
+import org.forester.util.BasicDescriptiveStatistics;
import org.forester.util.CommandLineArguments;
import org.forester.util.EasyWriter;
import org.forester.util.ForesterUtil;
public class rio {
final static private String PRG_NAME = "rio";
- final static private String PRG_VERSION = "4.000 beta 1";
- final static private String PRG_DATE = "2012.12.11";
+ final static private String PRG_VERSION = "4.000 beta 3";
+ final static private String PRG_DATE = "2012.12.17";
final static private String E_MAIL = "czmasek@burnham.org";
final static private String WWW = "www.phylosoft.org/forester/";
final static private String HELP_OPTION_1 = "help";
final static private String HELP_OPTION_2 = "h";
+ final static private String GT_FIRST = "f";
+ final static private String GT_LAST = "l";
+ final static private String REROOTING_OPT = "r";
+ final static private String OUTGROUP = "o";
final static private String USE_SDIR = "b";
public static void main( final String[] args ) {
if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
printHelp();
}
- if ( ( args.length < 3 ) || ( args.length > 5 ) ) {
+ if ( ( args.length < 3 ) || ( args.length > 8 ) ) {
System.out.println();
System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
System.out.println();
printHelp();
}
final List<String> allowed_options = new ArrayList<String>();
+ allowed_options.add( GT_FIRST );
+ allowed_options.add( GT_LAST );
+ allowed_options.add( REROOTING_OPT );
+ allowed_options.add( OUTGROUP );
allowed_options.add( USE_SDIR );
final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
if ( dissallowed_options.length() > 0 ) {
}
final File gene_trees_file = cla.getFile( 0 );
final File species_tree_file = cla.getFile( 1 );
- final File othology_outtable = cla.getFile( 2 );
+ final File orthology_outtable = cla.getFile( 2 );
final File logfile;
if ( cla.getNumberOfNames() > 3 ) {
logfile = cla.getFile( 3 );
else {
logfile = null;
}
+ String outgroup = null;
+ if ( cla.isOptionSet( OUTGROUP ) ) {
+ if ( !cla.isOptionHasAValue( OUTGROUP ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "no value for -" + OUTGROUP );
+ }
+ outgroup = cla.getOptionValueAsCleanString( OUTGROUP );
+ }
+ REROOTING rerooting = REROOTING.BY_ALGORITHM;
+ if ( cla.isOptionSet( REROOTING_OPT ) ) {
+ if ( !cla.isOptionHasAValue( REROOTING_OPT ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "no value for -" + REROOTING_OPT );
+ }
+ final String rerooting_str = cla.getOptionValueAsCleanString( REROOTING_OPT ).toLowerCase();
+ if ( rerooting_str.equals( "none" ) ) {
+ rerooting = REROOTING.NONE;
+ }
+ else if ( rerooting_str.equals( "midpoint" ) ) {
+ rerooting = REROOTING.MIDPOINT;
+ }
+ else if ( rerooting_str.equals( "outgroup" ) ) {
+ rerooting = REROOTING.OUTGROUP;
+ }
+ else {
+ ForesterUtil.fatalError( PRG_NAME, "legal values for -" + REROOTING_OPT
+ + " are: none, midpoint, or outgroup (minizming duplications is default)" );
+ }
+ }
+ int gt_first = -1;
+ int gt_last = -1;
+ if ( cla.isOptionSet( GT_FIRST ) ) {
+ if ( !cla.isOptionHasAValue( GT_FIRST ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "no value for -" + GT_FIRST );
+ }
+ try {
+ gt_first = cla.getOptionValueAsInt( GT_FIRST );
+ }
+ catch ( IOException e ) {
+ ForesterUtil.fatalError( PRG_NAME, "could not parse integer for -" + GT_FIRST );
+ }
+ }
+ if ( cla.isOptionSet( GT_LAST ) ) {
+ if ( !cla.isOptionHasAValue( GT_LAST ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "no value for -" + GT_LAST );
+ }
+ try {
+ gt_last = cla.getOptionValueAsInt( GT_LAST );
+ }
+ catch ( IOException e ) {
+ ForesterUtil.fatalError( PRG_NAME, "could not parse integer for -" + GT_LAST );
+ }
+ }
ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, gene_trees_file );
ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, species_tree_file );
- if ( othology_outtable.exists() ) {
- ForesterUtil.fatalError( PRG_NAME, "\"" + othology_outtable + "\" already exists" );
+ if ( orthology_outtable.exists() ) {
+ ForesterUtil.fatalError( PRG_NAME, "\"" + orthology_outtable + "\" already exists" );
}
boolean sdir = false;
if ( cla.isOptionSet( USE_SDIR ) ) {
+ if ( cla.isOptionHasAValue( USE_SDIR ) ) {
+ ForesterUtil.fatalError( PRG_NAME, "no value allowed for -" + USE_SDIR );
+ }
sdir = true;
if ( logfile != null ) {
ForesterUtil.fatalError( PRG_NAME, "logfile output only for GSDIR algorithm" );
long time = 0;
System.out.println( "Gene trees : " + gene_trees_file );
System.out.println( "Species tree : " + species_tree_file );
- System.out.println( "All vs all orthology table: " + othology_outtable );
+ System.out.println( "All vs all orthology table: " + orthology_outtable );
if ( !sdir ) {
if ( logfile != null ) {
System.out.println( "Logfile : " + logfile );
if ( !species_tree.isRooted() ) {
ForesterUtil.fatalError( PRG_NAME, "species tree is not rooted" );
}
+ final int o = PhylogenyMethods.countNumberOfOneDescendantNodes( species_tree );
+ if ( o > 0 ) {
+ ForesterUtil.printWarningMessage( PRG_NAME, "species tree has " + o
+ + " internal nodes with only one descendent! Going to strip them." );
+ PhylogenyMethods.deleteInternalNodesWithOnlyOneDescendent( species_tree );
+ if ( PhylogenyMethods.countNumberOfOneDescendantNodes( species_tree ) > 0 ) {
+ ForesterUtil.unexpectedFatalError( PRG_NAME, "stripping of one-desc nodes failed" );
+ }
+ }
final ALGORITHM algorithm;
if ( sdir ) {
algorithm = ALGORITHM.SDIR;
algorithm = ALGORITHM.GSDIR;
}
try {
- final RIO rio = new RIO( gene_trees_file, species_tree, algorithm, logfile != null, true );
+ final RIO rio = RIO.executeAnalysis( gene_trees_file,
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ logfile != null,
+ true );
if ( algorithm == ALGORITHM.GSDIR ) {
ForesterUtil.programMessage( PRG_NAME, "taxonomy linking based on: " + rio.getGSDIRtaxCompBase() );
}
- tableOutput( othology_outtable, rio );
- if ( ( algorithm == ALGORITHM.GSDIR ) && ( logfile != null ) ) {
- writeLogFile( logfile, rio );
+ tableOutput( orthology_outtable, rio );
+ if ( ( algorithm != ALGORITHM.SDIR ) && ( logfile != null ) ) {
+ writeLogFile( logfile,
+ rio,
+ species_tree_file,
+ gene_trees_file,
+ orthology_outtable,
+ PRG_NAME,
+ PRG_VERSION,
+ PRG_DATE,
+ ForesterUtil.getForesterLibraryInformation() );
}
+ final BasicDescriptiveStatistics stats = rio.getDuplicationsStatistics();
+ final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.#" );
+ ForesterUtil.programMessage( PRG_NAME,
+ "Mean number of duplications : " + df.format( stats.arithmeticMean() )
+ + " (sd: " + df.format( stats.sampleStandardDeviation() ) + ")" );
+ if ( stats.getN() > 3 ) {
+ ForesterUtil.programMessage( PRG_NAME, "Median number of duplications: " + df.format( stats.median() ) );
+ }
+ ForesterUtil.programMessage( PRG_NAME, "Minimum duplications : " + ( int ) stats.getMin() );
+ ForesterUtil.programMessage( PRG_NAME, "Maximum duplications : " + ( int ) stats.getMax() );
}
catch ( final RIOException e ) {
ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
System.exit( 0 );
}
- private static void writeLogFile( final File logfile, final RIO rio ) throws IOException {
- final EasyWriter out = ForesterUtil.createEasyWriter( logfile );
- out.println( "Species stripped from gene trees:" );
- final SortedSet<String> rn = new TreeSet<String>();
- for( final PhylogenyNode n : rio.getRemovedGeneTreeNodes() ) {
- final Taxonomy t = n.getNodeData().getTaxonomy();
- switch ( rio.getGSDIRtaxCompBase() ) {
- case CODE: {
- rn.add( t.getTaxonomyCode() );
- break;
- }
- case ID: {
- rn.add( t.getIdentifier().toString() );
- break;
- }
- case SCIENTIFIC_NAME: {
- rn.add( t.getScientificName() );
- break;
- }
- }
- }
- for( final String s : rn ) {
- out.println( s );
- }
- out.println();
- out.println( "Some information about duplication numbers in gene trees:" );
- out.println( rio.getLog().toString() );
- out.close();
- ForesterUtil.programMessage( PRG_NAME, "wrote log to \"" + logfile + "\"" );
+ private final static void printHelp() {
+ System.out.println( "Usage" );
+ System.out.println();
+ System.out
+ .println( PRG_NAME
+ + " [options] <gene trees infile> <species tree infile> <all vs all orthology table outfile> [logfile]" );
+ System.out.println();
+ System.out.println( " Options" );
+ System.out.println( " -" + GT_FIRST + "=<first> : to" );
+ System.out.println( " -" + GT_LAST + "=<last> : to" );
+ System.out.println( " -" + REROOTING_OPT + " : to" );
+ System.out.println( " -" + OUTGROUP + "=<outgroup>: tp" );
+ System.out.println( " -" + USE_SDIR
+ + " : to use SDIR instead of GSDIR (faster, but non-binary species trees are disallowed)" );
+ System.out.println();
+ System.out.println( " Formats" );
+ System.out.println( " The species tree is expected to be in phyloXML format." );
+ System.out
+ .println( " The gene trees ideally are in phyloXML as well, but can also be in New Hamphshire (Newick)" );
+ System.out.println( " or Nexus format as long as species information can be extracted from the gene names" );
+ System.out.println( " (e.g. \"HUMAN\" from \"BCL2_HUMAN\")." );
+ System.out.println();
+ System.out.println( " Examples" );
+ System.out.println( " \"rio gene_trees.nh species.xml outtable.tsv log.txt\"" );
+ System.out.println();
+ System.out.println( " More information: http://code.google.com/p/forester/wiki/RIO" );
+ System.out.println();
+ System.exit( -1 );
}
private static void tableOutput( final File table_outfile, final RIO rio ) throws IOException, RIOException {
writeTable( table_outfile, rio, m );
}
+ private static void writeLogFile( final File logfile,
+ final RIO rio,
+ final File species_tree_file,
+ final File gene_trees_file,
+ final File outtable,
+ final String prg_name,
+ final String prg_v,
+ final String prg_date,
+ final String f ) throws IOException {
+ final EasyWriter out = ForesterUtil.createEasyWriter( logfile );
+ out.println( prg_name );
+ out.println( "version : " + prg_v );
+ out.println( "date : " + prg_date );
+ out.println( "based on: " + f );
+ out.println( "----------------------------------" );
+ out.println( "Gene trees : " + gene_trees_file );
+ out.println( "Species tree : " + species_tree_file );
+ out.println( "All vs all orthology table : " + outtable );
+ out.flush();
+ out.println( rio.getLog().toString() );
+ out.close();
+ ForesterUtil.programMessage( PRG_NAME, "wrote log to \"" + logfile + "\"" );
+ }
+
private static void writeTable( final File table_outfile, final RIO rio, final IntMatrix m ) throws IOException {
final EasyWriter w = ForesterUtil.createEasyWriter( table_outfile );
final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.###" );
w.close();
ForesterUtil.programMessage( PRG_NAME, "wrote table to \"" + table_outfile + "\"" );
}
-
- private final static void printHelp() {
- System.out.println( "Usage" );
- System.out.println();
- System.out
- .println( PRG_NAME
- + " [options] <gene trees infile> <species tree infile> <all vs all orthology table outfile> [logfile]" );
- System.out.println();
- System.out.println( " Options" );
- System.out.println( " -" + USE_SDIR
- + " : to use SDIR instead of GSDIR (faster, but non-binary species trees are disallowed)" );
- System.out.println();
- System.out.println( " Formats" );
- System.out.println( " The species tree is expected to be in phyloXML format." );
- System.out
- .println( " The gene trees ideally are in phyloXML as well, but can also be in New Hamphshire (Newick)" );
- System.out.println( " or Nexus format as long as species information can be extracted from the gene names" );
- System.out.println( " (e.g. \"HUMAN\" from \"BCL2_HUMAN\")." );
- System.out.println();
- System.out.println( " Examples" );
- System.out.println( " \"rio gene_trees.nh species.xml outtable.tsv log.txt\"" );
- System.out.println();
- System.out.println( " More information: http://code.google.com/p/forester/wiki/RIO" );
- System.out.println();
- System.exit( -1 );
- }
}