com.opencsv.CSVParserBuilder Java Examples

public static void main(String[] args) throws FileNotFoundException, IOException {
    // TODO code application logic here 
    File phase3File = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\phase3_corrected.psam");
    File traitFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\TraitFile.txt");
    File probeAnnotationFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\ProbeAnnotationFile.txt");
    File couplingFile = new File("C:\\Users\\Sophie Mulc\\Documents\\DEPICT2\\CouplingFile.txt");
    //FileReader(String phase3_corrected)
    final CSVParser gmtParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
    final CSVReader gmtReader = new CSVReaderBuilder(new BufferedReader(new FileReader(phase3File))).withSkipLines(1).withCSVParser(gmtParser).build();


    List<String> iids = new ArrayList<>();

    String[] inputLine;
    while ((inputLine = gmtReader.readNext()) != null) {

        String iid = inputLine[0];

        iids.add(iid);
    }

    trait(iids, traitFile);
    probeAnnotation(probeAnnotationFile);
    coupling(iids, couplingFile);
}
 

public static List<String[]> oneByOne(Reader reader) {
    List<String[]> list = new ArrayList<>();
    try {
        CSVParser parser = new CSVParserBuilder()
                .withSeparator(',')
                .withIgnoreQuotations(true)
                .build();

        CSVReader csvReader = new CSVReaderBuilder(reader)
                .withSkipLines(0)
                .withCSVParser(parser)
                .build();

        String[] line;
        while ((line = csvReader.readNext()) != null) {
            list.add(line);
        }
        reader.close();
        csvReader.close();
    } catch (Exception ex) {
        Helpers.err(ex);
    }
    return list;
}
 

public static List<String[]> readAll(Reader reader) {

        CSVParser parser = new CSVParserBuilder()
                .withSeparator(',')
                .withIgnoreQuotations(true)
                .build();

        CSVReader csvReader = new CSVReaderBuilder(reader)
                .withSkipLines(0)
                .withCSVParser(parser)
                .build();

        List<String[]> list = new ArrayList<>();
        try {
            list = csvReader.readAll();
            reader.close();
            csvReader.close();
        } catch (Exception ex) {
            Helpers.err(ex);
        }
        return list;
    }
 

public ICSVParser createCSVParserBuilder() {
  final ICSVParser result;

  if (NULL_CHAR.equals(this.separatorChar) || this.useRFC4180Parser) {
    result = new RFC4180ParserBuilder()
        .withQuoteChar(this.quoteChar)
        .withSeparator(this.separatorChar)
        .withFieldAsNull(this.nullFieldIndicator)
        .build();
  } else {
    result = new CSVParserBuilder()
        .withEscapeChar(this.escapeChar)
        .withIgnoreLeadingWhiteSpace(this.ignoreLeadingWhitespace)
        .withIgnoreQuotations(this.ignoreQuotations)
        .withQuoteChar(this.quoteChar)
        .withSeparator(this.separatorChar)
        .withStrictQuotes(this.strictQuotes)
        .withFieldAsNull(this.nullFieldIndicator)
        .build();
  }

  return result;
}
 

/**
 * Initializes the CSVConverter based on the provided config. The config should contain
 * an entry for {@code columns}, and can optionally contain a {@code separator}.
 *
 * @param config The configuration used for setup
 */
public void initialize(Map<String, Object> config) {
  if(config.containsKey(COLUMNS_KEY)) {
    columnMap = getColumnMap(config);
  }
  else {
    throw new IllegalStateException("CSVExtractor requires " + COLUMNS_KEY + " configuration");
  }
  char separator = ',';
  if(config.containsKey(SEPARATOR_KEY)) {
    separator = config.get(SEPARATOR_KEY).toString().charAt(0);

  }
  parser = new CSVParserBuilder().withSeparator(separator)
            .build();
}
 

@Override
public void doInitialize(UimaContext context) throws ResourceInitializationException {
  if (folders == null || folders.length == 0) {
    folders = new String[1];
    folders[0] = System.getProperty("user.dir");
  }

  try {
    watcher = FileSystems.getDefault().newWatchService();
  } catch (IOException ioe) {
    throw new ResourceInitializationException(ioe);
  }

  csvParser = new CSVParserBuilder().withSeparator(separator.charAt(0)).build();
  registerFolders();
}
 

@Override
public void doProcessStream(InputStream stream, String source, JCas jCas) throws IOException {
  super.doProcessStream(stream, source, jCas);
  CSVParser parser = new CSVParserBuilder().withSeparator(separator.charAt(0)).build();
  try (CSVReader reader =
      new CSVReaderBuilder(new InputStreamReader(stream, StandardCharsets.UTF_8))
          .withCSVParser(parser)
          .build()) {
    String[] cols = reader.readNext();
    if (cols == null || cols.length < contentColumn) {
      throw new IOException("Not enough columns");
    }

    for (int i = 0; i < cols.length; i++) {
      if (i == (contentColumn - 1)) {
        jCas.setDocumentText(cols[i]);
      } else {
        addMetadata(jCas, i, cols[i]);
      }
    }
  }
}
 

private void init() throws IOException {
	String[] row;
	csv = new CSVReaderBuilder(reader).withCSVParser(
			new CSVParserBuilder()
					.withSeparator(delimiter)
					.withQuoteChar(quote)
					.withEscapeChar(escape)
					.build())
			.build();
	if (varsFromHeader) {
		while ((row = csv.readNext()) != null) {
			boolean foundValidColumnName = false;
			for (int i = 0; i < row.length; i++) {
				if (toVar(row[i]) == null)
					continue;
				foundValidColumnName = true;
			}
			// If row was empty or didn't contain anything usable
			// as column name, then try next row
			if (!foundValidColumnName)
				continue;
			for (int i = 0; i < row.length; i++) {
				Var var = toVar(row[i]);
				if (var == null || vars.contains(var)
						|| var.equals(TarqlQuery.ROWNUM)) {
					getVar(i);
				} else {
					vars.add(var);
				}
			}
			break;
		}
	}
	rownum = 1;
	next();
}
 

public static final List<String> readMatrixAnnotations(File file) throws IOException {

        final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
        final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(file))).withCSVParser(parser).build();

        ArrayList<String> identifiers = new ArrayList<>();

        String[] nextLine;
        while ((nextLine = reader.readNext()) != null) {
            identifiers.add(nextLine[0]);
        }

        return identifiers;
    }
 

private static HashMap<String, HashMap<String, HashSet<String>>> loadTfData(File tfFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(tfFile))).withSkipLines(1).withCSVParser(parser).build();

		HashMap<String, HashMap<String, HashSet<String>>> tfdatabasesPathwayToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if (nextLine[0].charAt(0) == '!') {
				continue;
			}

			String database = nextLine[0];
			String pathway = nextLine[1];
			String ensgId = nextLine[3];

			HashMap<String, HashSet<String>> pathwayToGenes = tfdatabasesPathwayToGenes.get(database);
			if (pathwayToGenes == null) {
				pathwayToGenes = new HashMap<>();
				tfdatabasesPathwayToGenes.put(database, pathwayToGenes);
			}

			HashSet<String> pathwayGenes = pathwayToGenes.get(pathway);
			if (pathwayGenes == null) {
				pathwayGenes = new HashSet<>();
				pathwayToGenes.put(pathway, pathwayGenes);
			}

			pathwayGenes.add(ensgId);

		}

		return tfdatabasesPathwayToGenes;

	}
 

private static HashMap<String, HashSet<String>> readHpoFile(File hpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String hpo = nextLine[0];
			String ncbiId = nextLine[2];
			String hgcnId = nextLine[3];
			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else {

				HashSet<String> hpoGenes = hpoToGenes.get(hpo);
				if (hpoGenes == null) {
					hpoGenes = new HashSet<>();
					hpoToGenes.put(hpo, hpoGenes);
				}

				for (String ensgId : ensgIds) {
					hpoGenes.add(ensgId);
				}

			}

		}

		return hpoToGenes;

	}
 

/**
 * Given a Reader and a separator character, return the contents of the table as a list of rows.
 *
 * @param reader a reader to read data from
 * @param separator separator character
 * @return a list of lists of strings
 * @throws IOException on file reading problems
 */
private static List<List<String>> readXSV(Reader reader, char separator) throws IOException {
  CSVReader csv =
      new CSVReaderBuilder(reader)
          .withCSVParser(new CSVParserBuilder().withSeparator(separator).build())
          .build();
  List<List<String>> rows = new ArrayList<>();
  for (String[] nextLine : csv) {
    rows.add(new ArrayList<>(Arrays.asList(nextLine)));
  }
  csv.close();
  return rows;
}
 

private static HashMap<String, HashSet<String>> readHpoFile(File hpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String hpo = nextLine[0];
			String ncbiId = nextLine[2];
			String hgcnId = nextLine[3];
			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else {

				HashSet<String> hpoGenes = hpoToGenes.get(hpo);
				if (hpoGenes == null) {
					hpoGenes = new HashSet<>();
					hpoToGenes.put(hpo, hpoGenes);
				}

				for (String ensgId : ensgIds) {
					hpoGenes.add(ensgId);
				}

			}

		}

		return hpoToGenes;

	}
 

private static HashMap<String, HashSet<String>> readClusterFile(File hpoFile) throws Exception {

		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(hpoFile))).withSkipLines(0).withCSVParser(hpoParser).build();

		HashMap<String, HashSet<String>> hpoToGenes = new HashMap<>();

		HashSet<String> allMyoclonusGenes = new HashSet<>();
		hpoToGenes.put("AllMyoclonus", allMyoclonusGenes);

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String gene = nextLine[0];
			String cluster = nextLine[1];

			HashSet<String> hpoGenes = hpoToGenes.get(cluster);
			if (hpoGenes == null) {
				hpoGenes = new HashSet<>();
				hpoToGenes.put(cluster, hpoGenes);
			}

			allMyoclonusGenes.add(gene);
			hpoGenes.add(gene);

		}

		return hpoToGenes;

	}
 

public CSVReader createCSVReader() throws IOException {
	Path path = Paths.get(this.datasetPath + this.datasetName + this.datasetEnding);
	
	CSVParser parser = new CSVParserBuilder()
			.withSeparator(this.valueSeparator)
			.withQuoteChar(this.valueQuote)
			.withEscapeChar(this.valueEscape)
			.withStrictQuotes(this.valueStrictQuotes)
			.withIgnoreLeadingWhiteSpace(this.valueIgnoreLeadingWhitespace)
			.withFieldAsNull(CSVReaderNullFieldIndicator.EMPTY_SEPARATORS)
			.build();
	
	BufferedReader buffer = Files.newBufferedReader(path, this.charset);
	CSVReader reader = new CSVReaderBuilder(buffer).withCSVParser(parser).build();
	
	if (this.fileHasHeader)
		reader.readNext();
	
	return reader;
}
 

@Override
  public boolean connect(File resource){
      String separator = properties.getProperty(Parameter.PROPERTY_CSV_SEPARATOR, ",");
      String quote = properties.getProperty(Parameter.PROPERTY_CSV_QUOTE, "\\\\");
      CSVParser parser = new CSVParserBuilder().withSeparator(separator.charAt(0)).withQuoteChar(quote.charAt(0)).build();
      try(CSVReader reader = new CSVReaderBuilder(new FileReader(resource)).withCSVParser(parser).build();)
      {
      	lines = reader.readAll();
      	String[] infoLine = lines.get(0);
	name = infoLine[0];
       id = FormatUtils.extractInteger(infoLine[1]);
       isDateTwoColumn = id == TimeFormatType.yyyy_MM_ddHmsz.id;
       dateTimeFormatter = FormatUtils.getDateTimeFormatter(id);
       String currencyString = null;
       if(infoLine.length>2) {
           currencyString = infoLine[2].replaceAll("\\s", "");
       }
       if(currencyString == null || currencyString.length() != 3)
           currencyString = Parameter.DEFAULT_CURRENCY;
       currency = Currency.getInstance(currencyString);
       lines.remove(0); // remove InfoLine
} catch (FileNotFoundException e) {
	log.error(e.getMessage());
	e.printStackTrace();
	return false;
} catch (IOException ioe) {
	log.error(ioe.getMessage());
	ioe.printStackTrace();
	return false;
}
      return true;
  }
 

@ProcessElement
public void processElement(ProcessContext c) throws IOException {
  String csvLine = c.element();
  CSVParser parser = new CSVParserBuilder().withQuoteChar(CSV_QUOTE_CHAR.charAt(0)).build();
  String[] parts = parser.parseLine(csvLine);
  c.output(parts);
}
 

private static HashSet<String> getMutatedGenes(File genoFile, int colWithGene, int skipHeaderLines) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(genoFile))).withSkipLines(skipHeaderLines).withCSVParser(parser).build();

		HashSet<String> genes = new HashSet<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			genes.add(nextLine[colWithGene]);

		}

		reader.close();

		return genes;

	}
 

/**
	 * @param args the command line arguments
	 */
	public static void main(String[] args) throws FileNotFoundException, IOException {

//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\samplesWithGeno.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\gavinRes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\Prioritisations\\rankingCandidateGenes");


//		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\Prioritisations\\samples.txt");
//		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\CandidateGenes\\");
//		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\Prioritisations");
//		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\PrioritizeRequests\\rankingCandidateGenes");

		final File sampleFile = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\hpo5gpm.txt");
		final File genoFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\Genes\\");
		final File prioFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\Prioritisations\\");
		final File resultFolder = new File("C:\\UMCG\\Genetica\\Projects\\GeneNetwork\\BenchmarkSamples\\New5gpm\\RankingCandidateGenes\\");

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader sampleFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(sampleFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine;
		while ((nextLine = sampleFileReader.readNext()) != null) {

			String sample = nextLine[0];

			String genoSampleName = sample + ".txt";

			File genoFile = new File(genoFolder, genoSampleName);
			File prioFile = new File(prioFolder, sample + ".txt");
			File rankingFile = new File(resultFolder, sample + ".txt");

			System.out.println("------------------------------------------------------------------");
			System.out.println("Sample: " + sample);
			System.out.println("Geno: " + genoFile.getAbsolutePath());
			System.out.println("Prio: " + prioFile.getAbsolutePath());
			System.out.println("Ranking: " + rankingFile.getAbsolutePath());

			HashSet<String> genesWithMutation = getMutatedGenes(genoFile, 0, 0);

			final CSVReader prioFileReader = new CSVReaderBuilder(new BufferedReader(new FileReader(prioFile))).withSkipLines(0).withCSVParser(parser).build();

			CSVWriter writer = new CSVWriter(new FileWriter(rankingFile), '\t', '\0', '\0', "\n");

			String[] outputLine = prioFileReader.readNext();
			writer.writeNext(outputLine);

			while ((outputLine = prioFileReader.readNext()) != null) {

				if (genesWithMutation.contains(outputLine[1])) {
					writer.writeNext(outputLine);
				}

			}

			writer.close();
			prioFileReader.close();

		}

	}
 

public DiseaseGeneHpoData(final File diseaseGeneHpoFile, HashMap<String, ArrayList<String>> ncbiToEnsgMap, HashMap<String, ArrayList<String>> hgncToEnsgMap, HashSet<String> exludedHpo, HashSet<String> includeGenes, String diseasePrefix) throws FileNotFoundException, IOException {

		geneToHpos = new HashMap<>();
		diseaseToGenes = new HashMap<>();
		diseaseGeneToHpos = new HashMap<>();

		Predicate<String> diseasePattern;
		if(diseasePrefix != null){
			diseasePattern = Pattern.compile("^" + diseasePrefix).asPredicate();
		} else {
			diseasePattern = null;
		}
		
		final CSVParser hpoParser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader hpoReader = new CSVReaderBuilder(new BufferedReader(new FileReader(diseaseGeneHpoFile))).withSkipLines(1).withCSVParser(hpoParser).build();

		String[] nextLine;
		while ((nextLine = hpoReader.readNext()) != null) {
			String disease = nextLine[0];
			String hgcnId = nextLine[1];
			String ncbiId = nextLine[2];
			String hpo = nextLine[3];
			
			if(diseasePattern != null && !diseasePattern.test(disease)){
				continue;
			}

			if (exludedHpo != null && exludedHpo.contains(hpo)) {
				continue;
			}

			ArrayList<String> ensgIds = ncbiToEnsgMap.get(ncbiId);
			if (ensgIds == null) {
				ensgIds = hgncToEnsgMap.get(hgcnId);
			}
			if (ensgIds == null) {
				System.err.println("Missing mapping for gene: " + ncbiId + " " + hgcnId);
			} else if (ensgIds.size() > 1) {
				System.err.println("Skipping becasue multiple ENSG IDs for gene: " + ncbiId + " " + hgcnId);
			} else if (!includeGenes.contains(ensgIds.get(0))) {
				System.err.println("Skipping becasue gene not in include list: " + ncbiId + " " + hgcnId);
			} else {

				String ensgId = ensgIds.get(0);

				HashSet<String> geneHpos = geneToHpos.get(ensgId);
				if (geneHpos == null) {
					geneHpos = new HashSet<>();
					geneToHpos.put(ensgId, geneHpos);
				}

				geneHpos.add(hpo);

				HashSet<String> diseaseGenes = diseaseToGenes.get(disease);
				if (diseaseGenes == null) {
					diseaseGenes = new HashSet<>();
					diseaseToGenes.put(disease, diseaseGenes);
				}
				diseaseGenes.add(ensgId);

				DiseaseGene diseaseGene = new DiseaseGene(disease, ensgId);

				HashSet<String> diseaseGeneHpos = diseaseGeneToHpos.get(diseaseGene);
				if (diseaseGeneHpos == null) {
					diseaseGeneHpos = new HashSet<>();
					diseaseGeneToHpos.put(diseaseGene, diseaseGeneHpos);
				}
				diseaseGeneHpos.add(hpo);

			}

		}

	}
 

public static TObjectDoubleMap<String> readSignificantPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		TObjectDoubleMap<String> hpos = new TObjectDoubleHashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if(Double.parseDouble(nextLine[4]) <= 0.05){
				hpos.put(nextLine[0], Double.parseDouble(nextLine[3]));
			}
			

		}

		reader.close();

		return hpos;

	}
 

public static TObjectDoubleMap<String> readPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		TObjectDoubleMap<String> hpos = new TObjectDoubleHashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			hpos.put(nextLine[0], Double.parseDouble(nextLine[3]));

		}

		reader.close();

		return hpos;

	}
 

private static Map<String, String> loadEnsgToHgnc(File mappingFile) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(mappingFile))).withSkipLines(1).withCSVParser(parser).build();

		HashMap<String, String> mapping = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			mapping.put(nextLine[0], nextLine[1]);

		}

		return Collections.unmodifiableMap(mapping);

	}
 

public static LinkedHashSet<String> readPredictedHpoTermFile(File predictedHpoTermFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		LinkedHashSet<String> hpos = new LinkedHashSet<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			hpos.add(nextLine[0]);

		}

		reader.close();

		return hpos;

	}
 

private static Map<String, String> loadUpdatedIds(File updatedIdFile) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(updatedIdFile))).withCSVParser(parser).build();

		HashMap<String, String> updates = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			updates.put(nextLine[0], nextLine[1]);

		}

		return Collections.unmodifiableMap(updates);

	}
 

private static HashMap<String, LinkedHashSet<String>> loadCaseHpo(File caseHpoFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(caseHpoFile))).withSkipLines(1).withCSVParser(parser).build();

		HashMap<String, LinkedHashSet<String>> caseHpo = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if (nextLine[5].isEmpty()) {

				LinkedHashSet<String> hpo = caseHpo.get(nextLine[0]);
				if (hpo == null) {
					hpo = new LinkedHashSet<>();
					caseHpo.put(nextLine[0], hpo);
				}
				hpo.add(nextLine[1]);

			}

		}

		return caseHpo;

	}
 

private static Map<String, String> loadEnsgToHgnc(File mappingFile) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(mappingFile))).withSkipLines(1).withCSVParser(parser).build();

		HashMap<String, String> mapping = new HashMap<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			mapping.put(nextLine[0], nextLine[1]);

		}

		return Collections.unmodifiableMap(mapping);

	}
 

public SkewnessInfo(File skewnessFile) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(skewnessFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine = reader.readNext();
		
		//check header
		if(!Arrays.equals(nextLine, EXPECTED_HEADER)){
			throw new RuntimeException("skewness header different than expected, is: " + String.join("\t", nextLine)); 
		}
		
		
		while ((nextLine = reader.readNext()) != null) {
			String gene = nextLine[0];
			
			hpoSkewnessMap.put(gene, Double.valueOf(nextLine[1]));
			maxSkewnessExHpoMap.put(gene, Double.valueOf(nextLine[2]));
			meanSkewnessExHpoMap.put(gene, Double.valueOf(nextLine[3]));
			
		}
		
		reader.close();

		
	}
 

private static LinkedHashSet<String> readPredictedHpoTermFileBonCutoff(File predictedHpoTermFile, double cutoff) throws FileNotFoundException, IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(predictedHpoTermFile))).withSkipLines(1).withCSVParser(parser).build();

		LinkedHashSet<String> hpos = new LinkedHashSet<>();

		String[] nextLine;
		while ((nextLine = reader.readNext()) != null) {

			if(Double.parseDouble(nextLine[4]) <= cutoff){
				hpos.add(nextLine[0]);
			}
			
		}

		reader.close();

		return hpos;

	}
 

private static ArrayList<String> readGenes(File geneOrderFile) throws IOException {

		final CSVParser parser = new CSVParserBuilder().withSeparator('\t').withIgnoreQuotations(true).build();
		final CSVReader reader = new CSVReaderBuilder(new BufferedReader(new FileReader(geneOrderFile))).withSkipLines(0).withCSVParser(parser).build();

		String[] nextLine;
		ArrayList<String> geneOrder = new ArrayList<>();

		while ((nextLine = reader.readNext()) != null) {

			geneOrder.add(nextLine[0]);

		}

		return geneOrder;

	}