public Bed2Bar(String[] args) {
try {
processArgs(args);
// load Window[]
for (int i = 0; i < bedFiles.length; i++) {
bedFile = bedFiles[i];
System.out.println("Parsing " + bedFile.getName());
bedLinesHash = Bed.parseBedFile(bedFile, true, false);
if (bedLinesHash == null || bedLinesHash.size() == 0) {
System.out.println("Problem parsing bed file, skipping!");
continue;
}
barDirectory = IO.makeDirectory(bedFile, "");
File bedOutFile =
new File(Misc.removeExtension(bedFile.toString()) + "_" + threshold + "_Filt.bed");
bedOut = new PrintWriter(new FileWriter(bedOutFile));
makeStairStepBarFiles();
}
bedOut.close();
System.out.println("\nDone!\n");
} catch (IOException e) {
e.printStackTrace();
}
}
/** This method will process each argument and assign new varibles */
public void processArgs(String[] args) {
File file = null;
Pattern pat = Pattern.compile("-[a-z]");
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'f':
file = new File(args[i + 1]);
i++;
break;
case 'v':
genomeVersion = args[i + 1];
i++;
break;
case 's':
sumScores = true;
break;
case 't':
threshold = Float.parseFloat(args[++i]);
break;
case 'h':
printDocs();
System.exit(0);
default:
Misc.printExit("\nError, unknown option! " + mat.group());
}
} catch (Exception e) {
System.out.print("\nSorry, something doesn't look right with this parameter: -" + test);
System.out.println();
System.exit(0);
}
}
}
if (file == null || file.exists() == false)
Misc.printErrAndExit("Problem finding your bed files!\n");
// pull files
File[][] tot = new File[3][];
tot[0] = IO.extractFiles(file, ".bed");
tot[1] = IO.extractFiles(file, ".bed.zip");
tot[2] = IO.extractFiles(file, ".bed.gz");
bedFiles = IO.collapseFileArray(tot);
if (bedFiles == null || bedFiles.length == 0)
Misc.printErrAndExit("Problem finding your xxx.bed(.zip/.gz OK) files!\n");
// genome version
if (genomeVersion == null)
Misc.printErrAndExit(
"Please enter a genome version (e.g. H_sapiens_Mar_2006, see http://genome.ucsc.edu/FAQ/FAQreleases\n");
}
/** This method will process each argument and assign new varibles */
public void processArgs(String[] args) {
Pattern pat = Pattern.compile("-[a-z]");
File dir = null;
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'f':
dir = new File(args[i + 1]);
i++;
break;
case 'v':
genomeVersion = args[i + 1];
i++;
break;
case 's':
strand = args[++i];
break;
case 't':
stairStep = true;
break;
case 'h':
printDocs();
System.exit(0);
default:
Misc.printExit("\nError: unknown option! " + mat.group());
}
} catch (Exception e) {
Misc.printExit(
"\nSorry, something doesn't look right with this parameter: -" + test + "\n");
}
}
}
if (dir == null || dir.canRead() == false)
Misc.printExit("\nError: cannot find or read your sgr file/ directory.\n");
File[][] tot = new File[3][];
tot[0] = IO.extractFiles(dir, ".sgr");
tot[1] = IO.extractFiles(dir, ".sgr.zip");
tot[2] = IO.extractFiles(dir, ".sgr.gz");
sgrFiles = IO.collapseFileArray(tot);
if (sgrFiles == null || sgrFiles.length == 0)
Misc.printExit("\nError: cannot find your xxx.sgr.zip file(s)");
if (genomeVersion == null)
Misc.printExit(
"\nError: you must supply a genome version. Goto http://genome.ucsc.edu/cgi-"
+ "bin/hgGateway load your organism to find the associated genome version.\n");
}
/** This method will process each argument and assign new variables */
public void processArgs(String[] args) {
Pattern pat = Pattern.compile("-[a-z]");
File forExtraction = null;
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'v':
forExtraction = new File(args[++i]);
break;
case 'm':
minimumSSC = Float.parseFloat(args[++i]);
break;
case 'a':
minimumCount = Integer.parseInt(args[++i]);
break;
case 'r':
minimumAbsFractionChange = Double.parseDouble(args[++i]);
break;
case 'n':
maximumNormalAltFraction = Double.parseDouble(args[++i]);
break;
default:
Misc.printErrAndExit("\nProblem, unknown option! " + mat.group());
}
} catch (Exception e) {
Misc.printErrAndExit(
"\nSorry, something doesn't look right with this parameter: -" + test + "\n");
}
}
}
System.out.println(
"\n" + IO.fetchUSeqVersion() + " Arguments: " + Misc.stringArrayToString(args, " ") + "\n");
// pull vcf files
if (forExtraction == null || forExtraction.exists() == false)
Misc.printErrAndExit(
"\nError: please enter a path to a vcf file or directory containing such.\n");
File[][] tot = new File[3][];
tot[0] = IO.extractFiles(forExtraction, ".vcf");
tot[1] = IO.extractFiles(forExtraction, ".vcf.gz");
tot[2] = IO.extractFiles(forExtraction, ".vcf.zip");
vcfFiles = IO.collapseFileArray(tot);
if (vcfFiles == null || vcfFiles.length == 0 || vcfFiles[0].canRead() == false)
Misc.printExit("\nError: cannot find your xxx.vcf(.zip/.gz OK) file(s)!\n");
}
// constructor
public TQuery(String[] args) {
try {
long startTime = System.currentTimeMillis();
processArgs(args);
queryIndex = new QueryIndex(this);
queryLoader = new QueryLoader(this);
// print some stats on building the engine
String diffTime =
Num.formatNumberOneFraction(((double) (System.currentTimeMillis() - startTime)) / 1000);
int numFiles = vcfDataFiles.length + bedDataFiles.length + mafDataFiles.length;
System.err.println("\n" + diffTime + " Sec to build using " + IO.memory() + " of RAM");
System.err.println("\t" + numFiles + "\tData sources loaded");
System.err.println("\t" + dataSources.getRecordsLoaded() + "\tRecords indexed");
System.err.println("\t" + dataSources.getRecordsSkipped() + "\tRecords skipped\n");
// print summary of available filters
System.err.println(dataSources.fetchSummary());
queryFilesFromCmdLine();
// release file handles
queryLoader.closeTabixReaders();
} catch (Exception e) {
e.printStackTrace();
System.err.println("\nProblem with executing the TQuery!");
}
}
private void buildXmlPropertiesFile() {
System.out.println(
"\nBuilding and checking your pipeline properties file -> " + truncPipePropFile);
StringBuilder toPrint = new StringBuilder();
// walk through the prop file
String[] prop = IO.loadFileIntoStringArray(truncPipePropFile);
Pattern val = Pattern.compile("(<entry key.+>)([D|A|B].*)</entry>");
boolean missingFile = false;
for (String s : prop) {
// does it match a file needing prepending? Data/, Apps/, Bed/
Matcher mat = val.matcher(s);
if (mat.matches()) {
File test = new File(referenceDir, mat.group(2));
if (test.exists()) {
System.out.println("Found\t" + test);
toPrint.append(mat.group(1));
toPrint.append(test.toString());
toPrint.append("</entry>");
} else {
System.out.println("Misssing\t" + test);
missingFile = true;
}
}
// threads?
else if (s.contains("threads"))
toPrint.append("<entry key=\"threads\">" + threads + "</entry>");
// nope just save it and add a line return
else toPrint.append(s);
toPrint.append("\n");
}
// anything missing? if so exit
if (missingFile)
Misc.printErrAndExit(
"\nFailed to find all of the files in your properties file, see above.\n");
// OK, write it out
completePipelinePropFile = new File(outputDirectory, "pipelineProperties.xml");
if (IO.writeString(toPrint.toString(), completePipelinePropFile) == false)
Misc.printErrAndExit("Problem writing -> " + truncPipePropFile);
}
private void checkForGzippedVcf() {
String vcfName = finalVcf.getName();
if (vcfName.endsWith(".gz")) {
File uncomp = new File(finalVcf.getParentFile(), vcfName.substring(0, vcfName.length() - 3));
if (uncomp.exists() == false) {
deleteTempVcf = true;
if (IO.uncompress(finalVcf, uncomp) == null)
Misc.printErrAndExit("ERROR: failed to uncompress -> " + finalVcf);
}
finalVcf = uncomp;
}
}
public boolean bedType(File bedFile) {
stranded = false;
scored = false;
named = false;
bed12 = false;
boolean bedLineFound = false;
try {
// read through first 10000 lines
// chrom start stop name score strand ....
// 0 1 2 3 4 5
BufferedReader in = IO.fetchBufferedReader(bedFile);
String[] tokens;
String line;
int counter = 0;
while ((line = in.readLine()) != null) {
if (counter++ > 10000) break;
// bed line?
if (bedLine.matcher(line).matches() == false) continue;
bedLineFound = true;
// split on tab
tokens = tab.split(line);
// bed12?
if (tokens.length == 12) {
bed12 = true;
break;
}
if (tokens.length > 3) {
// named?
if (badName.matcher(tokens[3]).matches() == false) named = true;
if (tokens.length > 4) {
// scored?
if (tokens[4].equals("0") == false) scored = true;
if (tokens.length > 5) {
// stranded?
if (tokens[5].equals(".") == false) stranded = true;
}
}
}
}
in.close();
} catch (Exception e) {
System.err.println("\nProblem parsing bed type.\n");
e.printStackTrace();
bedLineFound = false;
}
return bedLineFound;
}
private void executePipelineJob() {
String[] cmd = null;
try {
// write out tempTemplate
File template = new File(outputDirectory, "pipelineTemplate.xml");
if (IO.writeString(xmlTemplate, template) == false)
Misc.printErrAndExit("Problem writing -> " + template);
// build and execute cmd
cmd =
new String[] {
"java",
"-jar",
"-Xmx2G",
pJar.getCanonicalPath(),
"-props",
completePipelinePropFile.getCanonicalPath(),
template.getCanonicalPath()
};
String stringCmd = Misc.stringArrayToString(cmd, " ");
System.out.println("\nExecuting:\n" + stringCmd);
System.out.println("\nPipelineOutput:");
String[] out = IO.executeViaProcessBuilder(cmd, true);
// check output for possible errors
for (String line : out) {
String lcLine = line.toLowerCase();
// watch out for cases where error is mentioned in a warning output line.
if (lcLine.contains("error") && lcLine.startsWith("warning") == false)
Misc.printErrAndExit(
"\n\nERROR found in Pipeline.jar output, see above. Aborting!\n" + line);
}
} catch (Exception e) {
e.printStackTrace();
Misc.printErrAndExit("ERROR: executing " + Misc.stringArrayToString(cmd, " "));
}
}
/** This method will process each argument and assign new varibles */
public void processArgs(String[] args) {
Pattern pat = Pattern.compile("-[a-z]");
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'f':
fastas = IO.extractFiles(args[i + 1], "fasta");
i++;
break;
case 'n':
numberOfBases = Integer.parseInt(args[i + 1]);
i++;
break;
case 'i':
indexDirectory = new File(args[i + 1]);
i++;
break;
case 'h':
printDocs();
System.exit(0);
default:
Misc.printExit("\nError: unknown option! " + mat.group());
}
} catch (Exception e) {
Misc.printExit(
"\nSorry, something doesn't look right with this parameter: -" + test + "\n");
}
}
}
// make index directory?
if (indexDirectory == null) {
indexDirectory = new File(fastas[0].getParentFile(), "IndexedSequences");
indexDirectory.mkdir();
}
}
/** This method will process each argument and assign new variables */
public void processArgs(String[] args) {
Pattern pat = Pattern.compile("-[a-z]");
System.out.println(
"\n" + IO.fetchUSeqVersion() + " Arguments: " + Misc.stringArrayToString(args, " ") + "\n");
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'o':
jobId = args[++i];
break;
case 's':
sampleId = args[++i];
break;
case 'm':
submitter = args[++i];
break;
case 'y':
analysisType = args[++i];
break;
case 'w':
webRootForLinks = new File(args[++i]);
break;
case 'e':
snpEffGenome = args[++i];
break;
case 'i':
minimumReadDepth = args[++i];
break;
case 't':
threads = args[++i];
break;
case 'l':
uploadVarsToNGSWeb = true;
break;
case 'j':
pJar = new File(args[++i]);
break;
case 'p':
truncPipePropFile = new File(args[++i]);
break;
case 'q':
bedForCoverageQC = new File(args[++i]);
break;
case 'b':
bedForVarCalling = new File(args[++i]);
break;
case 'r':
fastaReference = new File(args[++i]);
break;
case 'u':
unfilteredBam = new File(args[++i]);
break;
case 'f':
finalBam = new File(args[++i]);
break;
case 'v':
finalVcf = new File(args[++i]);
break;
case 'd':
outputDirectory = new File(args[++i]);
break;
case 'c':
referenceDir = new File(args[++i]);
break;
case 'h':
printDocs();
System.exit(0);
default:
Misc.printErrAndExit("\nProblem, unknown option! " + mat.group());
}
} catch (Exception e) {
Misc.printErrAndExit(
"\nSorry, something doesn't look right with this parameter: -" + test + "\n");
}
}
}
// check output dir and if needed set sampleId
if (outputDirectory != null) {
outputDirectory.mkdirs();
if (sampleId.length() == 0) sampleId = outputDirectory.getName();
}
// check root directory if needed
if (webRootForLinks != null) {
if (webRootForLinks.exists() == false) webRootForLinks.mkdirs();
// links dir?
File links = new File(webRootForLinks, "links");
if (links.exists() == false) links.mkdirs();
}
// look for required fields and files
checkPrintFields();
checkPrintFiles();
checkForGzippedVcf();
}
/** This method will process each argument and assign new variables */
public void processArgs(String[] args) {
Pattern pat = Pattern.compile("-[a-z]");
File forExtraction = null;
File ucscDir = null;
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'b':
forExtraction = new File(args[++i]);
break;
case 'd':
ucscDir = new File(args[++i]);
break;
case 'v':
versionedGenome = args[++i];
break;
case 'e':
verbose = false;
break;
case 'f':
forceConversion = true;
break;
case 'h':
printDocs();
System.exit(0);
break;
default:
USeqUtilities.printExit("\nProblem, unknown option! " + mat.group());
}
} catch (Exception e) {
USeqUtilities.printExit(
"\nSorry, something doesn't look right with this parameter: -" + test + "\n");
}
}
}
if (verbose)
System.out.println(
"\n"
+ IO.fetchUSeqVersion()
+ " Arguments: "
+ USeqUtilities.stringArrayToString(args, " ")
+ "\n");
// versioned genome?
if (versionedGenome == null)
USeqUtilities.printExit(
"\nError: you must supply a genome version. Goto http://genome.ucsc.edu/cgi-"
+ "bin/hgGateway load your organism to find the associated genome version (e.g. H_sapiens_Mar_2006, H_sapiens_Feb_2009).\n");
// make files
if (ucscDir == null || ucscDir.isDirectory() == false)
USeqUtilities.printExit(
"\nCannot find your directory containing the UCSC wig2BigWig and bed2BigBed apps -> "
+ ucscDir);
bigWigToWig = new File(ucscDir, "bigWigToWig");
bigBedToBed = new File(ucscDir, "bigBedToBed");
// check files
// if (bigWigToBedGraph.canExecute() == false) USeqUtilities.printExit("\nCannot find or execute
// -> "+bigWigToBedGraph+"\n");
if (bigWigToWig.canExecute() == false)
USeqUtilities.printExit("\nCannot find or execute -> " + bigWigToWig + "\n");
if (bigBedToBed.canExecute() == false)
USeqUtilities.printExit("\nCannot find or execute -> " + bigBedToBed + "\n");
// pull ucsc files
if (forExtraction == null || forExtraction.exists() == false)
Misc.printExit(
"\nError: please enter a bw or bb file or directory containing such to convert!\n");
File[][] tot = new File[2][];
tot[0] = USeqUtilities.fetchFilesRecursively(forExtraction, ".bw");
tot[1] = USeqUtilities.fetchFilesRecursively(forExtraction, ".bb");
ucscArchives = IO.collapseFileArray(tot);
if (ucscArchives == null || ucscArchives.length == 0 || ucscArchives[0].canRead() == false)
Misc.printExit("\nError: cannot find or read any xxx.bb or xxx.bw file(s)!\n");
}
/** This method will process each argument and assign new varibles */
public void processArgs(String[] args) {
Pattern pat = Pattern.compile("-[a-z]");
String useqVersion = IO.fetchUSeqVersion();
System.err.println(
"\n" + useqVersion + " Arguments: " + Misc.stringArrayToString(args, " ") + "\n");
File tabixDataDir = null;
for (int i = 0; i < args.length; i++) {
String lcArg = args[i].toLowerCase();
Matcher mat = pat.matcher(lcArg);
if (mat.matches()) {
char test = args[i].charAt(1);
try {
switch (test) {
case 'c':
chrLengthFile = new File(args[++i]);
break;
case 'd':
tabixDataDir = new File(args[++i]);
break;
case 'n':
numberThreads = Integer.parseInt(args[++i]);
break;
case 'q':
numberQueriesInChunk = Integer.parseInt(args[++i]);
break;
default:
Misc.printErrAndExit("\nProblem, unknown option! " + mat.group());
}
} catch (Exception e) {
Misc.printErrAndExit(
"\nSorry, something doesn't look right with this parameter: -" + test + "\n");
}
}
}
if (chrLengthFile == null)
Misc.printErrAndExit(
"\nError: please provide a bed file of chromosome and their lengths, e.g. X 0 155270560\n");
if (tabixDataDir == null || tabixDataDir.isDirectory() == false)
Misc.printErrAndExit(
"\nError: please provide a directory containing tabix indexed xxx.vcf.gz and xxx.bed.gz files with their associated xxx.gz.tbi indexes");
// pull data sources
vcfDataFiles = IO.fetchFilesRecursively(tabixDataDir, "vcf.gz");
bedDataFiles = IO.fetchFilesRecursively(tabixDataDir, "bed.gz");
mafDataFiles = IO.fetchFilesRecursively(tabixDataDir, "maf.txt.gz");
if (vcfDataFiles.length == 0 && bedDataFiles.length == 0 && mafDataFiles.length == 0)
Misc.printErrAndExit(
"\nError: failed to find any xxx.bed.gz, xxx.vcf.gz, or xxx.maf.txt.gz tabix files in your tabixDataDir -> "
+ tabixDataDir);
// check for index
lookForTabixIndex(vcfDataFiles);
lookForTabixIndex(bedDataFiles);
lookForTabixIndex(mafDataFiles);
// threads to use
int numAvail = Runtime.getRuntime().availableProcessors();
if (numberThreads < 1) numberThreads = numAvail - 1;
System.err.println(
numAvail + " Available processors, using " + numberThreads + " threaded loaders\n");
}