public class IlluminaBasecallsToSam extends CommandLineProgram
COMPRESSION_LEVEL, CREATE_INDEX, CREATE_MD5_FILE, GA4GH_CLIENT_SECRETS, MAX_RECORDS_IN_RAM, QUIET, REFERENCE_SEQUENCE, TMP_DIR, VALIDATION_STRINGENCY, VERBOSITY
Constructor | Description |
---|---|
IlluminaBasecallsToSam() |
Modifier and Type | Method | Description |
---|---|---|
protected String[] |
customCommandLineValidation() |
Put any custom command-line validation in an override of this method.
|
protected int |
doWork() |
Do the work after command line has been parsed.
|
static void |
main(String[] args) |
getCommandLine, getCommandLineParser, getDefaultHeaders, getMetricsFile, getNestedOptions, getNestedOptionsForHelp, getStandardUsagePreamble, getVersion, instanceMain, instanceMainWithExit, parseArgs, setDefaultHeaders
public static final String USAGE
@Option(doc="The barcodes directory with _barcode.txt files (generated by ExtractIlluminaBarcodes). If not set, use BASECALLS_DIR. ", shortName="BCD", optional=true) public File BARCODES_DIR
@Option(doc="Deprecated (use LIBRARY_PARAMS). The output SAM or BAM file. Format is determined by extension.", shortName="O", mutex={"BARCODE_PARAMS","LIBRARY_PARAMS"}) public File OUTPUT
@Option(doc="The barcode of the run. Prefixed to read names.") public String RUN_BARCODE
@Option(doc="Deprecated (use LIBRARY_PARAMS). The name of the sequenced sample", shortName="ALIAS", mutex={"BARCODE_PARAMS","LIBRARY_PARAMS"}) public String SAMPLE_ALIAS
@Option(doc="ID used to link RG header record with RG tag in SAM record. If these are unique in SAM files that get merged, merge performance is better. If not specified, READ_GROUP_ID will be set to <first 5 chars of RUN_BARCODE>.<LANE> .", shortName="RG", optional=true) public String READ_GROUP_ID
@Option(doc="Deprecated (use LIBRARY_PARAMS). The name of the sequenced library", shortName="LIB", optional=true, mutex={"BARCODE_PARAMS","LIBRARY_PARAMS"}) public String LIBRARY_NAME
@Option(doc="The name of the sequencing center that produced the reads. Used to set the RG.CN tag.", optional=true) public String SEQUENCING_CENTER
@Option(doc="The name of the sequencing technology that produced the read.", optional=true) public String PLATFORM
@Option(doc="A description of the logical structure of clusters in an Illumina Run, i.e. a description of the structure IlluminaBasecallsToSam assumes the data to be in. It should consist of integer/character pairs describing the number of cycles and the type of those cycles (B for Sample Barcode, M for molecular barcode, T for Template, and S for skip). E.g. If the input data consists of 80 base clusters and we provide a read structure of \"28T8M8B8S28T\" then the sequence may be split up into four reads:\n* read one with 28 cycles (bases) of template\n* read two with 8 cycles (bases) of molecular barcode (ex. unique molecular barcode)\n* read three with 8 cycles (bases) of sample barcode\n* 8 cycles (bases) skipped.\n* read four with 28 cycles (bases) of template\nThe skipped cycles would NOT be included in an output SAM/BAM file or in read groups therein.", shortName="RS") public String READ_STRUCTURE
@Option(doc="Deprecated (use LIBRARY_PARAMS). Tab-separated file for creating all output BAMs for barcoded run with single IlluminaBasecallsToSam invocation. Columns are BARCODE, OUTPUT, SAMPLE_ALIAS, and LIBRARY_NAME. Row with BARCODE=N is used to specify a file for no barcode match", mutex={"OUTPUT","SAMPLE_ALIAS","LIBRARY_NAME","LIBRARY_PARAMS"}) public File BARCODE_PARAMS
@Option(doc="Tab-separated file for creating all output BAMs for a lane with single IlluminaBasecallsToSam invocation. The columns are OUTPUT, SAMPLE_ALIAS, and LIBRARY_NAME, BARCODE_1, BARCODE_2 ... BARCODE_X where X = number of barcodes per cluster (optional). Row with BARCODE_1 set to \'N\' is used to specify a file for no barcode match. You may also provide any 2 letter RG header attributes (excluding PU, CN, PL, and DT) as columns in this file and the values for those columns will be inserted into the RG tag for the BAM file created for a given row.", mutex={"OUTPUT","SAMPLE_ALIAS","LIBRARY_NAME","BARCODE_PARAMS"}) public File LIBRARY_PARAMS
@Option(doc="Which adapters to look for in the read.") public List<IlluminaUtil.IlluminaAdapterPair> ADAPTERS_TO_CHECK
@Option(doc="The number of threads to run in parallel. If NUM_PROCESSORS = 0, number of cores is automatically set to the number of cores available on the machine. If NUM_PROCESSORS < 0, then the number of cores used will be the number available on the machine less NUM_PROCESSORS.") public Integer NUM_PROCESSORS
@Option(doc="If set, this is the first tile to be processed (used for debugging). Note that tiles are not processed in numerical order.", optional=true) public Integer FIRST_TILE
@Option(doc="If set, process no more than this many tiles (used for debugging).", optional=true) public Integer TILE_LIMIT
@Option(doc="If true, call System.gc() periodically. This is useful in cases in which the -Xmx value passed is larger than the available memory.") public Boolean FORCE_GC
@Option(doc="Apply EAMSS filtering to identify inappropriately quality scored bases towards the ends of reads and convert their quality scores to Q2.") public boolean APPLY_EAMSS_FILTER
@Option(doc="Configure SortingCollections to store this many records before spilling to disk. For an indexed run, each SortingCollection gets this value/number of indices.") public int MAX_READS_IN_RAM_PER_TILE
@Option(doc="The minimum quality (after transforming 0s to 1s) expected from reads. If qualities are lower than this value, an error is thrown.The default of 2 is what the Illumina\'s spec describes as the minimum, but in practice the value has been observed lower.") public int MINIMUM_QUALITY
@Option(doc="Whether to include non-PF reads", shortName="NONPF", optional=true) public boolean INCLUDE_NON_PF_READS
@Option(doc="Whether to ignore reads whose barcodes are not found in LIBRARY_PARAMS. Useful when outputting BAMs for only a subset of the barcodes in a lane.", shortName="IGNORE_UNEXPECTED") public boolean IGNORE_UNEXPECTED_BARCODES
@Option(doc="The tag to use to store any molecular indexes. If more than one molecular index is found, they will be concatenated and stored here.", optional=true) public String MOLECULAR_INDEX_TAG
@Option(doc="The tag to use to store any molecular index base qualities. If more than one molecular index is found, their qualities will be concatenated and stored here (.i.e. the number of \"M\" operators in the READ_STRUCTURE)", optional=true) public String MOLECULAR_INDEX_BASE_QUALITY_TAG
protected int doWork()
CommandLineProgram
doWork
in class CommandLineProgram
public static void main(String[] args)
protected String[] customCommandLineValidation()
customCommandLineValidation
in class CommandLineProgram