public class IlluminaBasecallsToFastq extends CommandLineProgram
Modifier and Type | Class and Description |
---|---|
static class |
IlluminaBasecallsToFastq.ReadNameFormat
Simple switch to control the read name format to emit.
|
Modifier and Type | Field and Description |
---|---|
List<IlluminaUtil.IlluminaAdapterPair> |
ADAPTERS_TO_CHECK |
boolean |
APPLY_EAMSS_FILTER |
File |
BARCODES_DIR |
File |
BASECALLS_DIR |
boolean |
COMPRESS_OUTPUTS |
Integer |
FIRST_TILE |
String |
FLOWCELL_BARCODE |
Boolean |
FORCE_GC |
boolean |
INCLUDE_NON_PF_READS |
Integer |
LANE |
String |
MACHINE_NAME |
int |
MAX_READS_IN_RAM_PER_TILE |
int |
MINIMUM_QUALITY |
File |
MULTIPLEX_PARAMS |
Integer |
NUM_PROCESSORS |
File |
OUTPUT_PREFIX |
IlluminaBasecallsToFastq.ReadNameFormat |
READ_NAME_FORMAT |
String |
READ_STRUCTURE |
String |
RUN_BARCODE |
Integer |
TILE_LIMIT |
COMPRESSION_LEVEL, CREATE_INDEX, CREATE_MD5_FILE, GA4GH_CLIENT_SECRETS, MAX_RECORDS_IN_RAM, QUIET, REFERENCE_SEQUENCE, TMP_DIR, VALIDATION_STRINGENCY, VERBOSITY
Constructor and Description |
---|
IlluminaBasecallsToFastq() |
Modifier and Type | Method and 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
@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="The prefix for output fastqs. Extensions as described above are appended. Use this option for a non-barcoded run, or for a barcoded run in which it is not desired to demultiplex reads into separate files by barcode.", shortName="O", mutex="MULTIPLEX_PARAMS") public File OUTPUT_PREFIX
@Option(doc="The barcode of the run. Prefixed to read names.", optional=false) public String RUN_BARCODE
@Option(doc="The name of the machine on which the run was sequenced; required if emitting Casava1.8-style read name headers", optional=true) public String MACHINE_NAME
@Option(doc="The barcode of the flowcell that was sequenced; required if emitting Casava1.8-style read name headers", optional=true) public String FLOWCELL_BARCODE
@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 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 \"36T8B8S28T\" then, before being converted to SAM records those bases will be split into 4 reads where read one consists of 36 cycles of template, read two consists of 8 cycles of barcode, read three will be an 8 base read of skipped cycles and read four is another 28 cycle template read. The read consisting of skipped cycles would NOT be included in output SAM/BAM file read groups.", shortName="RS") public String READ_STRUCTURE
@Option(doc="Tab-separated file for creating all output fastqs demultiplexed by barcode for a lane with single IlluminaBasecallsToFastq invocation. The columns are OUTPUT_PREFIX, and 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 an output_prefix for no barcode match.", mutex="OUTPUT_PREFIX") public File MULTIPLEX_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="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="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="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="The read name header formatting to emit. Casava1.8 formatting has additional information beyond Illumina, including: the passing-filter flag value for the read, the flowcell name, and the sequencer name.", optional=false) public IlluminaBasecallsToFastq.ReadNameFormat READ_NAME_FORMAT
protected int doWork()
CommandLineProgram
doWork
in class CommandLineProgram
protected String[] customCommandLineValidation()
CommandLineProgram
customCommandLineValidation
in class CommandLineProgram
public static void main(String[] args)