def strandSpecificity(infile, outfile):
'''This function will determine the strand specificity of your library
from the bam file'''
iterations = "1000000"
PipelineBamStats.getStrandSpecificity(infile, outfile, iterations)
def strandSpecificity(infile, outfile):
'''This function will determine the strand specificity of your library
from the bam file'''
iterations = "1000000"
PipelineBamStats.getStrandSpecificity(infile,
outfile,
iterations)
def processGenomicContext(infile, outfile):
'''
This module process genomic context file.
It assigns each and every features of context
file to a specific catagory. It helps us to
understand heiarchical classification
of features.
'''
PipelineBamStats.defineBedFeatures(infile, outfile)
def processGenomicContext(infile, outfile):
'''
This module process genomic context file.
It assigns each and every features of context
file to a specific catagory. It helps us to
understand heiarchical classification
of features.
'''
PipelineBamStats.defineBedFeatures(infile, outfile)
def intBam(infile, outfile):
'''make an intermediate bam file if there is no sequence infomation.
If there is no sequence quality then make a softlink. Picard tools
has an issue when quality score infomation is missing'''
if PARAMS["bam_sequence_stripped"] is True:
PipelineBamStats.addPseudoSequenceQuality(infile, outfile)
else:
PipelineBamStats.copyBamFile(infile, outfile)
def buildPicardStats(infiles, outfile):
''' build Picard alignment stats '''
infile, reffile = infiles
# patch for mapping against transcriptome - switch genomic reference
# to transcriptomic sequences
if "transcriptome.dir" in infile:
reffile = "refcoding.fa"
PipelineBamStats.buildPicardAlignmentStats(infile, outfile, reffile)
def buildPicardRnaSeqMetrics(infiles, outfile):
'''Get duplicate stats from picard RNASeqMetrics '''
# convert strandness to tophat-style library type
if PARAMS["strandness"] == ("RF" or "R"):
strand = "SECOND_READ_TRANSCRIPTION_STRAND"
elif PARAMS["strandness"] == ("FR" or "F"):
strand = "FIRST_READ_TRANSCRIPTION_STRAND"
else:
strand = "NONE"
PipelineBamStats.buildPicardRnaSeqMetrics(infiles, strand, outfile)
def buildPicardRnaSeqMetrics(infiles, outfile):
'''Get duplicate stats from picard RNASeqMetrics '''
# convert strandness to tophat-style library type
if PARAMS["strandness"] == ("RF" or "R"):
strand = "SECOND_READ_TRANSCRIPTION_STRAND"
elif PARAMS["strandness"] == ("FR" or "F"):
strand = "FIRST_READ_TRANSCRIPTION_STRAND"
else:
strand = "NONE"
PipelineBamStats.buildPicardRnaSeqMetrics(infiles, strand, outfile)
def intBam(infile, outfile):
'''make an intermediate bam file if there is no sequence infomation.
If there is no sequence quality then make a softlink. Picard tools
has an issue when quality score infomation is missing'''
if PARAMS["bam_sequence_stripped"] is True:
PipelineBamStats.addPseudoSequenceQuality(infile,
outfile)
else:
PipelineBamStats.copyBamFile(infile,
outfile)
def buildPicardStats(infiles, outfile):
''' build Picard alignment stats '''
infile, reffile = infiles
# patch for mapping against transcriptome - switch genomic reference
# to transcriptomic sequences
if "transcriptome.dir" in infile:
reffile = "refcoding.fa"
PipelineBamStats.buildPicardAlignmentStats(infile,
outfile,
reffile)
def loadIdxStats(infiles, outfile):
'''merge idxstats files into single dataframe and load
to database
Loads tables into the database
* mapped_reads_per_chromosome
Arguments
---------
infiles : list
list where each element is a string of the filename containing samtools
idxstats output. Filename format is expected to be 'sample.idxstats'
outfile : string
Logfile. The table name will be derived from `outfile`.'''
PipelineBamStats.loadIdxstats(infiles, outfile)
def loadIdxStats(infiles, outfile):
'''merge idxstats files into single dataframe and load
to database
Loads tables into the database
* mapped_reads_per_chromosome
Arguments
---------
infiles : list
list where each element is a string of the filename containing samtools
idxstats output. Filename format is expected to be 'sample.idxstats'
outfile : string
Logfile. The table name will be derived from `outfile`.'''
PipelineBamStats.loadIdxstats(infiles, outfile)
def buildBAMStats(infiles, outfile):
'''count number of reads mapped, duplicates, etc.
Excludes regions overlapping repetitive RNA sequences
Parameters
----------
infiles : list
infiles[0] : str
Input filename in :term:`bam` format
infiles[1] : str
Input filename with number of reads per sample
outfile : str
Output filename with read stats
annotations_interface_rna_gtf : str
:term:`PARMS`. :term:`gtf` format file with repetitive rna
'''
rna_file = PARAMS["annotations_interface_rna_gff"]
job_memory = "32G"
bamfile, readsfile = infiles
nreads = PipelineBamStats.getNumReadsFromReadsFile(readsfile)
track = P.snip(os.path.basename(readsfile),
".nreads")
# if a fastq file exists, submit for counting
if os.path.exists(track + ".fastq.gz"):
fastqfile = track + ".fastq.gz"
elif os.path.exists(track + ".fastq.1.gz"):
fastqfile = track + ".fastq.1.gz"
else:
fastqfile = None
if fastqfile is not None:
fastq_option = "--fastq-file=%s" % fastqfile
else:
fastq_option = ""
statement = '''
cgat bam2stats
%(fastq_option)s
--force-output
--mask-bed-file=%(rna_file)s
--ignore-masked-reads
--num-reads=%(nreads)i
--output-filename-pattern=%(outfile)s.%%s
< %(bamfile)s
> %(outfile)s
'''
P.run()
def buildBAMStats(infiles, outfile):
'''count number of reads mapped, duplicates, etc.
Excludes regions overlapping repetitive RNA sequences
Parameters
----------
infiles : list
infiles[0] : str
Input filename in :term:`bam` format
infiles[1] : str
Input filename with number of reads per sample
outfile : str
Output filename with read stats
annotations_interface_rna_gtf : str
:term:`PARMS`. :term:`gtf` format file with repetitive rna
'''
rna_file = PARAMS["annotations_interface_rna_gff"]
job_memory = "32G"
bamfile, readsfile = infiles
nreads = PipelineBamStats.getNumReadsFromReadsFile(readsfile)
track = P.snip(os.path.basename(readsfile), ".nreads")
# if a fastq file exists, submit for counting
if os.path.exists(track + ".fastq.gz"):
fastqfile = track + ".fastq.gz"
elif os.path.exists(track + ".fastq.1.gz"):
fastqfile = track + ".fastq.1.gz"
else:
fastqfile = None
if fastqfile is not None:
fastq_option = "--fastq-file=%s" % fastqfile
else:
fastq_option = ""
statement = '''
cgat bam2stats
%(fastq_option)s
--force-output
--mask-bed-file=%(rna_file)s
--ignore-masked-reads
--num-reads=%(nreads)i
--output-filename-pattern=%(outfile)s.%%s
< %(bamfile)s
> %(outfile)s
'''
P.run()
def buildPicardDuplicationStats(infile, outfile):
'''Get duplicate stats from picard MarkDuplicates '''
PipelineBamStats.buildPicardDuplicationStats(infile, outfile)
def loadBAMStats(infiles, outfile):
''' load bam statistics into bam_stats table '''
PipelineBamStats.loadBAMStats(infiles, outfile)
def loadContextStats(infiles, outfile):
''' load context mapping statistics into context_stats table '''
PipelineBamStats.loadSummarizedContextStats(infiles, outfile)
def loadPicardStats(infiles, outfile):
'''merge alignment stats into single tables.'''
PipelineBamStats.loadPicardAlignmentStats(infiles, outfile)
def loadPicardDuplicationStats(infiles, outfiles):
'''merge alignment stats into single tables.'''
PipelineBamStats.loadPicardDuplicationStats(infiles, outfiles)
def buildContextStats(infiles, outfile):
''' build mapping context stats '''
PipelineBamStats.summarizeTagsWithinContext(infiles[0], infiles[1],
outfile)
def loadPicardRnaSeqMetrics(infiles, outfiles):
'''merge alignment stats into single tables.'''
PipelineBamStats.loadPicardRnaSeqMetrics(infiles, outfiles)
def loadTranscriptProfile(infiles, outfile):
''' merge transcript profiles into a single table'''
PipelineBamStats.loadTranscriptProfile(infiles, outfile)
def loadContextStats(infiles, outfile):
''' load context mapping statistics into context_stats table '''
PipelineBamStats.loadSummarizedContextStats(infiles, outfile)
def loadPicardStats(infiles, outfile):
'''merge alignment stats into single tables.'''
PipelineBamStats.loadPicardAlignmentStats(infiles, outfile)
def loadPicardRnaSeqMetrics(infiles, outfiles):
'''merge alignment stats into single tables.'''
PipelineBamStats.loadPicardRnaSeqMetrics(infiles, outfiles)
def buildPicardDuplicationStats(infile, outfile):
'''Get duplicate stats from picard MarkDuplicates '''
PipelineBamStats.buildPicardDuplicationStats(infile, outfile)
def loadPicardDuplicationStats(infiles, outfiles):
'''merge alignment stats into single tables.'''
PipelineBamStats.loadPicardDuplicationStats(infiles, outfiles)
def loadStrandSpecificity(infiles, outfile):
''' merge strand specificity data into a single table'''
PipelineBamStats.loadStrandSpecificity(infiles, outfile)
def loadTranscriptProfile(infiles, outfile):
''' merge transcript profiles into a single table'''
PipelineBamStats.loadTranscriptProfile(infiles, outfile)
def loadCountReads(infiles, outfile):
''' load read counts count_reads table '''
PipelineBamStats.loadCountReads(infiles, outfile)
def loadCountReads(infiles, outfile):
''' load read counts count_reads table '''
PipelineBamStats.loadCountReads(infiles, outfile)
def buildContextStats(infiles, outfile):
''' build mapping context stats '''
PipelineBamStats.summarizeTagsWithinContext(
infiles[0], infiles[1], outfile)
def loadStrandSpecificity(infiles, outfile):
''' merge strand specificity data into a single table'''
PipelineBamStats.loadStrandSpecificity(infiles, outfile)
def loadBAMStats(infiles, outfile):
''' load bam statistics into bam_stats table '''
PipelineBamStats.loadBAMStats(infiles, outfile)
