def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", sailfish.get_build_string(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambiguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data, out_dir)
assert file_exists(gtf_fa), "%s was not found, exiting." % gtf_fa
tmpdir = dd.get_tmp_dir(data)
out_file = os.path.join(out_dir, "versionInfo.json")
if file_exists(out_file):
return out_dir
files = dd.get_input_sequence_files(data)
readlength = bam.fastq.estimate_read_length(files[0])
if readlength % 2 == 0:
readlength -= 1
kmersize = min(readlength, 31)
with file_transaction(data, out_dir) as tx_out_dir:
cmd = "{salmon} index -k {kmersize} -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def _create_combined_fasta(data, out_dir):
"""
if there are genomes to be disambiguated, create a FASTA file of
all of the transcripts for all genomes
"""
items = disambiguate.split([data])
fasta_files = []
for i in items:
odata = i[0]
gtf_file = dd.get_gtf_file(odata)
ref_file = dd.get_ref_file(odata)
out_file = os.path.join(out_dir, dd.get_genome_build(odata) + ".fa")
if file_exists(out_file):
fasta_files.append(out_file)
else:
out_file = _gtf_to_fasta(gtf_file, ref_file, out_file)
out_file = _clean_gtf_fa(out_file, out_file)
fasta_files.append(out_file)
out_stem = os.path.join(out_dir, dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_stem = "-".join([out_stem] + dd.get_disambiguate(data))
combined_file = out_stem + ".fa"
if file_exists(combined_file):
return combined_file
fasta_file_string = " ".join(fasta_files)
cmd = "cat {fasta_file_string} > {tx_out_file}"
with file_transaction(combined_file) as tx_out_file:
do.run(cmd.format(**locals()), "Combining transcriptome FASTA files.")
return combined_file
def rapmap_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambiguate(data))
rapmap = config_utils.get_program("rapmap", data["config"])
gtf_fa = create_combined_fasta(data, out_dir)
if file_exists(out_dir + "rapidx.jfhash"):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = "{rapmap} pseudoindex -i {tx_out_dir} -t {gtf_fa}"
message = "Creating RapMap pseudoindex for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def sailfish_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambiguate(data))
sailfish = config_utils.get_program("sailfish", data["config"])
num_cores = dd.get_num_cores(data)
gtf_fa = create_combined_fasta(data, out_dir)
if file_exists(out_dir + "versionInfo.json"):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = "{sailfish} index -p {num_cores} -t {gtf_fa} -o {tx_out_dir} -k 25"
message = "Creating sailfish index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def sailfish_index(gtf_file, ref_file, data, out_dir, kmer_size):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + (dd.get_disambiguate(data) or []))
sailfish = config_utils.get_program("sailfish", data["config"])
num_cores = dd.get_num_cores(data)
gtf_fa = create_combined_fasta(data, out_dir)
if file_exists(out_dir + "versionInfo.json"):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = ("{sailfish} index -p {num_cores} -t {gtf_fa} -o {tx_out_dir} "
"-k {kmer_size}")
message = "Creating sailfish index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def generate_transcript_counts(data):
"""Generate counts per transcript and per exon from an alignment"""
data["count_file"] = featureCounts.count(data)
if dd.get_fusion_mode(data, False):
oncofuse_file = oncofuse.run(data)
if oncofuse_file:
data = dd.set_oncofuse_file(data, oncofuse_file)
if dd.get_transcriptome_align(data) and not dd.get_transcriptome_bam(data):
file1, file2 = None, None
if dd.get_disambiguate(data):
bam_path = data["work_bam"]
fastq_paths = alignprep._bgzip_from_bam(bam_path, data["dirs"], data["config"], is_retry=False, output_infix='-transcriptome')
if len(fastq_paths) == 2:
file1, file2 = fastq_paths
else:
file1, file2 = fastq_paths[0], None
else:
file1, file2 = dd.get_input_sequence_files(data)
ref_file = dd.get_ref_file(data)
logger.info("Transcriptome alignment was flagged to run, but the "
"transcriptome BAM file was not found. Aligning to the "
"transcriptome with bowtie2.")
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
return [[data]]
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", sailfish.get_build_string(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data, out_dir)
assert file_exists(gtf_fa), "%s was not found, exiting." % gtf_fa
tmpdir = dd.get_tmp_dir(data)
out_file = os.path.join(out_dir, "versionInfo.json")
if file_exists(out_file):
return out_dir
files = dd.get_input_sequence_files(data)
readlength = bam.fastq.estimate_read_length(files[0])
if readlength % 2 == 0:
readlength -= 1
kmersize = min(readlength, 31)
with file_transaction(data, out_dir) as tx_out_dir:
cmd = "{salmon} index -k {kmersize} -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def rapmap_index(gtf_file, ref_file, algorithm, data, out_dir):
valid_indexes = ["pseudoindex", "quasiindex"]
index_type = algorithm + "index"
assert index_type in valid_indexes, \
"RapMap only supports %s indices." % valid_indexes
out_dir = os.path.join(out_dir, index_type, dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
rapmap = config_utils.get_program("rapmap", dd.get_config(data))
# use user supplied transcriptome FASTA file if it exists
if dd.get_transcriptome_fasta(data):
out_dir = os.path.join(out_dir, index_type, dd.get_genome_build(data))
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
tmpdir = dd.get_tmp_dir(data)
if file_exists(out_dir + "rapidx.jfhash"):
return out_dir
files = dd.get_input_sequence_files(data)
kmersize = sailfish.pick_kmersize(files[0])
message = "Creating rapmap {index_type} for {gtf_fa} with {kmersize} bp kmers."
with file_transaction(out_dir) as tx_out_dir:
cmd = "{rapmap} {index_type} -k {kmersize} -i {tx_out_dir} -t {gtf_fa}"
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def generate_transcript_counts(data):
"""Generate counts per transcript and per exon from an alignment"""
data["count_file"] = featureCounts.count(data)
if dd.get_fusion_mode(data, False):
oncofuse_file = oncofuse.run(data)
if oncofuse_file:
data = dd.set_oncofuse_file(data, oncofuse_file)
if dd.get_transcriptome_align(data) and not dd.get_transcriptome_bam(data):
file1, file2 = None, None
if dd.get_disambiguate(data):
bam_path = data["work_bam"]
fastq_paths = alignprep._bgzip_from_bam(
bam_path,
data["dirs"],
data["config"],
is_retry=False,
output_infix='-transcriptome')
if len(fastq_paths) == 2:
file1, file2 = fastq_paths
else:
file1, file2 = fastq_paths[0], None
else:
file1, file2 = dd.get_input_sequence_files(data)
ref_file = dd.get_ref_file(data)
logger.info("Transcriptome alignment was flagged to run, but the "
"transcriptome BAM file was not found. Aligning to the "
"transcriptome with bowtie2.")
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
return [[data]]
def rapmap_index(gtf_file, ref_file, algorithm, data, out_dir):
valid_indexes = ["pseudoindex", "quasiindex"]
index_type = algorithm + "index"
assert index_type in valid_indexes, \
"RapMap only supports %s indices." % valid_indexes
out_dir = os.path.join(out_dir, index_type, dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
rapmap = config_utils.get_program("rapmap", dd.get_config(data))
# use user supplied transcriptome FASTA file if it exists
if dd.get_transcriptome_fasta(data):
out_dir = os.path.join(out_dir, index_type, dd.get_genome_build(data))
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
tmpdir = dd.get_tmp_dir(data)
if file_exists(out_dir + "rapidx.jfhash"):
return out_dir
files = dd.get_input_sequence_files(data)
kmersize = sailfish.pick_kmersize(files[0])
message = "Creating rapmap {index_type} for {gtf_fa} with {kmersize} bp kmers."
with file_transaction(out_dir) as tx_out_dir:
cmd = "{rapmap} {index_type} -k {kmersize} -i {tx_out_dir} -t {gtf_fa}"
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def generate_transcript_counts(data):
"""Generate counts per transcript and per exon from an alignment"""
data["count_file"] = featureCounts.count(data)
if dd.get_transcriptome_align(data):
# to create a disambiguated transcriptome file realign with bowtie2
if dd.get_disambiguate(data):
logger.info("Aligning to the transcriptome with bowtie2 using the "
"disambiguated reads.")
bam_path = data["work_bam"]
fastq_paths = alignprep._bgzip_from_bam(
bam_path,
data["dirs"],
data,
is_retry=False,
output_infix='-transcriptome')
if len(fastq_paths) == 2:
file1, file2 = fastq_paths
else:
file1, file2 = fastq_paths[0], None
ref_file = dd.get_ref_file(data)
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
else:
file1, file2 = dd.get_input_sequence_files(data)
if not dd.get_transcriptome_bam(data):
ref_file = dd.get_ref_file(data)
logger.info(
"Transcriptome alignment was flagged to run, but the "
"transcriptome BAM file was not found. Aligning to the "
"transcriptome with bowtie2.")
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
data = spikein.counts_spikein(data)
return [[data]]
def kallisto_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index")
out_stem = dd.get_genome_build(data)
if dd.get_disambiguate(data):
out_stem = "-".join([out_stem] + dd.get_disambiguate(data))
index_dir = os.path.join(out_dir, out_stem)
out_file = os.path.join(index_dir, out_stem + ".idx")
kallisto = config_utils.get_program("kallisto", dd.get_config(data))
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tx_out_file:
cmd = "{kallisto} index -k 31 -i {tx_out_file} {gtf_fa}"
message = "Creating Kallisto index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_file
def kallisto_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index")
out_stem = dd.get_genome_build(data)
if dd.get_disambiguate(data):
out_stem = "-".join([out_stem] + dd.get_disambiguate(data))
index_dir = os.path.join(out_dir, out_stem)
out_file = os.path.join(index_dir, out_stem + ".idx")
kallisto = config_utils.get_program("kallisto", dd.get_config(data))
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
if file_exists(out_file):
return out_file
with file_transaction(out_file) as tx_out_file:
cmd = "{kallisto} index -k 31 -i {tx_out_file} {gtf_fa}"
message = "Creating Kallisto index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_file
def determine_indexes_to_make(samples):
"""
returns a subset of the samples that have different indexes in them to make sure we only
make each index once
"""
samples = [to_single_data(x) for x in samples]
indexes = set()
tomake = []
for data in samples:
out_dir = os.path.join(dd.get_work_dir(data), "inputs", "transcriptome")
out_stem = os.path.join(out_dir, dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_stem = "-".join([out_stem] + (dd.get_disambiguate(data) or []))
if dd.get_disambiguate(data):
out_stem = "-".join([out_stem] + (dd.get_disambiguate(data) or []))
combined_file = out_stem + ".fa"
if combined_file not in indexes:
tomake.append(data)
indexes.add(combined_file)
return tomake
def rapmap_pseudoindex(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "pseudoindex", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
rapmap = config_utils.get_program("rapmap", dd.get_config(data))
gtf_fa = sailfish._create_combined_fasta(data, out_dir)
tmpdir = dd.get_tmp_dir(data)
if file_exists(out_dir + "rapidx.jfhash"):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = "{rapmap} pseudoindex -k 31 -i {tx_out_dir} -t {gtf_fa}"
message = "Creating rapmap pseudoindex for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
gtf_fa = sailfish._create_combined_fasta(data, out_dir)
tmpdir = dd.get_tmp_dir(data)
### TODO PUT MEMOZATION HERE
with file_transaction(out_dir) as tx_out_dir:
cmd = "{salmon} index -k 31 -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", sailfish.get_build_string(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambiguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
assert file_exists(gtf_fa), "%s was not found, exiting." % gtf_fa
tmpdir = dd.get_tmp_dir(data)
out_file = os.path.join(out_dir, "versionInfo.json")
if file_exists(out_file):
logger.info("Transcriptome index for %s detected, skipping building." % gtf_fa)
return out_dir
files = dd.get_input_sequence_files(data)
kmersize = sailfish.pick_kmersize(files[0])
with file_transaction(data, out_dir) as tx_out_dir:
cmd = "{salmon} index -k {kmersize} -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa} with {kmersize} bp kmers."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
gtf_fa = sailfish._create_combined_fasta(data, out_dir)
tmpdir = dd.get_tmp_dir(data)
### TODO PUT MEMOZATION HERE
with file_transaction(out_dir) as tx_out_dir:
cmd = "{salmon} index -k 31 -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", sailfish.get_build_string(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambiguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
assert file_exists(gtf_fa), "%s was not found, exiting." % gtf_fa
tmpdir = dd.get_tmp_dir(data)
out_file = os.path.join(out_dir, "versionInfo.json")
if file_exists(out_file):
logger.info("Transcriptome index for %s detected, skipping building." % gtf_fa)
return out_dir
files = dd.get_input_sequence_files(data)
kmersize = sailfish.pick_kmersize(files[0])
with file_transaction(data, out_dir) as tx_out_dir:
cmd = "{salmon} index -k {kmersize} -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa} with {kmersize} bp kmers."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def prepare_input_data(config):
""" In case of disambiguation, we want to run fusion calling on
the disambiguated reads, which are in the work_bam file.
As EricScript accepts 2 fastq files as input, we need to convert
the .bam to 2 .fq files.
"""
if not dd.get_disambiguate(config):
return dd.get_input_sequence_files(config)
work_bam = dd.get_work_bam(config)
logger.info("Converting disambiguated reads to fastq...")
fq_files = convert_bam_to_fastq(work_bam, dd.get_work_dir(config), None,
None, config)
return fq_files
def prepare_input_data(config):
""" In case of disambiguation, we want to run fusion calling on
the disambiguated reads, which are in the work_bam file.
As EricScript accepts 2 fastq files as input, we need to convert
the .bam to 2 .fq files.
"""
if not dd.get_disambiguate(config):
return dd.get_input_sequence_files(config)
work_bam = dd.get_work_bam(config)
logger.info("Converting disambiguated reads to fastq...")
fq_files = convert_bam_to_fastq(
work_bam, dd.get_work_dir(config), None, None, config
)
return fq_files
def rapmap_index(gtf_file, ref_file, algorithm, data, out_dir):
valid_indexes = ["pseudoindex", "quasiindex"]
index_type = algorithm + "index"
assert index_type in valid_indexes, \
"RapMap only supports %s indices." % valid_indexes
out_dir = os.path.join(out_dir, index_type, dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
rapmap = config_utils.get_program("rapmap", dd.get_config(data))
gtf_fa = sailfish.create_combined_fasta(data, out_dir)
tmpdir = dd.get_tmp_dir(data)
if file_exists(out_dir + "rapidx.jfhash"):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = "{rapmap} {index_type} -k 31 -i {tx_out_dir} -t {gtf_fa}"
message = "Creating rapmap {index_type} for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data, out_dir)
tmpdir = dd.get_tmp_dir(data)
out_file = os.path.join(out_dir, "versionInfo.json")
if file_exists(out_file):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = "{salmon} index -k 31 -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def salmon_index(gtf_file, ref_file, data, out_dir):
out_dir = os.path.join(out_dir, "index", dd.get_genome_build(data))
if dd.get_disambiguate(data):
out_dir = "-".join([out_dir] + dd.get_disambguate(data))
salmon = config_utils.get_program("salmon", dd.get_config(data))
num_cores = dd.get_num_cores(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data, out_dir)
tmpdir = dd.get_tmp_dir(data)
out_file = os.path.join(out_dir, "versionInfo.json")
if file_exists(out_file):
return out_dir
with file_transaction(out_dir) as tx_out_dir:
cmd = "{salmon} index -k 31 -p {num_cores} -i {tx_out_dir} -t {gtf_fa}"
message = "Creating Salmon index for {gtf_fa}."
do.run(cmd.format(**locals()), message.format(**locals()), None)
return out_dir
def generate_transcript_counts(data):
"""Generate counts per transcript and per exon from an alignment"""
data["count_file"] = featureCounts.count(data)
if dd.get_fusion_mode(data, False):
oncofuse_file = oncofuse.run(data)
if oncofuse_file:
data = dd.set_oncofuse_file(data, oncofuse_file)
# if RSEM set to run, but the aligner didn't create the transcriptome BAM
# file, make one with bwa
if dd.get_disambiguate(data):
logger.info("RSEM is not supported yet for disambiguation protocols. "
"See https://github.com/chapmanb/bcbio-nextgen/issues/859")
return [[data]]
if dd.get_rsem(data) and not dd.get_transcriptome_bam(data):
file1, file2 = dd.get_input_sequence_files(data)
ref_file = dd.get_ref_file(data)
logger.info("RSEM was flagged to run, but the transcriptome BAM file "
"was not found. Aligning to the transcriptome with bowtie2.")
data = bowtie2.align_transcriptome(file1, file2, ref_file, data)
return [[data]]
def get_average_coverage(target_name, bed_file, data, bam_file=None):
if not bam_file:
bam_file = dd.get_align_bam(data) or dd.get_work_bam(data)
cache_file = _get_cache_file(data, target_name)
if dd.get_disambiguate(data):
cache = _read_cache(cache_file, [bed_file])
else:
cache = _read_cache(cache_file, [bam_file, bed_file])
if "avg_coverage" in cache:
return int(cache["avg_coverage"])
if bed_file:
avg_cov = _average_bed_coverage(bed_file, target_name, data)
else:
avg_cov = _average_genome_coverage(data, bam_file)
cache["avg_coverage"] = int(avg_cov)
_write_cache(cache, cache_file)
return int(avg_cov)
def get_build_string(data):
build_string = dd.get_genome_build(data)
if dd.get_disambiguate(data):
build_string = "-".join([build_string] + (dd.get_disambiguate(data) or []))
return build_string
def get_build_string(data):
build_string = dd.get_genome_build(data)
if dd.get_disambiguate(data):
build_string = "-".join([build_string] +
(dd.get_disambiguate(data) or []))
return build_string
