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)
gtf_fa = fasta.strip_transcript_versions(gtf_fa, os.path.join(out_dir, os.path.basename(gtf_fa)))
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 rapmap_index(gtf_file, ref_file, algorithm, data, out_dir):
out_dir = os.path.join(out_dir, "index")
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, sailfish.get_build_string(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):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
gtf_fa = fasta.strip_transcript_versions(gtf_fa, os.path.join(out_dir, os.path.basename(gtf_fa)))
tmpdir = dd.get_tmp_dir(data)
if file_exists(os.path.join(out_dir, "sa.bin")):
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 run_pizzly(data):
work_dir = dd.get_work_dir(data)
pizzlydir = os.path.join(work_dir, "pizzly")
samplename = dd.get_sample_name(data)
gtf = dd.get_gtf_file(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
stripped_fa = os.path.splitext(
os.path.basename(gtf_fa))[0] + "-noversions.fa"
stripped_fa = os.path.join(pizzlydir, stripped_fa)
gtf_fa = fasta.strip_transcript_versions(gtf_fa, stripped_fa)
fraglength = get_fragment_length(data)
cachefile = os.path.join(pizzlydir, "pizzly.cache")
fusions = kallisto.get_kallisto_fusions(data)
pizzlypath = config_utils.get_program("pizzly", dd.get_config(data))
outdir = pizzly(pizzlypath, gtf, gtf_fa, fraglength, cachefile, pizzlydir,
fusions, samplename, data)
return outdir
def run_pizzly(data):
samplename = dd.get_sample_name(data)
work_dir = dd.get_work_dir(data)
pizzlydir = os.path.join(work_dir, "pizzly")
gtf = dd.get_transcriptome_gtf(data)
if not gtf:
gtf = dd.get_gtf_file(data)
if dd.get_transcriptome_fasta(data):
gtf_fa = dd.get_transcriptome_fasta(data)
else:
gtf_fa = sailfish.create_combined_fasta(data)
stripped_fa = os.path.splitext(os.path.basename(gtf_fa))[0] + "-noversions.fa"
stripped_fa = os.path.join(pizzlydir, stripped_fa)
gtf_fa = fasta.strip_transcript_versions(gtf_fa, stripped_fa)
fraglength = get_fragment_length(data)
cachefile = os.path.join(pizzlydir, "pizzly.cache")
fusions = kallisto.get_kallisto_fusions(data)
pizzlypath = config_utils.get_program("pizzly", dd.get_config(data))
outdir = pizzly(pizzlypath, gtf, gtf_fa, fraglength, cachefile, pizzlydir,
fusions, samplename, data)
return outdir