def test_ena():
from easydev import TempFile
with TempFile() as f1:
df.download_fasta("FN433596.1", output_filename=f1.name, method="ENA")
with TempFile() as f2:
df.download_fasta("FN433596.1", output_filename=f2.name, method="EUtils")
with TempFile() as f3:
from bioservices import ENA
ena = ENA()
df.download_fasta("FN433596.1", output_filename=f2.name, method="EUtils",
service=ena)
try:
df.download_fasta("FN433596.1", method="dummy")
assert False
except:
assert True
def test_ena():
from easydev import TempFile
with TempFile() as f1:
df.download_fasta("FN433596.1", output_filename=f1.name, method="ENA")
with TempFile() as f2:
df.download_fasta("FN433596.1", output_filename=f2.name, method="EUtils")
with TempFile() as f3:
from bioservices import ENA
ena = ENA()
df.download_fasta("FN433596.1", output_filename=f2.name, method="EUtils",
service=ena)
try:
df.download_fasta("FN433596.1", method="dummy")
assert False
except:
assert True
def main(args=None):
if args is None:
args = sys.argv[:]
user_options = Options(prog="sequana")
# If --help or no options provided, show the help
if len(args) == 1:
user_options.parse_args(["prog", "--help"])
else:
options = user_options.parse_args(args[1:])
sequana_debug_level(options.logging_level)
if options.download_reference:
logger.info("Downloading reference %s from %s\n" %
(options.download_reference, options.database))
from bioservices.apps import download_fasta as df
df.download_fasta(options.download_reference, method=options.database)
if options.download_genbank is None:
return
if options.download_genbank:
logger.info("Downloading genbank %s from %s\n" %
(options.download_reference, options.database))
from sequana.snpeff import download_fasta_and_genbank
download_fasta_and_genbank(options.download_genbank,
options.download_genbank,
genbank=True, fasta=False)
return
if options.genbank:
assert os.path.exists(options.genbank), \
"%s does not exists" % options.genbank
if options.verbose:
logger.info("Reading %s. This may take time depending on "
"your input file" % options.input)
# Convert BAM to BED
if options.input.endswith(".bam"):
bedfile = options.input.replace(".bam", ".bed")
if options.verbose:
logger.info("Converting BAM into BED file")
shellcmd("bedtools genomecov -d -ibam %s > %s" % (options.input, bedfile))
elif options.input.endswith(".bed"):
bedfile = options.input
else:
raise ValueError("Input file must be a BAM or BED file")
# Set the thresholds
if options.low_threshold is None:
options.low_threshold = -options.threshold
if options.high_threshold is None:
options.high_threshold = options.threshold
# and output directory
config.output_dir = options.output_directory
config.sample_name = os.path.basename(options.input).split('.')[0]
# Now we can create the instance of GenomeCoverage
gc = GenomeCov(bedfile, options.genbank, options.low_threshold,
options.high_threshold, 0.5, 0.5)
# if we have the reference, let us use it
if options.reference:
logger.info('Computing GC content')
gc.compute_gc_content(options.reference, options.w_gc,
options.circular)
# Now we scan the chromosomes,
if len(gc.chr_list) == 1:
if options.verbose:
logger.warning("There is only one chromosome. Selected automatically.")
chrom = gc.chr_list[0]
chromosomes = [chrom]
run_analysis(chrom, options, gc.feature_dict)
elif options.chromosome <=-1 or options.chromosome > len(gc.chr_list):
raise ValueError("invalid chromosome index ; must be in [1-{}]".format(len(gc.chr_list)+1))
else: # chromosome index is zero
# For user, we start at position 1 but in python, we start at zero
if options.chromosome:
chromosomes = [gc[options.chromosome-1]]
else:
chromosomes = gc
if options.verbose:
print("There are %s chromosomes/contigs." % len(gc))
for this in gc.chr_list:
print(" {}".format(this.chrom_name))
for i, chrom in enumerate(chromosomes):
if options.verbose:
print("==================== analysing chrom/contig %s/%s (%s)"
% (i + options.chromosome, len(gc),
chrom.chrom_name))
run_analysis(chrom, options, gc.feature_dict)
if options.verbose:
logger.info("Creating report in %s. Please wait" % config.output_dir)
if options.chromosome:
cc = options.chromosome - 1
datatable = CoverageModule.init_roi_datatable(gc[cc])
ChromosomeCoverageModule(chromosomes[0], datatable, None)
page = "{0}{1}{2}.cov.html".format(config.output_dir, os.sep,
chrom.chrom_name)
else:
CoverageModule(gc)
page = "{0}{1}coverage.html".format(config.output_dir, os.sep)
if options.show_html:
from easydev import onweb
onweb(page)
def main(args=None):
if args is None:
args = sys.argv[:]
user_options = Options(prog="sequana")
# If --help or no options provided, show the help
if len(args) == 1:
user_options.parse_args(["prog", "--help"])
else:
options = user_options.parse_args(args[1:])
logger.level = options.logging_level
if options.download_reference:
logger.info("Downloading reference %s from %s\n" %
(options.download_reference, options.database))
from bioservices.apps import download_fasta as df
df.download_fasta(options.download_reference, method=options.database)
if options.download_genbank is None:
return
if options.download_genbank:
logger.info("Downloading genbank %s from %s\n" %
(options.download_genbank, options.database))
from sequana.snpeff import download_fasta_and_genbank
download_fasta_and_genbank(options.download_genbank,
options.download_genbank,
genbank=True, fasta=False)
return
if options.genbank:
assert os.path.exists(options.genbank), \
"%s does not exists" % options.genbank
logger.info("Reading %s. This may take time depending on "
"your input file" % options.input)
# Convert BAM to BED
if options.input.endswith(".bam"):
bedfile = options.input.replace(".bam", ".bed")
logger.info("Converting BAM into BED file")
shellcmd("bedtools genomecov -d -ibam %s > %s" % (options.input, bedfile))
elif options.input.endswith(".bed"):
bedfile = options.input
else:
raise ValueError("Input file must be a BAM or BED file")
# Set the thresholds
if options.low_threshold is None:
options.low_threshold = -options.threshold
if options.high_threshold is None:
options.high_threshold = options.threshold
# and output directory
config.output_dir = options.output_directory
config.sample_name = os.path.basename(options.input).split('.')[0]
# Now we can create the instance of GenomeCoverage
if options.chromosome == -1:
chrom_list = []
else:
chrom_list = [options.chromosome]
gc = GenomeCov(bedfile, options.genbank, options.low_threshold,
options.high_threshold, options.double_threshold,
options.double_threshold, chunksize=options.chunksize,
chromosome_list=chrom_list)
# if we have the reference, let us use it
if options.reference:
logger.info('Computing GC content')
gc.compute_gc_content(options.reference, options.w_gc,
options.circular)
# Now we scan the chromosomes,
if len(gc.chrom_names) == 1:
logger.warning("There is only one chromosome. Selected automatically.")
run_analysis(gc.chr_list[0], options, gc.feature_dict)
elif options.chromosome <-1 or options.chromosome > len(gc.chrom_names):
msg = "invalid chromosome index; must be in [1;{}]".format(len(gc.chrom_names))
logger.error(msg)
sys.exit(1)
else:
if options.chromosome == -1:
chromosomes = gc.chrom_names # take all chromosomes
else:
# For user, we start at position 1 but in python, we start at zero
chromosomes = [gc.chrom_names[options.chromosome-1]]
logger.info("There are %s chromosomes/contigs." % len(gc))
for this in gc.chrom_names:
data = (this, gc.positions[this]["start"], gc.positions[this]["end"])
logger.info(" {} (starting pos: {}, ending pos: {})".format(*data))
# here we read chromosome by chromosome to save memory.
# However, if the data is small.
for i, chrom in enumerate(chromosomes):
logger.info("==================== analysing chrom/contig %s/%s (%s)"
% (i + 1, len(gc), gc.chrom_names[i]))
# since we read just one contig/chromosome, the chr_list contains
# only one contig, so we access to it with index 0
run_analysis(gc.chr_list[i], options, gc.feature_dict)
if options.skip_multiqc is False:
logger.info("=========================")
logger.info("Creating multiqc report")
pathtocfg = sequana_data("multiqc_config.yaml", "../multiqc/")
cmd = 'multiqc . -m sequana_coverage -f -c {}'.format(pathtocfg)
import subprocess
proc = subprocess.Popen(cmd.split(), cwd=options.output_directory)
proc.wait()
def main(args=None):
if args is None:
args = sys.argv[:]
user_options = Options(prog="sequana")
# If --help or no options provided, show the help
if len(args) == 1:
user_options.parse_args(["prog", "--help"])
else:
options = user_options.parse_args(args[1:])
logger.level = options.logging_level
if options.download_reference:
logger.info("Downloading reference %s from %s\n" %
(options.download_reference, options.database))
from bioservices.apps import download_fasta as df
df.download_fasta(options.download_reference, method=options.database)
if options.download_genbank is None:
return
if options.download_genbank:
logger.info("Downloading genbank %s from %s\n" %
(options.download_genbank, options.database))
from sequana.snpeff import download_fasta_and_genbank
download_fasta_and_genbank(options.download_genbank,
options.download_genbank,
genbank=True, fasta=False)
return
if options.genbank:
assert os.path.exists(options.genbank), \
"%s does not exists" % options.genbank
logger.info("Reading %s. This may take time depending on "
"your input file" % options.input)
# Convert BAM to BED
if options.input.endswith(".bam"):
bedfile = options.input.replace(".bam", ".bed")
logger.info("Converting BAM into BED file")
shellcmd("bedtools genomecov -d -ibam %s > %s" % (options.input, bedfile))
elif options.input.endswith(".bed"):
bedfile = options.input
else:
raise ValueError("Input file must be a BAM or BED file")
# Set the thresholds
if options.low_threshold is None:
options.low_threshold = -options.threshold
if options.high_threshold is None:
options.high_threshold = options.threshold
# Now we can create the instance of GenomeCoverage
if options.chromosome == -1:
chrom_list = []
else:
chrom_list = [options.chromosome]
gc = GenomeCov(bedfile, options.genbank, options.low_threshold,
options.high_threshold, options.double_threshold,
options.double_threshold, chunksize=options.chunksize,
chromosome_list=chrom_list)
# if we have the reference, let us use it
if options.reference:
logger.info('Computing GC content')
gc.compute_gc_content(options.reference, options.w_gc,
options.circular)
# Now we scan the chromosomes,
if len(gc.chrom_names) == 1:
logger.warning("There is only one chromosome. Selected automatically.")
run_analysis(gc.chr_list[0], options, gc.feature_dict)
elif options.chromosome <-1 or options.chromosome > len(gc.chrom_names):
msg = "invalid chromosome index; must be in [1;{}]".format(len(gc.chrom_names))
logger.error(msg)
sys.exit(1)
else:
if options.chromosome == -1:
chromosomes = gc.chrom_names # take all chromosomes
else:
# For user, we start at position 1 but in python, we start at zero
chromosomes = [gc.chrom_names[options.chromosome-1]]
logger.info("There are %s chromosomes/contigs." % len(gc))
for this in gc.chrom_names:
end = gc.positions[this]["end"]
start = gc.positions[this]["start"]
data = (this, gc.positions[this]["start"], gc.positions[this]["end"], end-start)
logger.info(" {} (starting pos: {}, ending pos: {}, length: {})".format(*data))
# here we read chromosome by chromosome to save memory.
# However, if the data is small.
for i, chrom in enumerate(chromosomes):
logger.info("==================== analysing chrom/contig %s/%s (%s)"
% (i + 1, len(gc), gc.chrom_names[i]))
# since we read just one contig/chromosome, the chr_list contains
# only one contig, so we access to it with index 0
run_analysis(gc.chr_list[i], options, gc.feature_dict)
# logging level seems to be reset to warning somewhere
logger.level = options.logging_level
if options.skip_multiqc is False:
logger.info("Creating multiqc report")
pathtocfg = sequana_data("multiqc_config.yaml", "../multiqc/")
cmd = 'multiqc . -m sequana_coverage -f -c {} '.format(pathtocfg)
import subprocess
proc = subprocess.Popen(cmd.split(), cwd=options.output_directory)
proc.wait()
# stdout=subprocess.PIPE, stderr=subprocess.PIPE)
#out, err = proc.communicate()
#with open("multiqc.log", "w") as fout:
# fout.write(err.decode())
logger.info("Done")