'any filtering option (other than --referenceId) you also specify '
'that is provided by the SAMFilter.addFilteringOptions will be '
'silently ignored!'))
args = parser.parse_args()
if args.noOffsets and args.noStats:
print(
'You have used both --noOffsets and --noStats, so there is no '
'output!',
file=sys.stderr)
sys.exit(1)
# We don't have a file of reads, we just want a read filter that we can use
# to filter the SAM file query sequences and to get reference lengths from.
reads = parseFASTAFilteringCommandLineOptions(args, Reads())
samFilter = SAMFilter.parseFilteringOptions(args, reads.filterRead)
printOffsets = not args.noOffsets
printStats = not args.noStats
if samFilter.referenceIds and len(samFilter.referenceIds) > 1:
print(
'Only one reference id can be given. To calculate coverage for more '
'than one reference, run this script multiple times.',
file=sys.stderr)
sys.exit(1)
try:
referenceLengths = samFilter.referenceLengths()
except UnknownReference:
'fact we typically do not have the reference in the SAM/BAM file), '
'we cut the inserted bases out of the aligned query and save the '
'information about what would have been inserted and where. That '
'information is printed by this option. The output gives the '
'0-based offset where the inserted base would be placed, followed '
'by a list of the nucleotides that were suggested as being '
'inserted and the number of times each nucleotide was suggested. '
'So for example the output might contain "27: T:3, G:10" which '
'indicates that 13 query (3 with T and 10 with G) matches would '
'insert a nucleotide into the reference at offset 27.'))
SAMFilter.addFilteringOptions(parser)
addFASTAFilteringCommandLineOptions(parser)
args = parser.parse_args()
reads = parseFASTAFilteringCommandLineOptions(args, Reads())
samFilter = SAMFilter.parseFilteringOptions(
args, filterRead=reads.filterRead)
paddedSAM = PaddedSAM(samFilter)
for read in paddedSAM.queries(rcSuffix=args.rcSuffix, rcNeeded=args.rcNeeded):
print(read.toString('fasta'), end='')
if args.listReferenceInsertions:
if paddedSAM.referenceInsertions:
print('(0-based) insertions into the reference:\n%s' %
nucleotidesToStr(paddedSAM.referenceInsertions, ' '),
file=sys.stderr)
else:
print('No matches required an insertion into the reference.',
file=sys.stderr)
'used to force conversion from FASTQ to FASTA'))
parser.add_argument(
'--checkResultCount', type=int,
help=('The number of reads expected in the output. If this number is '
'not seen, the script exits with status 1 and an error '
'message is printed unless --quiet was used.'))
addFASTACommandLineOptions(parser)
addFASTAFilteringCommandLineOptions(parser)
addFASTAEditingCommandLineOptions(parser)
args = parser.parse_args()
reads = parseFASTAEditingCommandLineOptions(
args, parseFASTAFilteringCommandLineOptions(
args, parseFASTACommandLineOptions(args)))
saveAs = (
args.saveAs or
(args.fasta and 'fasta') or
(args.fastq and 'fastq') or
(args.fasta_ss and 'fasta-ss'))
# Check for incompatible read/write formats. We can't write FASTQ
# unless we have FASTQ on input (else we won't have quality information),
# and we can't write PDB FASTA with secondary structure information
# unless we have that on input.
if saveAs == 'fastq' and not args.fastq:
raise ValueError(
'You have specified --saveAs fastq without using --fastq '
'to indicate that the input is FASTQ. Please be explicit.')
parser.add_argument(
'--checkResultCount',
type=int,
help=('The number of reads expected in the output. If this number is '
'not seen, the script exits with status 1 and an error '
'message is printed unless --quiet was used.'))
addFASTACommandLineOptions(parser)
addFASTAFilteringCommandLineOptions(parser)
addFASTAEditingCommandLineOptions(parser)
args = parser.parse_args()
reads = parseFASTAEditingCommandLineOptions(
args,
parseFASTAFilteringCommandLineOptions(
args, parseFASTACommandLineOptions(args)))
saveAs = (args.saveAs or (args.fasta and 'fasta')
or (args.fastq and 'fastq') or (args.fasta_ss and 'fasta-ss'))
# Check for incompatible read/write formats. We can't write FASTQ
# unless we have FASTQ on input (else we won't have quality information),
# and we can't write PDB FASTA with secondary structure information
# unless we have that on input.
if saveAs == 'fastq' and not args.fastq:
raise ValueError(
'You have specified --saveAs fastq without using --fastq '
'to indicate that the input is FASTQ. Please be explicit.')
elif saveAs == 'fasta-ss' and not args.fasta_ss:
raise ValueError(
'You have specified --saveAs fasta-ss without using --fasta-ss '