def main(recordFilenames, fastaFilename, title, xRange, bitRange):
"""
Print reads that match in a specified X-axis and bit score range.
@param recordFilenames: A C{list} of C{str} file names contain results of a
BLAST run, in JSON format.
@param fastaFilename: The C{str} name of the FASTA file that was originally
BLASTed.
@param title: The C{str} title of the subject sequence, as output by BLAST.
@param xRange: A (start, end) list of C{int}s, giving an X-axis range or
C{None} if the entire X axis range should be printed.
@param bitRange: A (start, end) list of C{int}s, giving a bit score range
or C{None} if the entire bit score range should be printed.
"""
reads = FastaReads(fastaFilename)
blastReadsAlignments = BlastReadsAlignments(reads, recordFilenames)
filtered = blastReadsAlignments.filter(whitelist=set([title]),
negativeTitleRegex='.')
titlesAlignments = TitlesAlignments(filtered)
if title not in titlesAlignments:
print('%s: Title %r not found in BLAST output' % (sys.argv[0], title))
sys.exit(3)
for titleAlignment in titlesAlignments[title]:
for hsp in titleAlignment.hsps:
if ((xRange is None or (xRange[0] <= hsp.subjectEnd
and xRange[1] >= hsp.subjectStart))
and (bitRange is None or
(bitRange[0] <= hsp.score.score <= bitRange[1]))):
print(('query: %s, start: %d, end: %d, score: %d' %
(titleAlignment.read.id, hsp.subjectStart,
hsp.subjectEnd, hsp.score.score)))
def main(recordFilenames, fastaFilename, title, xRange, bitRange):
"""
Print reads that match in a specified X-axis and bit score range.
@param recordFilenames: A C{list} of C{str} file names contain results of a
BLAST run, in JSON format.
@param fastaFilename: The C{str} name of the FASTA file that was originally
BLASTed.
@param title: The C{str} title of the subject sequence, as output by BLAST.
@param xRange: A (start, end) list of C{int}s, giving an X-axis range or
C{None} if the entire X axis range should be printed.
@param bitRange: A (start, end) list of C{int}s, giving a bit score range
or C{None} if the entire bit score range should be printed.
"""
reads = FastaReads(fastaFilename)
blastReadsAlignments = BlastReadsAlignments(reads, recordFilenames)
filtered = blastReadsAlignments.filter(whitelist=set([title]),
negativeTitleRegex='.')
titlesAlignments = TitlesAlignments(filtered)
if title not in titlesAlignments:
print('%s: Title %r not found in BLAST output' % (sys.argv[0], title))
sys.exit(3)
for titleAlignment in titlesAlignments[title]:
for hsp in titleAlignment.hsps:
if ((xRange is None or (xRange[0] <= hsp.subjectEnd and
xRange[1] >= hsp.subjectStart)) and
(bitRange is None or (bitRange[0] <= hsp.score.score <=
bitRange[1]))):
print(('query: %s, start: %d, end: %d, score: %d' % (
titleAlignment.read.id, hsp.subjectStart,
hsp.subjectEnd, hsp.score.score)))
args.diamondSqliteDatabaseFilename is None):
print('--diamondDatabaseFastaFilename and '
'--diamondSqliteDatabaseFilename cannot both be used with '
'--matcher diamond.', file=sys.stderr)
sys.exit(1)
from dark.diamond.alignments import DiamondReadsAlignments
readsAlignments = DiamondReadsAlignments(
reads, jsonFiles,
databaseFilename=args.diamondDatabaseFastaFilename,
databaseDirectory=args.diamondDatabaseFastaDirectory,
sqliteDatabaseFilename=args.diamondSqliteDatabaseFilename)
readsAlignments.filter(
maxAlignmentsPerRead=args.maxAlignmentsPerRead,
minSequenceLen=args.minSequenceLen,
maxSequenceLen=args.maxSequenceLen,
minStart=args.minStart, maxStop=args.maxStop,
oneAlignmentPerRead=args.oneAlignmentPerRead,
maxHspsPerHit=args.maxHspsPerHit,
scoreCutoff=args.scoreCutoff,
whitelist=whitelist, blacklist=blacklist,
titleRegex=args.titleRegex, negativeTitleRegex=args.negativeTitleRegex,
truncateTitlesAfter=args.truncateTitlesAfter, taxonomy=args.taxonomy)
format_ = 'fasta' if args.fasta else 'fastq'
write = sys.stdout.write
for readAlignments in readsAlignments:
write(readAlignments.read.toString(format_=format_))
