def main():
parser = argparse.ArgumentParser(description = "Annotate SVGTools tree")
parser.add_argument('SVGFile', metavar = 'SVGTools file', type=str, \
help = "The input SVGTools tree")
parser.add_argument('insertFile', metavar = 'Insert file', type=str, \
help = "The FASTA file of extracted insert sequences")
parser.add_argument('--sizeScaling', nargs='?', const=1, type=float, \
help = "Global size scaling factor ", default=0.1)
parser.add_argument('--circleScaling', nargs='?', const=1, type=float, \
help = "Circle scaling factor ", default=0.05)
parser.add_argument('--fontScaling', nargs='?', const=1, type=float, \
help = "Extra font scaling factor ", default=1)
parser.add_argument('--renameFile', type=str, \
help = "File for renaming leaves")
parser.add_argument('--alwaysLabel', type=str, \
help = "Always label leaves with this accession")
parser.add_argument('--labelThresh', default=1, type=int, \
help = "Minimum size of insert to label")
args = parser.parse_args()
seqs = fasta.getProteinSeqs(args.insertFile)
rename = {}
alwaysLabel = {}
if args.renameFile:
(rename,orgs) = loadRenameFile(args.renameFile)
if args.alwaysLabel:
alwaysLabel = loadAlwaysLabelFile(args.alwaysLabel)
processSVG(args.SVGFile, seqs, args.sizeScaling, args.circleScaling, args.fontScaling, rename=orgs, alwaysLabel=alwaysLabel, labelThresh=args.labelThresh)
def extractInserts(outputSeqs, curOrg, genomeFile):
'''
Extracts all flagellin insert sequences and appends them to a FASTA file.
curOrg is of type organismClass
genomeFile is the input FASTA genome file
rename is bool: if True, rename as a integer for output as a lookup table
'''
seqs = fasta.getProteinSeqs(genomeFile)
sorted_proteins = sorted(curOrg.families["FliC"].items(),
key=operator.itemgetter(1))[::-1]
for protein, data in sorted_proteins:
outputSeqs[protein] = \
seqs[protein][data.notes['insert_start']-1:data.notes['insert_end']-1]
def main():
parser = OptionParser("usage: %prog <FASTA file> <list of seq IDs>")
#parser.add_option("-s", "--svg", dest="svg", help="output an SVGTools file of this name")
(options, args) = parser.parse_args()
if (len(args) < 2):
parser.error("Incorrect number of arguments!")
seqs = fasta.getProteinSeqs(args[0])
count = 1
while count < len(args):
newSeqs = {}
newSeqs[args[count]] = seqs[args[count]]
fasta.printFASTA(newSeqs)
count += 1
def main():
parser = argparse.ArgumentParser(description = "Get class stats")
parser.add_argument('classFile', metavar = 'Class file', type=str, \
help = "The file listing different classes")
parser.add_argument('insertFile', metavar = 'Insert file', type=str, \
help = "The FASTA file of extracted insert sequences")
parser.add_argument('renameFile', type=str, \
help = "File for renaming leaves")
args = parser.parse_args()
seqs = fasta.getProteinSeqs(args.insertFile)
classes = getClasses(args.classFile)
rename = loadRenameFile(args.renameFile)
classLens = getClassLengths(classes,seqs,rename)
for the_class in classLens:
print the_class+"\t"+str(len(classLens[the_class]))+"\t"+str(numpy.mean(classLens[the_class]))
def extractConservedEnds(outputSeqs, curOrg, genomeFile):
'''
Extracts all flagellin conserved N- and C-terminal domains,
concatenates them both into a single sequence with excised insert,
and appends them to a FASTA file.
curOrg is of type organismClass
genomeFile is the input FASTA genome file
rename is bool: if True, rename as a integer for output as a lookup table
'''
seqs = fasta.getProteinSeqs(genomeFile)
sorted_proteins = sorted(curOrg.families["FliC"].items(),
key=operator.itemgetter(1))[::-1]
for protein, data in sorted_proteins:
outputSeqs[protein] = \
seqs[protein][0:(data.notes['insert_start']-1)] + \
seqs[protein][(data.notes['insert_end']-1):-1]
def main():
parser = argparse.ArgumentParser(
description=
"Plots an SVG of domain structures HMMs specified in a directory")
parser.add_argument('fastaFile', metavar = 'FASTA file', type=str, \
help = "The FASTA file to plot")
parser.add_argument('SVGout', metavar = 'SVG output filename', type=str, \
help = "The SVGTools output filename")
parser.add_argument('xdomain', \
help = "Filename of x-domain HMM (not directory -- this is HMM_DIR)")
parser.add_argument('--hmmdir', \
help = "Location of HMMs (overrides HMM_DIR environment variable)")
parser.add_argument(
'--extractSlivers',
help="label, and extract to FAA, sliver sections > X aa")
parser.add_argument(
'--outputOthers',
help="Also output stretches of sequence between annotated domains")
args = parser.parse_args()
# ----------
# Init
yInc = 40
xScale = 0.1
yScale = 0.5
geneHeight = yInc * 0.4
sliverCount = 0
xMargin = 500
sliverProteins = {}
coords = {}
#-----------
if "HMM_DIR" in os.environ:
HMMDir = os.environ["HMM_DIR"]
if args.hmmdir:
HMMDir = args.hmmdir
else:
if not "HMM_DIR" in os.environ:
sys.exit(
"ERROR: HMM_DIR not specified on command line or environment var"
)
proteins = fasta.getProteinSeqs(args.fastaFile)
proteinList = fasta.getSequenceOrder(args.fastaFile)
annotations = annotateGenes.organismClass(args.fastaFile,
HMMDir,
annotateAll=False)
annotations.getStraightforwardsProtein("X", [args.xdomain], HMMDir=HMMDir)
annotations.annotateFlagellins()
# -----------------
SVGFile = SVGTools.SVGClass(imageHeight=1500)
y = yInc
for protein in proteinList:
slivers = [[1, len(proteins[protein])]]
Y = (y) * yScale
SVGFile.addItem(
SVGTools.lineClass(x1=xMargin * xScale,
y1=Y,
x2=(xMargin + len(proteins[protein])) * xScale,
y2=Y))
SVGFile.addItem(SVGTools.textClass(protein,
x=0,
y=(geneHeight + y) * yScale),
layer=1)
y += yInc
if protein in annotations.families["FliC"]:
annotation = annotations.families["FliC"][protein]
for FliCn in annotation.notes["FliCn"]:
slivers = recalcSlivers(slivers, FliCn["from"], FliCn["to"])
x1 = (xMargin + FliCn["from"]) * xScale
x2 = (xMargin + FliCn["to"]) * xScale
SVGFile.addItem(
SVGTools.rectClass(x=x1,
y=Y - (geneHeight * 0.5),
width=x2 - x1,
height=geneHeight,
colour=SVGTools.colourClass(r=255)))
for FliCc in annotation.notes["FliCc"]:
slivers = recalcSlivers(slivers, FliCc["from"], FliCc["to"])
x1 = (xMargin + FliCc["from"]) * xScale
x2 = (xMargin + FliCc["to"]) * xScale
SVGFile.addItem(
SVGTools.rectClass(x=x1,
y=Y - (geneHeight * 0.5),
width=x2 - x1,
height=geneHeight,
colour=SVGTools.colourClass(b=255)))
if protein in annotations.families["X"]:
annotation = annotations.families["X"][protein]
green = 255
for domainHit in annotation.notes["notes"]:
greenColour = SVGTools.colourClass(g=green)
x1 = (xMargin + domainHit["from"]) * xScale
x2 = (xMargin + domainHit["to"]) * xScale
if "iEvalue" in domainHit:
if (domainHit["iEvalue"] < 0.001):
slivers = recalcSlivers(slivers, domainHit["from"],
domainHit["to"])
SVGFile.addItem(
SVGTools.rectClass(x=x1,
y=Y - (geneHeight * 0.5),
width=x2 - x1,
height=geneHeight,
colour=greenColour))
#SVGFile.addItem(SVGTools.textClass(str(domainHit["iEvalue"]),fontsize=8, x=((x1+x2)/2),y=(geneHeight+y-yInc)*yScale),layer=1)
#green = green * 0.75
if args.extractSlivers:
for sliver in slivers:
if sliver[1] - sliver[0] >= int(args.extractSlivers):
_x = (xMargin + (sliver[0] + sliver[1]) / 2) * xScale
_y = (geneHeight + y - yInc) * yScale
coords[str(sliverCount)] = [_x, _y]
SVGFile.addItem(SVGTools.textClass(str(str(sliverCount)),
fontsize=8,
x=_x,
y=_y),
layer=1)
sliverProteins[str(
sliverCount)] = proteins[protein][sliver[0]:sliver[1]]
sliverCount += 1
f = open("slivers.xy", 'w')
for sliver in sliverProteins:
f.write(sliver + "\t" + str(int(coords[sliver][0])) + "," +
str(int(coords[sliver][1])) + "\n")
fasta.writeFASTA("slivers.faa", sliverProteins)
SVGout = open(args.SVGout, 'w')
SVGout.write(str(SVGFile) + "\n")