def main():
usage = "usage: %prog <project> <output graphviz .dot file>"
description = "TEST: draw the outgroup DAG"
parser = OptionParser(usage=usage, description=description)
parser.add_option("--justLeaves",
dest="justLeaves",
action="store_true",
default=False,
help="Assign only leaves as outgroups")
parser.add_option("--threshold",
dest="threshold",
type='int',
default=None,
help="greedy threshold")
parser.add_option("--numOutgroups",
dest="maxNumOutgroups",
help="Maximum number of outgroups to provide",
type=int)
parser.add_option("--dynamic",
help="Use new dynamic programming"
" algorithm",
action="store_true",
default=False)
options, args = parser.parse_args()
if len(args) != 2:
parser.print_help()
raise RuntimeError("Wrong number of arguments")
proj = MultiCactusProject()
proj.readXML(args[0])
if not options.dynamic:
outgroup = GreedyOutgroup()
outgroup.importTree(proj.mcTree)
if options.justLeaves:
candidates = set(
[proj.mcTree.getName(x) for x in proj.mcTree.getLeaves()])
else:
candidates = None
outgroup.greedy(threshold=options.threshold,
candidateSet=candidates,
candidateChildFrac=1.1,
maxNumOutgroups=options.maxNumOutgroups)
else:
outgroup = DynamicOutgroup()
outgroup.importTree(proj.mcTree, proj.getInputSequenceMap())
outgroup.compute(options.maxNumOutgroups)
try:
NX.drawing.nx_agraph.write_dot(outgroup.dag, args[1])
except Exception as e:
print "NetworkX failed: %s" % str(e)
print "Writing ogMap in non-graphviz format"
with open(args[1], "w") as f:
for node, ogs in outgroup.ogMap.items():
f.write("%s -> %s\n" % (node, str(ogs)))
return 0
def main():
usage = "usage: %prog <project> <output graphviz .dot file>"
description = "TEST: draw the outgroup DAG"
parser = OptionParser(usage=usage, description=description)
parser.add_option("--justLeaves", dest="justLeaves", action="store_true",
default = False, help="Assign only leaves as outgroups")
parser.add_option("--threshold", dest="threshold", type='int',
default = None, help="greedy threshold")
parser.add_option("--numOutgroups", dest="maxNumOutgroups",
help="Maximum number of outgroups to provide", type=int)
parser.add_option("--dynamic", help="Use new dynamic programming"
" algorithm", action="store_true", default=False)
options, args = parser.parse_args()
if len(args) != 2:
parser.print_help()
raise RuntimeError("Wrong number of arguments")
proj = MultiCactusProject()
proj.readXML(args[0])
if not options.dynamic:
outgroup = GreedyOutgroup()
outgroup.importTree(proj.mcTree)
if options.justLeaves:
candidates = set([proj.mcTree.getName(x)
for x in proj.mcTree.getLeaves()])
else:
candidates = None
outgroup.greedy(threshold=options.threshold, candidateSet=candidates,
candidateChildFrac=1.1,
maxNumOutgroups=options.maxNumOutgroups)
else:
outgroup = DynamicOutgroup()
outgroup.importTree(proj.mcTree, proj.getInputSequenceMap())
outgroup.compute(options.maxNumOutgroups)
try:
NX.drawing.nx_agraph.write_dot(outgroup.dag, args[1])
except Exception as e:
print "NetworkX failed: %s" % str(e)
print "Writing ogMap in non-graphviz format"
with open(args[1], "w") as f:
for node, ogs in outgroup.ogMap.items():
f.write("%s -> %s\n" % (node, str(ogs)))
return 0
def createMCProject(tree, experiment, config, options):
mcTree = MultiCactusTree(tree, config.getSubtreeSize())
mcTree.nameUnlabeledInternalNodes(config.getDefaultInternalNodePrefix())
mcTree.computeSubtreeRoots()
mcProj = MultiCactusProject()
mcProj.mcTree = mcTree
mcProj.inputSequences = experiment.getSequences()[:]
if config.getDoSelfAlignment():
mcTree.addSelfEdges()
for name in mcProj.mcTree.getSubtreeRootNames():
expPath = "%s/%s/%s_experiment.xml" % (options.path, name, name)
mcProj.expMap[name] = os.path.abspath(expPath)
alignmentRootId = mcProj.mcTree.getRootId()
if options.root is not None:
try:
alignmentRootId = mcProj.mcTree.getNodeId(options.root)
except:
raise RuntimeError("Specified root name %s not found in tree" %
options.root)
mcProj.outgroup = None
if config.getOutgroupStrategy() == 'greedy':
# use the provided outgroup candidates, or use all outgroups
# as candidates if none are given
mcProj.outgroup = GreedyOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, alignmentRootId)
mcProj.outgroup.greedy(
threshold=config.getOutgroupThreshold(),
candidateSet=options.outgroupNames,
candidateChildFrac=config.getOutgroupAncestorQualityFraction(),
maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() == 'greedyLeaves':
# use all leaves as outgroups, unless outgroup candidates are given
mcProj.outgroup = GreedyOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, alignmentRootId)
ogSet = options.outgroupNames
if ogSet is None:
ogSet = set(
[mcProj.mcTree.getName(x) for x in mcProj.mcTree.getLeaves()])
mcProj.outgroup.greedy(threshold=config.getOutgroupThreshold(),
candidateSet=ogSet,
candidateChildFrac=2.0,
maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() == 'greedyPreference':
# prefer the provided outgroup candidates, if any, but use
# other nodes as "filler" if we can't find enough.
mcProj.outgroup = GreedyOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, alignmentRootId)
mcProj.outgroup.greedy(
threshold=config.getOutgroupThreshold(),
candidateSet=options.outgroupNames,
candidateChildFrac=config.getOutgroupAncestorQualityFraction(),
maxNumOutgroups=config.getMaxNumOutgroups())
mcProj.outgroup.greedy(
threshold=config.getOutgroupThreshold(),
candidateSet=None,
candidateChildFrac=config.getOutgroupAncestorQualityFraction(),
maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() == 'dynamic':
# dynamic programming algorithm that exactly optimizes probability
# that base in target node aligns to at least one base in the
# outgroup set. Caveats are that it only returns leaves, and
# the model used for optimization is super naive. Still, it does
# some things better than greedy approaches such as properly account
# for phylogenetic redundancy, as well as try to factor assembly
# size/quality automatically.
mcProj.outgroup = DynamicOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree,
mcProj.getInputSequenceMap(),
alignmentRootId,
candidateSet=options.outgroupNames)
mcProj.outgroup.compute(maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() != 'none':
raise RuntimeError("Could not understand outgroup strategy %s" %
config.getOutgroupStrategy())
# if necessary, we reroot the tree at the specified alignment root id. all leaf genomes
# that are no longer in the tree, but still used as outgroups, are moved into special fields
# so that we can remember to, say, get their paths for preprocessing.
specifyAlignmentRoot(mcProj, alignmentRootId)
return mcProj
def createMCProject(tree, experiment, config, options):
mcTree = MultiCactusTree(tree, config.getSubtreeSize())
mcTree.nameUnlabeledInternalNodes(config.getDefaultInternalNodePrefix())
mcTree.computeSubtreeRoots()
mcProj = MultiCactusProject()
mcProj.mcTree = mcTree
mcProj.inputSequences = experiment.getSequences()[:]
mcProj.outputSequenceDir = experiment.getOutputSequenceDir()
if config.getDoSelfAlignment():
mcTree.addSelfEdges()
for name in mcProj.mcTree.getSubtreeRootNames():
expPath = "%s/%s/%s_experiment.xml" % (options.path, name, name)
mcProj.expMap[name] = os.path.abspath(expPath)
alignmentRootId = mcProj.mcTree.getRootId()
if options.root is not None:
try:
alignmentRootId = mcProj.mcTree.getNodeId(options.root)
except Exception as e:
raise RuntimeError("Specified root name %s not found in tree" % options.root)
mcProj.outgroup = None
if config.getOutgroupStrategy() == 'greedy':
# use the provided outgroup candidates, or use all outgroups
# as candidates if none are given
mcProj.outgroup = GreedyOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, alignmentRootId)
mcProj.outgroup.greedy(threshold=config.getOutgroupThreshold(),
candidateSet=options.outgroupNames,
candidateChildFrac=config.getOutgroupAncestorQualityFraction(),
maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() == 'greedyLeaves':
# use all leaves as outgroups, unless outgroup candidates are given
mcProj.outgroup = GreedyOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, alignmentRootId)
ogSet = options.outgroupNames
if ogSet is None:
ogSet = set([mcProj.mcTree.getName(x) for x in mcProj.mcTree.getLeaves()])
mcProj.outgroup.greedy(threshold=config.getOutgroupThreshold(),
candidateSet=ogSet,
candidateChildFrac=2.0,
maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() == 'greedyPreference':
# prefer the provided outgroup candidates, if any, but use
# other nodes as "filler" if we can't find enough.
mcProj.outgroup = GreedyOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, alignmentRootId)
mcProj.outgroup.greedy(threshold=config.getOutgroupThreshold(),
candidateSet=options.outgroupNames,
candidateChildFrac=config.getOutgroupAncestorQualityFraction(),
maxNumOutgroups=config.getMaxNumOutgroups())
mcProj.outgroup.greedy(threshold=config.getOutgroupThreshold(),
candidateSet=None,
candidateChildFrac=config.getOutgroupAncestorQualityFraction(),
maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() == 'dynamic':
# dynamic programming algorithm that exactly optimizes probability
# that base in target node aligns to at least one base in the
# outgroup set. Caveats are that it only returns leaves, and
# the model used for optimization is super naive. Still, it does
# some things better than greedy approaches such as properly account
# for phylogenetic redundancy, as well as try to factor assembly
# size/quality automatically.
mcProj.outgroup = DynamicOutgroup()
mcProj.outgroup.importTree(mcProj.mcTree, mcProj.getInputSequenceMap(), alignmentRootId,
candidateSet=options.outgroupNames)
mcProj.outgroup.compute(maxNumOutgroups=config.getMaxNumOutgroups())
elif config.getOutgroupStrategy() != 'none':
raise RuntimeError("Could not understand outgroup strategy %s" % config.getOutgroupStrategy())
# if necessary, we reroot the tree at the specified alignment root id. all leaf genomes
# that are no longer in the tree, but still used as outgroups, are moved into special fields
# so that we can remember to, say, get their paths for preprocessing.
specifyAlignmentRoot(mcProj, alignmentRootId)
return mcProj
