def pipeline(task, wkname, conf=None):
logindent(2)
if not task: # in this case, conf is expected
source_seqtype = "aa" if "aa" in GLOBALS["seqtypes"] else "nt"
all_seqs = GLOBALS["target_sequences"]
initial_task = Msf(set(all_seqs), set(), seqtype=source_seqtype)
initial_task.main_tree = None
initial_task.threadid = generate_runid()
initial_task.configid = initial_task.threadid
initial_task.target_wkname = wkname
# Register node
db.add_node(initial_task.threadid, initial_task.nodeid,
initial_task.cladeid, initial_task.target_seqs,
initial_task.out_seqs)
new_tasks = [initial_task]
else:
conf = GLOBALS[task.configid]
npr_conf = IterConfig(conf, wkname, task.size, task.seqtype)
new_tasks = process_task(task, wkname, npr_conf, conf["_nodeinfo"])
process_new_tasks(task, new_tasks, conf)
logindent(-2)
return new_tasks
def load_jobs(self):
# I want a single phylognetic tree for each cog
from ete3.tools.phylobuild_lib.workflow.genetree import pipeline
for co in self.cogs:
# Register a new msf task for each COG, using the same
# config file but opening an new tree reconstruction
# thread.
job = Msf(set(co), set(), seqtype=self.seqtype)
job.main_tree = None
job.threadid = generate_runid()
job.configid = self.conf["_configid"]
# This converts the job in a workflow job. As soon as a
# task is done, it will be automatically processed and the
# new tasks will be registered as new jobs.
job.task_processor = pipeline
job.target_wkname = self.genetree_workflow
self.jobs.append(job)
self.cog_ids.add(job.nodeid)
def process_task(task, wkname, npr_conf, nodeid2info):
alignerconf, alignerclass = npr_conf.aligner
cleanerconf, cleanerclass = npr_conf.alg_cleaner
mtesterconf, mtesterclass = npr_conf.model_tester
treebuilderconf, treebuilderclass = npr_conf.tree_builder
if not treebuilderclass:
# Allows to dump algs in workflows with no tree tasks
treebuilderclass = DummyTree
splitterconf, splitterclass = npr_conf.tree_splitter
conf = GLOBALS[task.configid]
seqtype = task.seqtype
nodeid = task.nodeid
ttype = task.ttype
taskid = task.taskid
threadid = task.threadid
node_info = nodeid2info[nodeid]
size = task.size #node_info.get("size", 0)
target_seqs = node_info.get("target_seqs", [])
out_seqs = node_info.get("out_seqs", [])
if not treebuilderclass or size < 4:
# Allows to dump algs in workflows with no tree tasks or if tree
# inference does not make sense given the number of sequences. DummyTree
# will produce a fake fully collapsed newick tree.
treebuilderclass = DummyTree
# If more than one outgroup are used, enable the use of constrain
if out_seqs and len(out_seqs) > 1:
constrain_id = nodeid
else:
constrain_id = None
new_tasks = []
if ttype == "msf":
# Register Tree constrains
constrain_tree = "(%s, (%s));" % (','.join(sorted(
task.out_seqs)), ','.join(sorted(task.target_seqs)))
_outs = "\n".join([">%s\n0" % name for name in sorted(task.out_seqs)])
_tars = "\n".join(
[">%s\n1" % name for name in sorted(task.target_seqs)])
constrain_alg = '\n'.join([_outs, _tars])
db.add_task_data(nodeid, DATATYPES.constrain_tree, constrain_tree)
db.add_task_data(nodeid, DATATYPES.constrain_alg, constrain_alg)
db.dataconn.commit() # since the creation of some Task
# objects may require this info, I need
# to commit right now.
# Register node
db.add_node(task.threadid, task.nodeid, task.cladeid, task.target_seqs,
task.out_seqs)
nodeid2info[nodeid]["size"] = task.size
nodeid2info[nodeid]["target_seqs"] = task.target_seqs
nodeid2info[nodeid]["out_seqs"] = task.out_seqs
alg_task = alignerclass(nodeid, task.multiseq_file, seqtype, conf,
alignerconf)
alg_task.size = task.size
new_tasks.append(alg_task)
elif ttype == "alg" or ttype == "acleaner":
if ttype == "alg":
nodeid2info[nodeid]["alg_path"] = task.alg_fasta_file
elif ttype == "acleaner":
nodeid2info[nodeid]["alg_clean_path"] = task.clean_alg_fasta_file
alg_fasta_file = getattr(task, "clean_alg_fasta_file",
task.alg_fasta_file)
alg_phylip_file = getattr(task, "clean_alg_phylip_file",
task.alg_phylip_file)
# Calculate alignment stats
# cons_mean, cons_std = get_trimal_conservation(task.alg_fasta_file,
# conf["app"]["trimal"])
#
# max_identity = get_trimal_identity(task.alg_fasta_file,
# conf["app"]["trimal"])
# log.info("Conservation: %0.2f +-%0.2f", cons_mean, cons_std)
# log.info("Max. Identity: %0.2f", max_identity)
#import time
#t1 = time.time()
#mx, mn, mean, std = get_identity(task.alg_fasta_file)
#print time.time()-t1
#log.log(26, "Identity: max=%0.2f min=%0.2f mean=%0.2f +- %0.2f",
# mx, mn, mean, std)
#t1 = time.time()
if seqtype == "aa" and npr_conf.switch_aa_similarity < 1:
try:
alg_stats = db.get_task_data(taskid, DATATYPES.alg_stats)
except Exception as e:
alg_stats = {}
if ttype == "alg":
algfile = pjoin(GLOBALS["input_dir"], task.alg_phylip_file)
dataid = DATATYPES.alg_phylip
elif ttype == "acleaner":
algfile = pjoin(GLOBALS["input_dir"],
task.clean_alg_phylip_file)
dataid = DATATYPES.clean_alg_phylip
if "i_mean" not in alg_stats:
log.log(24, "Calculating alignment stats...")
# dump data if necesary
algfile = pjoin(GLOBALS["input_dir"], task.alg_phylip_file)
if not pexist(algfile):
# dump phylip alg
open(algfile,
"w").write(db.get_data(db.get_dataid(taskid, dataid)))
mx, mn, mean, std = get_statal_identity(
algfile, conf["app"]["statal"])
alg_stats = {
"i_max": mx,
"i_mean": mean,
"i_min": mn,
"i_std": std
}
db.add_task_data(taskid, DATATYPES.alg_stats, alg_stats)
log.log(22, "Alignment stats (sequence similarity):")
log.log(
22,
" max: %(i_max)0.2f, min:%(i_min)0.2f, avg:%(i_mean)0.2f+-%(i_std)0.2f"
% (alg_stats))
else:
alg_stats = {"i_max": -1, "i_mean": -1, "i_min": -1, "i_std": -1}
#print time.time()-t1
#log.log(24, "Identity: max=%0.2f min=%0.2f mean=%0.2f +- %0.2f",
# mx, mn, mean, std)
task.max_ident = alg_stats["i_max"]
task.min_ident = alg_stats["i_min"]
task.mean_ident = alg_stats["i_mean"]
task.std_ident = alg_stats["i_std"]
next_task = None
if ttype == "alg" and cleanerclass:
next_task = cleanerclass(nodeid, seqtype, alg_fasta_file,
alg_phylip_file, conf, cleanerconf)
else:
# Converts aa alignment into nt if necessary
if seqtype == "aa" and \
"nt" in GLOBALS["seqtypes"] and \
task.mean_ident >= npr_conf.switch_aa_similarity:
log.log(28, "@@2:Switching to codon alignment!@@1: amino-acid sequence similarity: %0.2f >= %0.2f" %\
(task.mean_ident, npr_conf.switch_aa_similarity))
alg_fasta_file = "%s.%s" % (taskid, DATATYPES.alg_nt_fasta)
alg_phylip_file = "%s.%s" % (taskid, DATATYPES.alg_nt_phylip)
try:
alg_fasta_file = db.get_dataid(taskid,
DATATYPES.alg_nt_fasta)
alg_fasta_file = db.get_dataid(taskid,
DATATYPES.alg_nt_phylip)
except ValueError:
log.log(22, "Calculating codon alignment...")
source_alg = pjoin(GLOBALS["input_dir"],
task.alg_fasta_file)
if ttype == "alg":
kept_columns = []
elif ttype == "acleaner":
# if original alignment was trimmed, use it as reference
# but make the nt alignment only on the kept columns
kept_columns = db.get_task_data(
taskid, DATATYPES.kept_alg_columns)
if not pexist(source_alg):
open(source_alg, "w").write(
db.get_task_data(taskid, DATATYPES.alg_fasta))
nt_alg = switch_to_codon(source_alg,
kept_columns=kept_columns)
db.add_task_data(taskid, DATATYPES.alg_nt_fasta,
nt_alg.write())
db.add_task_data(taskid, DATATYPES.alg_nt_phylip,
nt_alg.write(format='iphylip_relaxed'))
npr_conf = IterConfig(conf, wkname, task.size, "nt")
seqtype = "nt"
if mtesterclass:
next_task = mtesterclass(nodeid, alg_fasta_file,
alg_phylip_file, constrain_id, conf,
mtesterconf)
elif treebuilderclass:
next_task = treebuilderclass(nodeid, alg_phylip_file,
constrain_id, None, seqtype, conf,
treebuilderconf)
if next_task:
next_task.size = task.size
new_tasks.append(next_task)
elif ttype == "mchooser":
if treebuilderclass:
alg_fasta_file = task.alg_fasta_file
alg_phylip_file = task.alg_phylip_file
model = task.best_model
tree_task = treebuilderclass(nodeid, alg_phylip_file, constrain_id,
model, seqtype, conf, treebuilderconf)
tree_task.size = task.size
new_tasks.append(tree_task)
elif ttype == "tree":
treemerge_task = splitterclass(nodeid, seqtype, task.tree_file, conf,
splitterconf)
#if conf["tree_splitter"]["_outgroup_size"]:
# treemerge_task = TreeSplitterWithOutgroups(nodeid, seqtype, task.tree_file, main_tree, conf)
#else:
# treemerge_task = TreeSplitter(nodeid, seqtype, task.tree_file, main_tree, conf)
treemerge_task.size = task.size
new_tasks.append(treemerge_task)
elif ttype == "treemerger":
if not task.task_tree:
task.finish()
log.log(24, "Saving task tree...")
annotate_node(task.task_tree, task)
db.update_node(nid=task.nodeid,
runid=task.threadid,
newick=db.encode(task.task_tree))
db.commit()
if not isinstance(treebuilderclass,
DummyTree) and npr_conf.max_iters > 1:
current_iter = get_iternumber(threadid)
if npr_conf.max_iters and current_iter >= npr_conf.max_iters:
log.warning("Maximum number of iterations reached!")
else:
# Add new nodes
source_seqtype = "aa" if "aa" in GLOBALS["seqtypes"] else "nt"
ttree, mtree = task.task_tree, task.main_tree
log.log(26, "Processing tree: %s seqs, %s outgroups",
len(target_seqs), len(out_seqs))
alg_path = node_info.get("clean_alg_path",
node_info["alg_path"])
for node, seqs, outs, wkname in get_next_npr_node(
threadid, ttree, task.out_seqs, mtree, alg_path,
npr_conf):
log.log(24, "Registering new node: %s seqs, %s outgroups",
len(seqs), len(outs))
new_task_node = Msf(seqs, outs, seqtype=source_seqtype)
new_task_node.target_wkname = wkname
new_tasks.append(new_task_node)
return new_tasks