示例#1
0
def process_task(task, wkname, npr_conf, nodeid2info):
    cogconf, cogclass = npr_conf.cog_selector
    concatconf, concatclass = npr_conf.alg_concatenator
    treebuilderconf, treebuilderclass = npr_conf.tree_builder
    splitterconf, splitterclass = npr_conf.tree_splitter
    
    threadid, nodeid, seqtype, ttype = (task.threadid, task.nodeid,
                                        task.seqtype, task.ttype)
    cladeid, targets, outgroups = db.get_node_info(threadid, nodeid)

    if not treebuilderclass or task.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 outgroups and len(outgroups) > 1:
        constrain_id = nodeid
    else:
        constrain_id = None
        
    node_info = nodeid2info[nodeid]
    conf = GLOBALS[task.configid]
    new_tasks = []    
    if ttype == "cog_selector":
       
        # Generates a md5 id based on the genetree configuration workflow used
        # for the concat alg task. If something changes, concat alg will change
        # and the associated tree will be rebuilt
        config_blocks = set([wkname])
        for key, value in conf[wkname].iteritems():
            if isinstance(value, list) or  isinstance(value, tuple) \
                    or isinstance(value, set):
                for elem in value:
                    config_blocks.add(elem[1:]) if isinstance(elem, str) and elem.startswith("@") else None
            elif isinstance(value, str):
                config_blocks.add(value[1:]) if value.startswith("@") else None
        config_checksum =  md5(''.join(["[%s]\n%s" %(x, dict_string(conf[x]))
                                        for x in sorted(config_blocks)]))

        # THIS PART HAS BEEN MOVED TO COG_SELECTOR TASK
        # Check that current selection of cogs will cover all target and
        # outgroup species
        #cog_hard_limit = int(conf[concatconf]["_max_cogs"])
        #sp_repr = defaultdict(int)
        #for co in task.raw_cogs[:cog_hard_limit]:
        #    for sp, seq in co:
        #        sp_repr[sp] += 1
        #missing_sp = (targets | outgroups) - set(sp_repr.keys())
        #if missing_sp:
        #    raise TaskError("missing species under current cog selection: %s" %missing_sp)
        #else:
        #    log.log(28, "Analysis of current COG selection:")
        #    for sp, ncogs in sorted(sp_repr.items(), key=lambda x:x[1]):
        #        log.log(28, "   % 30s species present in % 6d COGs" %(sp, ncogs))
                
        # register concat alignment task. NodeId associated to concat_alg tasks
        # and all its children jobs should take into account cog information and
        # not only species and outgroups included.
        
        concat_job = concatclass(task.cogs, seqtype, conf, concatconf,
                                 config_checksum)
        db.add_node(threadid,
                    concat_job.nodeid, cladeid,
                    targets, outgroups)

        # Register Tree constrains
        constrain_tree = "(%s, (%s));" %(','.join(sorted(outgroups)), 
                                         ','.join(sorted(targets)))
        _outs = "\n".join(map(lambda name: ">%s\n0" %name, sorted(outgroups)))
        _tars = "\n".join(map(lambda name: ">%s\n1" %name, sorted(targets)))
        constrain_alg = '\n'.join([_outs, _tars])
        db.add_task_data(concat_job.nodeid, DATATYPES.constrain_tree, constrain_tree)
        db.add_task_data(concat_job.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.
        concat_job.size = task.size
        new_tasks.append(concat_job)
       
    elif ttype == "concat_alg":
        # register tree for concat alignment, using constraint tree if
        # necessary
        alg_id = db.get_dataid(task.taskid, DATATYPES.concat_alg_phylip)
        try:
            parts_id = db.get_dataid(task.taskid, DATATYPES.model_partitions)
        except ValueError:
            parts_id = None

        nodeid2info[nodeid]["size"] = task.size
        nodeid2info[nodeid]["target_seqs"] = targets
        nodeid2info[nodeid]["out_seqs"] = outgroups
        tree_task = treebuilderclass(nodeid, alg_id,
                                     constrain_id, None,
                                     task.seqtype, conf, treebuilderconf,
                                     parts_id=parts_id)
        tree_task.size = task.size
        new_tasks.append(tree_task)
        
    elif ttype == "tree":
        merger_task = splitterclass(nodeid, seqtype, task.tree_file, conf, splitterconf)
        merger_task.size = task.size
        new_tasks.append(merger_task)

    elif ttype == "treemerger":
        # Lets merge with main tree
        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(targets), len(outgroups))

                target_cladeids = None
                if tobool(conf[splitterconf].get("_find_ncbi_targets", False)):
                    tcopy = mtree.copy()
                    ncbi.connect_database()
                    tax2name, tax2track = ncbi.annotate_tree_with_taxa(tcopy, None)
                    #tax2name, tax2track = ncbi.annotate_tree_with_taxa(tcopy, "fake") # for testing sptree example
                    n2content = tcopy.get_cached_content()
                    broken_branches, broken_clades, broken_clade_sizes, tax2name = ncbi.get_broken_branches(tcopy, n2content)
                    log.log(28, 'restricting NPR to broken clades: '+
                            colorify(', '.join(map(lambda x: "%s"%tax2name[x], broken_clades)), "wr"))
                    target_cladeids = set()
                    for branch in broken_branches:
                        print branch.get_ascii(attributes=['spname', 'taxid'], compact=True)
                        print map(lambda x: "%s"%tax2name[x], broken_branches[branch])
                        target_cladeids.add(branch.cladeid)

                for node, seqs, outs, wkname in get_next_npr_node(task.configid, ttree,
                                                          task.out_seqs, mtree, None,
                                                          npr_conf, target_cladeids): # None is to avoid alg checks
                    log.log(24, "Adding new node: %s seqs, %s outgroups",
                            len(seqs), len(outs))
                    new_task_node = cogclass(seqs, outs,
                                             source_seqtype, conf, cogconf)
                    new_task_node.target_wkname = wkname
                    new_tasks.append(new_task_node)
                    db.add_node(threadid,
                                new_task_node.nodeid, new_task_node.cladeid,
                                new_task_node.targets,
                                new_task_node.outgroups)
    return new_tasks
示例#2
0
文件: genetree.py 项目: jhcepas/npr
            #    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,