from itol import *
from muscle import Muscle
from mafft import MAFFT
import clique_filter
import quorum
if __name__=="__main__":
faidx = "/home/mortonjt/Projects/Bacfinder/workspace/quorum/data/all_trans.fai"
gffFile = "/home/mortonjt/Projects/Bacfinder/workspace/quorum/data/all.gff"
folder = "/home/mortonjt/Projects/Bacfinder/workspace/quorum/intermediate"
if os.path.exists("test.pickle"):
all_hits = cPickle.load(open("test.pickle",'rb'))
else:
toxin_hits = hmmer.parse("%s/toxin.out"%folder)
modifier_hits = hmmer.parse("%s/modifier.out"%folder)
immunity_hits = hmmer.parse("%s/immunity.out"%folder)
regulator_hits = hmmer.parse("%s/regulator.out"%folder)
transport_hits = hmmer.parse("%s/transport.out"%folder)
gff = gff.GFF(gff_file=gffFile,fasta_index=faidx)
toxin_hits = gff.call_orfs(toxin_hits )
modifier_hits = gff.call_orfs(modifier_hits )
immunity_hits = gff.call_orfs(immunity_hits )
regulator_hits = gff.call_orfs(regulator_hits)
transport_hits = gff.call_orfs(transport_hits)
open("%s/toxin_orfs.out"%folder,'w').write(hmmer.hmmerstr(toxin_hits))
open("%s/modifier_orfs.out"%folder,'w').write(hmmer.hmmerstr(modifier_hits))
open("%s/immunity_orfs.out"%folder,'w').write(hmmer.hmmerstr(immunity_hits))
open("%s/regulator_orfs.out"%folder,'w').write(hmmer.hmmerstr(regulator_hits))
def cliqueFilter(self,clique_radius=50000,threshold=62,functions = ["toxin","modifier","immunity","transport","regulator"]):
print "Clique filtering","Looking for cliques with",functions
toxin_hits = hmmer.parse("%s/toxin.out"%self.intermediate)
modifier_hits = hmmer.parse("%s/modifier.out"%self.intermediate)
immunity_hits = hmmer.parse("%s/immunity.out"%self.intermediate)
regulator_hits = hmmer.parse("%s/regulator.out"%self.intermediate)
transport_hits = hmmer.parse("%s/transport.out"%self.intermediate)
faaindex = fasta.Indexer(self.faa,self.faaidx)
faaindex.index()
faaindex.load()
genefile = gff.GFF(self.gff,fasta_index=self.faaidx)
genefile.indexdb()
toxin_hits = genefile.call_orfs(toxin_hits ,faaindex)
modifier_hits = genefile.call_orfs(modifier_hits ,faaindex)
immunity_hits = genefile.call_orfs(immunity_hits ,faaindex)
regulator_hits = genefile.call_orfs(regulator_hits,faaindex)
transport_hits = genefile.call_orfs(transport_hits,faaindex)
toxin_hits = threshold_filter.filter(toxin_hits,threshold)
modifier_hits = threshold_filter.filter(modifier_hits,threshold)
immunity_hits = threshold_filter.filter(immunity_hits,threshold)
regulator_hits = threshold_filter.filter(regulator_hits,threshold)
transport_hits = threshold_filter.filter(transport_hits,threshold)
all_hits = toxin_hits+modifier_hits+immunity_hits+regulator_hits+transport_hits
seq_dict = {x[0]:x[1] for x in all_hits}
del all_hits
toxin_ids,toxin_seqs = zip(*toxin_hits)
modifier_ids,modifier_seqs = zip(*modifier_hits)
immunity_ids,immunity_seqs = zip(*immunity_hits)
regulator_ids,regulator_seqs = zip(*regulator_hits)
transport_ids,transport_seqs = zip(*transport_hits)
del toxin_hits
del modifier_hits
del immunity_hits
del regulator_hits
del transport_hits
all_ids = toxin_ids+modifier_ids+immunity_ids+regulator_ids+transport_ids
all_ids = interval_filter.unique(all_ids)
# #Sort by start/end position and genome name
all_ids=sorted(all_ids,key=lambda x: x[6])
all_ids=sorted(all_ids,key=lambda x: x[5])
all_ids=sorted(all_ids,key=lambda x: x[0])
#all_ids=sorted(all_ids,key=lambda x: x[-3])
del toxin_ids
del modifier_ids
del immunity_ids
del regulator_ids
del transport_ids
print "all ids",len(all_ids)
print '\n'.join(map(str,all_ids[:10]))
#Find operons with at least a toxin and a transport
clusters = clique_filter.findContextGeneClusters(all_ids,
radius=clique_radius,
backtrans=False,
functions=["toxin","transport"])
print "Clusters: ",len(clusters)
outhandle = open(self.operons_out,'w')
self.writeClusters(clusters,seq_dict,outhandle)
outhandle.close()
#Predict operons based on just context genes
clusters = clique_filter.findContextGeneClusters(all_ids,
radius=clique_radius,
backtrans=False,
functions=["modifier","regulator","immunity","transport"])
print "Clusters: ",len(clusters)
outhandle = open(self.pred_operons_out,'w')
self.writeClusters(clusters,seq_dict,outhandle)
outhandle.close()