#pVOGdb.addPvogs_old(pVOGlines,LOG_H)
pVOGdb.addPvogs(PVOG_LIB_DIR, LOG_H)
if CHATTY:
print("pVOGs have been recorded")
LOG_H.write("%s%s%s\n" % ("There are ", len(pVOGdb.pVOGlist), " pVOGs"))
accessionCount = pVOGdb.getAccessionCount()
LOG_H.write("%s%s\n" % ("The total number of accessions is ", accessionCount))
# Visit each pVOG and find the fasta sequence that corresponds to each member accession
# Modify the header of each identified fasta to reflect its membership in the pVOG cluster
if CHATTY:
print("Searching sequences for each pVOG-associated accession")
# Create a fasta object (to be replicated as needed)
nextFasta = dbPrep_fastaSequence.fasta()
# For each pVOG, get its associated peptide accessions, then
# Find that fasta in the ncbi database subset, and
# Tag the fasta header with the pVOG information
accnCount = 0
for pVOG in pVOGdb.pVOGlist:
foundCount = 0
missingCount = 0
missingList = []
for accession in pVOG.accessionList: # For each accession (approx 200k of them, members of pVOG groups)
accnCount += 1
if CHATTY:
print("Processing pVOG", pVOG.pVOGid, "and accession", accession)
LOG_H.write(
"%s%s%s%s\n" %
import timeit
import datetime
import dbPrep_fastaSequence
#DEBUG = True
DEBUG = False
VERBOSE = False
if "dbPrep_VERBOSE" in os.environ.keys():
if os.environ["dbPrep_VERBOSE"] == 'True':
VERBOSE = True
DO_GENE = True
DO_PROTEIN = True
fastaObj = dbPrep_fastaSequence.fasta()
class VOG(object):
def __init__(self):
self.VOGid = '' # e.g., VOG0334
self.VOGannotation = ''
self.accnList = [] # list of accession numbers
self.geneCount = 0
self.peptideCount = 0 # ??? are these different?
def printAll(self):
print("VOG identifier:", self.VOGid)
print("VOG annotation:", self.VOGannotation)
print("accnList:", self.accnList)
print("geneCount:", self.geneCount)