def start_app_from_args(args):
global homDB
global genomDB
global xrefDB
global opDB
global sorfDB
global pfamDB
global tssDB
global tmpfolder
global clustalobin
tmpfolder = args.tmp
clustalobin = args.clustalo.name
homDB = HomologyDatabase.loadFromFile(args.databases + "/homdb/" +
"/hpdb_full_new")
xrefDB = XRefDatabase(gobo=args.databases + "/obos/go.obo",
fileName=args.databases + "/homdb/" +
"/hpdb_full_xref")
opDB = OperonDB.from_cs_operons(args.databases + "/sharma/operons.xlsx")
tssDB = TSSDB.from_cs_tss(args.databases + "/sharma/tss.xlsx")
sorfDB = SORFDB.from_cs_sorfs(args.databases + "/sharma/sorfs.xlsx")
pfamDB = PfamResultDB.from_folder(args.databases + "/pfam/")
genomDB = GenomeDB(args.genomes, loadAll=False)
for orgname in homDB.get_all_organisms():
genomDB.loadGenome(orgname)
if printAlignment:
print(orgJT[1])
#print("WL Changes", orgIT, orgJT, orgSubMatrix[('L', 'W')])
#print(alignment[0])
#print(alignment[1])
for x in orgSubMatrix:
orgSubMatRel[x] = orgSubMatrix[x] / aaLength
print("W content")
for org in orgAACounts:
print(org, "W", orgAACounts[org]['W'])
return orgSubMatrix, orgSubMatRel, aaLength, orgSubMatrixDir
hpHomolDB = HomologyDatabase.loadFromFile(fileLocation + "/hpp12_hp")
cbHomolDB = HomologyDatabase.loadFromFile(fileLocation + "../cbdb/" +
"/cbj")
genomeDB = GenomeDB(fileLocation + "/genomes/")
genomeDB.loadGenome(fileLocation + "/genomes/CP001217.gb")
genomeDB.loadGenome(fileLocation + "/genomes/AE000511.gb")
genomeDB.fileExtension = '.gbff'
genomeDB.fileFormat = 'gb'
genomeDB.loadGenome(fileLocation + "../cbdb/genomes/NC003912.gbff")
genomeDB.loadGenome(fileLocation + "../cbdb/genomes/NC002163.gbff")
matrix = matlist.blosum80
import glob
import os
from Bio import SeqIO
from Bio.SeqRecord import SeqRecord
from database.genomedb import GenomeDB
from database.homDBAnalyser import HomDBAnalyser
from database.homologydb import HomologyDatabase
if __name__ == '__main__':
baseDIR = '/mnt/c/dev/data/haas/homdb/'
homDB = HomologyDatabase.loadFromFile(baseDIR + "/hpp_split")
homs = ['HOMID1448', 'HOMID1742', 'HOMID1692', 'HOMID1795', 'HOMID2024', 'HOMID2027', 'HOMID1621', 'HOMID1338', 'HOMID1672', 'HOMID1693']
homs = ['HOMID1286']
homs = ['HOMID933', 'HOMID1354', 'HOMID1792', 'HOMID1621', 'HOMID1165', 'HOMID2171', 'HOMID283']
homs = ['HOMID933', 'HOMID1354']
homs = ['sp_HOMID2426', 'sp_HOMID2488']
homs = ['HOMID403', 'HOMID1649', 'HOMID981', 'HOMID607', 'HOMID346']
promLen = 50
for homid in homs:
alignSeqs = []
import editdistance
from database.genomedb import GenomeDB
from database.homologydb import HomologyDatabase
if __name__ == '__main__':
genomeLocation = '/home/users/joppich/ownCloud/data/hpyloriDB/genomes/'
homDB = HomologyDatabase.loadFromFile(
"/home/proj/projekte/dataintegration/hpyloriDB/hpp12.homdb")
genDB = GenomeDB(genomeLocation)
for homGroup in homDB.homologies:
entries = homDB.homologies[homGroup]
allSeqs = []
for seqID in entries:
if not seqID[0] in genDB.genomes:
genDB.loadGenome(genomeLocation + "/" + seqID[0] + ".gb")
seq = genDB.get_sequence(seqID[0], seqID[1])
allSeqs.append(seq)
if len(allSeqs) == 0:
continue
def distance(r1, r2):
# sort the two ranges such that the range with smaller first element
# is assigned to x and the bigger one is assigned to y
x, y = sorted((r1, r2))
if x[0] <= x[1] < y[0] and all(y[0] <= y[1] for y in (r1, r2)):
return y[0] - x[1]
return 0
if __name__ == '__main__':
fileLocation = "/mnt/c/dev/data/haas/homdb/"
homDB = HomologyDatabase.loadFromFile(fileLocation + "/hpp_split")
genomDB = GenomeDB(fileLocation + "/genomes", loadAll=False)
allorgs = homDB.get_all_organisms()
for org in allorgs:
genomDB.loadGenome(org)
extra = ['AE001439', 'CP009259']
mc = [
'4_N1-031C1', '2_N1-025A2', '14_1-20A_UB64', '13_N5-004A1',
'3_N1-029C1', '11_N4-029C2', '10_N2-085C2', '1_N1-024A1'
]
nmc = [
x for x in allorgs
if not x in mc and not x in extra and not x.startswith("6_")
for homID in interestHomCluster:
val = homDB.get_homology_cluster(homID)
mcc = sum([1 for x in val if x in mc])
nmcc = sum([1 for x in val if x in nmc])
print(homID, "MC", mcc, "NMC", nmcc)
print([int(x.replace('HOMID', '')) for x in interestHomCluster])
if __name__ == '__main__':
fileLocation = "/mnt/c/dev/data/haas/homdb/"
homDB = HomologyDatabase.loadFromFile(fileLocation + "/combed")
genomDB = GenomeDB(fileLocation + "/genomes", loadAll=False)
"""
for combid in homDB.combinations:
elems = homDB.combinations[combid]
homDB.homologies[combid] = elems
homDB.finalize()
homDB.save_to_file(fileLocation + "combed")
"""
for orgname in homDB.get_all_organisms():
genomDB.loadGenome(orgname)
allorgs = list(homDB.get_all_organisms())
import sys
import os
from collections import defaultdict
sys.path.insert(0, str(os.path.dirname(os.path.realpath(__file__))) + "/../")
import math
from database.genomedb import GenomeDB
from database.homologydb import HomologyDatabase
from utils.utils import fileLocation
if __name__ == '__main__':
homolDB = HomologyDatabase.loadFromFile(fileLocation + "/hpp12_hp")
genomeDB = GenomeDB(fileLocation + "/genomes/")
allowedOrgs = ['CP001217', 'AE000511']
compareAA = (['W'], ['F', 'G', 'A'])
compareAA = (['W'], ['H', 'F', 'Y', 'P', 'K'])
#compareAA = (['W', 'M'], ['H', 'F', 'Y', 'P', 'K'])
#compareAA = (['W', 'M'], ['F', 'G', 'A'])
def calculateDifferences(orgI, orgJ, allAA):
allDiffs = list()
foundGenes = 0
'--output',
type=argparse.FileType('w'),
help='input',
required=True)
parser.add_argument('--redo',
action='store_true',
help='input',
default=False)
restrictOrgs = ['AE001439', 'AE000511', 'CP001217']
restrictOrgs = None
args = parser.parse_args()
print("Loading Hom DB")
homDB = HomologyDatabase.loadFromFile(args.location.name)
print("Loading Genomes")
genomDB = GenomeDB(os.path.dirname(args.location.name) + "/genomes",
loadAll=False)
allorgs = homDB.get_all_organisms()
if restrictOrgs:
allorgs = restrictOrgs
for org in allorgs:
genomDB.loadGenome(org)
print("Loading HomDB analyser")
analyse = HomDBAnalyser(homDB, genomDB, loadAll=False)
from database.genomedb import GenomeDB
from database.homDBAnalyser import HomDBAnalyser
from database.homologydb import HomologyDatabase
if __name__ == '__main__':
baseDIR = '/mnt/c/dev/data/haas/homdb/'
genomeDB = GenomeDB(baseDIR + "/genomes", loadAll=False)
homDB = HomologyDatabase.loadFromFile(baseDIR + "/hpp_comb")
analyse = HomDBAnalyser(homDB, genomeDB)
def printHOM(homid):
print(homid)
aligned = analyse.cluster_align('HOMID'+str(homid))
longest = ""
allseqs = set()
for rec in sorted(aligned._records, key=lambda x: x.id):
seq = str(rec.seq).replace('-', '')
allseqs.add((seq, rec.id))
if len(seq) > len(longest):
longest = str(rec.seq).replace('-', '')
print(rec.seq, rec.id)
return ('HOMID'+str(homid), longest, set(allseqs))
from database.homologydb import HomologyDatabase
from utils.utils import fileLocation
from xrefs.GeneIdentity import GeneIdentity
from xrefs.uniprotStore import UniprotStore
hpHomolDB = HomologyDatabase.loadFromFile(fileLocation + "/hpdb_full")
allIDS = []
for org in hpHomolDB.get_all_organisms():
allOrgElems = hpHomolDB.get_organism_elements(org)
for x in allOrgElems:
allIDS.append(x)
print("Fetching information for", len(allIDS), "gene ids")
finalDF = None
chunksize = 1000
for i in range(0, len(allIDS), chunksize):
imax = min([i + chunksize, len(allIDS)])
chunkElems = allIDS[i:imax]
print(i, imax, len(chunkElems))
up = UniprotStore()
allConvertedIDs = up.fetch(GeneIdentity.GENE_NAME,