def getGeneData():
# Look for non-complements second arg in gb.GenLocs is False
path = 'bacteriaGB/Genbank/'
# lists for starts and nonStarts
startList = []
nonStartList = []
for filename in os.listdir(path):
#print(path + filename)
data,dna = readGenesIn(path+filename)
# Find the keyword locations and gene locations
klocs = gb.FindKeywordLocs ( data )
glocs = gb.GeneLocs ( data , klocs )
for start in glocs:
# check for valid gene
goodness,stNum,endNum = preCheck(start,dna)
if (goodness):
# Check that the complement is False aka a Non-Complement
isComp = start[1]
codon = dna[stNum:stNum+3]
if (not isComp and codon == 'atg'): # these are the START
startList.append(dna[stNum-30:stNum+23])
else: # This is NOT a START
nonStartList.append(dna[stNum-30:stNum+23])
return startList,nonStartList
def DumpSequences( gbname ):
data = gb.ReadFile( gbname )
klocs = gb.FindKeywordLocs(data)
N = len( klocs )
genes = []
for i in range( N ):
g = gb.Translation( data, klocs[i])
genes.append( g )
return genes
def FileReadConvert(fname, codkeys):
# fname is the name of a Genbank file
# codkeys is codons.keys( ) were codons is from genbank.Codons()
# read in the DNA sequences for the genes
data = genbank.ReadGenbank(fname)
dna = genbank.ParseDNA(data)
klocs = genbank.FindKeywordLocs(data)
glocs = genbank.GeneLocs(data, klocs)
NG = len(glocs) # number of genes
codons = []
for i in range(NG):
# extract DNA for this sequence
cdna = genbank.GetCodingDNA(dna, glocs[i])
# convert to codons
c = [] # codons for this gene
for j in range(0, len(cdna), 3):
c.append(codkeys.index(cdna[j:j + 3]))
codons.append(c)
return codons
def GetData(fn):
gb = genbank.ReadGenbank(fn)
dna = genbank.ParseDNA(gb)
klocs = genbank.FindKeywordLocs(gb)
genes = genbank.GeneLocs(gb, klocs)
return genes, dna