def write_gbk_file(output_file_name, contig_dict, sample_name,
nucleotide_seq_dict, protein_seq_dict):
date = genbankDate()
output_file_name_tmp = output_file_name + ".tmp"
outputfile = open(output_file_name_tmp, 'w')
#print contig_dict
count = 0
outputStr = ""
for key in contig_dict:
first = True
if count % 10000 == 0:
#print "count " + str(count)
outputfile.write(outputStr)
outputStr = ""
count += 1
for attrib in contig_dict[key]:
id = attrib['id']
try:
protein_seq = protein_seq_dict[id]
except:
protein_seq = ""
None
definition = sample_name
accession = '.'
version = '.' + spaces(10) + "GI:."
dblink = sample_name
keywords = '.'
source = sample_name
organism = sample_name
if first:
first = False
try:
dna_seq = nucleotide_seq_dict[key]
dna_seq_formatted = format_sequence_origin(dna_seq)
dna_length = len(dna_seq)
sourceStr = "1.." + str(dna_length)
except:
dna_seq = ""
dna_seq_formatted = ""
dna_length = 0
sourceStr = "0..0"
outputStr += (
"LOCUS %-18s %4d bp DNA BCT %-11s\n"
% (key, dna_length, date))
outputStr += (wrap("DEFINITION ", 12, 74, definition) + '\n')
outputStr += (wrap("ACCESSION ", 12, 74, accession) + '\n')
outputStr += (wrap("VERSION ", 12, 74, version) + '\n')
outputStr += (wrap("DBLINK ", 12, 74, dblink) + '\n')
outputStr += (wrap("KEYWORDS ", 12, 74, keywords) + '\n')
outputStr += (wrap("SOURCE ", 12, 74, keywords) + '\n')
outputStr += (wrap(" ORGANISM ", 12, 74, organism) + '\n')
outputStr += (wrap("", 12, 74, "Metagenome") + '\n')
outputStr += (
wrap("REFERENCE ", 12, 74, "1 (bases 1 to XXXXX)") +
'\n')
outputStr += (wrap(" AUTHORS ", 12, 74, "YYYYYY,X.") + '\n')
outputStr += (wrap(" CONSRTM ", 12, 74, "XXXXX") + '\n')
outputStr += (wrap(" TITLE ", 12, 74, "XXXXX") + '\n')
outputStr += (wrap(" JOURNAL ", 12, 74, "XXXXX") + '\n')
outputStr += (wrap(" PUBMED ", 12, 74, "XXXXX") + '\n')
outputStr += (wrap(" REMARK ", 12, 74, "XXXXX") + '\n')
outputStr += (wrap(
"COMMENT ", 12, 74,
"PROVISIONAL REFSEQ: This record has not yet been subject to final NCBI review COMPLETENESS: XXXXX"
) + '\n')
outputStr += (
wrap("FEATURES ", 21, 74, "Location/Qualifiers") + '\n')
outputStr += (wrap(" source", 21, 74, sourceStr) + '\n')
outputStr += (
wrap("", 21, 74, "/organism=\"" + sourceStr + "\"") + '\n')
outputStr += (wrap("", 21, 74, "/strain=\"1\"") + '\n')
outputStr += (wrap("", 21, 74, "/chromosome=\"1\"") + '\n')
if 'start' in attrib and 'end' in attrib:
geneLoc = str(attrib['start']) + ".." + str(attrib['end'])
else:
geneLoc = "0..0"
if 'strand' in attrib:
if attrib['strand'] == '-':
geneLoc = 'complement' + '(' + geneLoc + ')'
outputStr += (wrap(" gene", 21, 74, geneLoc) + '\n')
if 'locus_tag' in attrib:
locus_tag = "/locus_tag=" + "\"" + attrib['locus_tag'] + "\""
else:
locus_tag = "/locus_tag" + "\"\""
outputStr += (wrap("", 21, 74, locus_tag) + '\n')
outputStr += (wrap(" CDS", 21, 74, geneLoc) + '\n')
if 'product' in attrib:
product = "/product=" + attrib['product']
else:
product = "/product=\"\""
outputStr += (wrap("", 21, 74, product) + '\n')
outputStr += (wrap("", 21, 74, locus_tag) + '\n')
codon_start = "/codon_start=1"
translation_table = "/transl_table=11"
outputStr += (wrap("", 21, 74, codon_start) + '\n')
outputStr += (wrap("", 21, 74, translation_table) + '\n')
translation = "/translation=" + protein_seq
outputStr += (wrap("", 21, 74, translation) + '\n')
outputStr += (wrap("ORIGIN", 21, 74, "") + '\n')
outputStr += (dna_seq_formatted + '\n')
outputStr += ("//\n")
outputfile.write(outputStr)
outputfile.close()
rename(output_file_name_tmp, output_file_name)
def writeGbkFile(output_file_name, contig_dict, sample_name, nucleotide_seq_dict, protein_seq_dict):
"""This function creates the genbank file from the gff, protein and nucleotide sequences."""
date = genbankDate()
output_file_name_tmp = output_file_name + ".tmp"
outputfile = open(output_file_name_tmp, 'w')
count = 0
outputStr = ""
for key in contig_dict:
first = True
if count % 10000 == 0:
outputfile.write(outputStr)
outputStr = ""
count+=1
for attrib in contig_dict[key]:
id = attrib['id']
try:
protein_seq = protein_seq_dict[id]
except:
protein_seq = ""
definition = sample_name
accession = '.'
version = '.' + " "*10 + "GI:."
dblink = sample_name
keywords = '.'
source = sample_name
organism = sample_name
dna_seq_formatted = ""
if first:
first = False
try:
dna_seq = nucleotide_seq_dict[key]
dna_seq_formatted = formatSequenceOrigin(dna_seq)
dna_length = len(dna_seq)
sourceStr = "1.." + str(dna_length)
except:
dna_seq = ""
dna_seq_formatted = ""
dna_length = 0
sourceStr = "0..0"
outputStr+=("LOCUS %-18s %4d bp DNA BCT %-11s\n" % (key, dna_length, date))
outputStr+=(wrap("DEFINITION ",12,74, definition)+'\n')
outputStr+=(wrap("ACCESSION ", 12, 74, accession)+'\n')
outputStr+=(wrap("VERSION ", 12, 74, version)+'\n')
outputStr+=(wrap("DBLINK ", 12, 74, dblink)+'\n')
outputStr+=(wrap("KEYWORDS ", 12, 74,keywords)+'\n')
outputStr+=(wrap("SOURCE ", 12, 74, keywords)+'\n')
outputStr+=(wrap(" ORGANISM ",12, 74, organism)+'\n')
outputStr+=(wrap("", 12, 74, "Metagenome")+'\n')
outputStr+=( wrap("REFERENCE ",12,74, "1 (bases 1 to XXXXX)")+'\n')
outputStr+=( wrap(" AUTHORS ",12,74, "YYYYYY,X.")+'\n')
outputStr+=( wrap(" CONSRTM ",12,74, "XXXXX")+'\n')
outputStr+=( wrap(" TITLE ",12,74, "XXXXX")+'\n')
outputStr+=( wrap(" JOURNAL ",12,74,"XXXXX")+'\n')
outputStr+=( wrap(" PUBMED ",12,74,"XXXXX")+'\n')
outputStr+=( wrap(" REMARK ",12,74, "XXXXX")+'\n')
outputStr+=( wrap("COMMENT ", 12, 74,"PROVISIONAL REFSEQ: This record has not yet been subject to final NCBI review COMPLETENESS: XXXXX")+'\n')
outputStr+=( wrap("FEATURES ",21,74,"Location/Qualifiers") +'\n')
outputStr+=( wrap(" source",21,74,sourceStr) +'\n')
outputStr+=( wrap("",21,74,"/organism=\"" + sourceStr +"\"") +'\n')
outputStr+=( wrap("",21,74,"/strain=\"1\"")+'\n')
outputStr+=( wrap("",21,74,"/chromosome=\"1\"") +'\n')
if 'start' in attrib and 'end' in attrib:
geneLoc = str(attrib['start']) +".." + str(attrib['end'])
else:
geneLoc = "0..0"
if 'strand' in attrib:
if attrib['strand']=='-':
geneLoc='complement' + '(' + geneLoc +')'
outputStr+=( wrap(" gene",21,74,geneLoc) +'\n')
if 'locus_tag' in attrib:
locus_tag = "/locus_tag=" + "\"" + attrib['locus_tag'] + "\""
else:
locus_tag = "/locus_tag" + "\"\""
outputStr+=( wrap("",21,74,locus_tag) +'\n')
outputStr+=( wrap(" CDS",21,74,geneLoc) +'\n')
if 'product' in attrib:
product="/product=" + attrib['product']
else:
product="/product=\"\""
outputStr+=( wrap("",21,74,product) +'\n')
outputStr+=( wrap("",21,74,locus_tag) +'\n')
codon_start="/codon_start=1"
translation_table="/transl_table=11"
outputStr+=( wrap("",21,74,codon_start) +'\n')
outputStr+=( wrap("",21,74,translation_table) +'\n')
translation= "/translation="+ protein_seq
outputStr+=( wrap("",21,74,translation) +'\n')
outputStr+=(wrap("ORIGIN", 21, 74, "")+'\n')
outputStr+=(dna_seq_formatted +'\n')
outputStr+=("//\n")
outputfile.write(outputStr)
outputfile.close()
rename(output_file_name_tmp, output_file_name)