print()
"You have listed", len(seqList), "sequences. They are:"
print(sequences + "\n")
seqRecords = getSeqRecords(
seqList) # Acquires list of sequence record objects from NCBI using the sequence list as reference.
No16sGenomes = []
SixTeens = []
for sequence in seqRecords:
sequenceID = sequence.id
No16s = True
if "plasmid" in sequence.description.lower(): # If sequence is from a plasmid skip the iteration.
continue
if isSSProject(sequence): # If accession is a WGSS project...
contigList = extractContigs(sequence.id) # Extract all contig accessions.
contigRecords = getSeqRecords(contigList) # Extract sequence record object for each contig.
for contig in contigRecords:
fasta = get16sFasta(sequenceID, contig) # Builds list fasta files.
if fasta: # If 16S is found.
No16s = False
SixTeens.append(fasta[0])
break # If 16S is found in one contig break out and skip all the other contigs
else: # If accession is a regular genome...
fasta = get16sFasta(sequenceID, sequence) # Builds list fasta files.
if fasta:
No16s = False
SixTeens.append(fasta[0])
if No16s: # If not 16S is found add genome to the no 16s found list.
No16sGenomeInfo = [sequenceID, sequence.annotations["organism"]]
print(sequences + "\n\n")
seqRecords = getSeqRecords(
seqList
) # Gets sequence record objects from NCBI using the sequence list as reference.
for sequence in seqRecords:
outFile = sequence.id + ".fna"
try:
# Attempted to create to output file.
writeFile = open(outFile, "w")
print("Writing " + outFile + " to file...")
# Checks if the accession leads to a WGSS project.
# If accession is a WGSS project...
if isSSProject(sequence):
contigList = extractContigs(
sequence.id) # Extract all contig accessions.
contigRecords = getSeqRecords(
contigList) # Extract sequence record object for each contig.
for contig in contigRecords:
writeFile.write(
contig.format("fasta")
) # Write each contig to the same file in fasta format.
# If accession is a regular genome...
else:
writeFile.write(
sequence.format("fasta")) # Write genome as fasta to file
writeFile.close()
except IOError:
print("Failed to create " + outFile)
seqRecords = getSeqRecords(seqList) # Gets sequence record objects from NCBI using the sequence list as reference.
for sequence in seqRecords:
outFile = sequence.id + ".faa"
outCSV = sequence.id + ".csv"
try:
# Attempted to create to output file.
writeFile = open(outFile, "w")
print "Writing " + outFile + " to file..."
csvFile = open(outCSV, "w")
CSVWriter = csv.writer(csvFile)
print "Writing " + outCSV + " to file..."
# Checks if the accession leads to a WGSS project.
# If accession is a WGSS project...
if isSSProject(sequence):
contigList = extractContigs(sequence.id) # Extract all contig accessions.
contigRecords = getSeqRecords(contigList) # Extract sequence record object for each contig.
for contig in contigRecords:
fasta = getProtienAnnotationFasta(contig) # Builds list fasta files.
csvRows = getProtienAnnotationCSV(contig) # Builds list of csv rows.
for annotation in fasta:
writeFile.write(annotation)
for row in csvRows:
CSVWriter.writerow(row)
# If accession is a regular genome...
else:
OrganismGenomeLength = len(sequence.seq) # Gets Genome Length
fasta = getProtienAnnotationFasta(sequence) # Builds list fasta files.
csvRows = getProtienAnnotationCSV(sequence) # Builds list of csv rows.
for annotation in fasta:
"You have listed", len(seqList), "sequences. They are:"
print(sequences + "\n")
seqRecords = getSeqRecords(
seqList
) # Acquires list of sequence record objects from NCBI using the sequence list as reference.
No16sGenomes = []
SixTeens = []
for sequence in seqRecords:
sequenceID = sequence.id
No16s = True
if "plasmid" in sequence.description.lower(
): # If sequence is from a plasmid skip the iteration.
continue
if isSSProject(sequence): # If accession is a WGSS project...
contigList = extractContigs(
sequence.id) # Extract all contig accessions.
contigRecords = getSeqRecords(
contigList) # Extract sequence record object for each contig.
for contig in contigRecords:
fasta = get16sFasta(sequenceID, contig) # Builds list fasta files.
if fasta: # If 16S is found.
No16s = False
SixTeens.append(fasta[0])
break # If 16S is found in one contig break out and skip all the other contigs
else: # If accession is a regular genome...
fasta = get16sFasta(sequenceID, sequence) # Builds list fasta files.
if fasta:
No16s = False
SixTeens.append(fasta[0])
