records = list()
for i, k in enumerate(taxID):
try:
handle = Entrez.efetch(db="taxonomy", id=k, retmode="xml")
temp_rec = Entrez.read(handle)
handle.close()
records.append(temp_rec[0])
print("%s" % (temp_rec[0]['Lineage']))
print("%s" % (temp_rec[0]['ScientificName']))
except:
records.append('')
end = time.clock()
print("Look up for taxonomy information complete. Time: %f" %
(end - start))
# Write to the output fasta file.
s_records = list()
[hd, seqs] = sca.readAlg(options.Input_MSA)
f = open(options.output, 'w')
for i, k in enumerate(seqs):
try:
hdnew = hd[i] + '|' + records[i][
'ScientificName'] + '|' + ','.join(
records[i]['Lineage'].split(';'))
except:
hdnew = hd[i] + '| unknown '
print("Unable to add taxonomy information for seq: %s" % hd[i])
f.write('>%s\n' % hdnew)
f.write('%s\n' % k)
f.close()
if options.refseq is not None and options.refpos is None:
print_("Using reference sequence but no position list provided! Just numbering positions 1 to length(sequence)")
if options.pdbid is not None:
print_("And...ignoring the PDB file...")
options.pdbid = None
options.refpos = range(len(options.refseq)) + 1
if options.refseq is not None and options.refpos is not None:
print_("Using the reference sequence and position list...")
if options.pdbid is not None:
print_("And...ignoring the PDB file...")
options.pdbid = None
else:
i_ref = options.i_ref
# Read in initial alignment
headers_full, sequences_full = sca.readAlg(options.alignment)
print_('Loaded alignment of {:d} sequences, {:d} positions.'.format(len(headers_full), len(sequences_full[0])))
# Check the alignment and remove sequences containing non-standard amino acids
print_("Checking alignment for non-standard amino acids")
alg_out = list()
hd_out = list()
for i, k in enumerate(sequences_full):
flag = 0
for aa in k:
if aa not in 'ACDEFGHIKLMNPQRSTVWY-':
flag = 1
if (flag == 0):
alg_out.append(k)
hd_out.append(headers_full[i])
headers_full = hd_out
)
if options.pdbid is not None:
print("And...ignoring the PDB file...")
options.pdbid = None
options.refpos = range(len(options.refseq)) + 1
if options.refseq is not None and options.refpos is not None:
print("Using the reference sequence and position list...")
if options.pdbid is not None:
print("And...ignoring the PDB file...")
options.pdbid = None
else:
i_ref = options.i_ref
# Read in initial alignment
headers_full, sequences_full = sca.readAlg(options.alignment)
print('Loaded alignment of %i sequences, %i positions.' %
(len(headers_full), len(sequences_full[0])))
# Check the alignment and remove sequences containing non-standard amino acids
print("Checking alignment for non-standard amino acids")
alg_out = list()
hd_out = list()
for i, k in enumerate(sequences_full):
flag = 0
for aa in k:
if aa not in 'ACDEFGHIKLMNPQRSTVWY-':
flag = 1
if (flag == 0):
alg_out.append(k)
hd_out.append(headers_full[i])
"-t",
"--tolerance",
dest="tol",
type=int,
default=50,
help=
"allowable sequence length variation in number of amino acids (alignment will be trimmed to mean +/- tolerance, default = 50)"
)
parser.add_argument("--output",
dest="outputfile",
default='FilteredAln.fa',
help="specify an outputfile name")
options = parser.parse_args()
headers, seqs = sca.readAlg(options.alignment)
seqLen = np.zeros((len(seqs), 1)).astype(int)
for i, k in enumerate(seqs):
seqLen[i] = len(k)
avgLen = seqLen.mean()
print("Average sequence length: %i" % avgLen)
print("Min: %i, Max %i" % (seqLen.min(), seqLen.max()))
minsz = avgLen - options.tol
maxsz = avgLen + options.tol
print("Keeping sequences in the range: %i - %i" % (minsz, maxsz))
keepSeqs = list()
keepHeaders = list()
for i, k in enumerate(seqLen):
if (k > minsz) & (k < maxsz):
keepSeqs.append(seqs[i])
"""
import scaTools as sca
import numpy as np
import argparse
if __name__ =='__main__':
#parse inputs
parser = argparse.ArgumentParser()
parser.add_argument("alignment", help='Input Sequence Alignment')
parser.add_argument("-t","--tolerance", dest = "tol", type = int, default = 50, help="allowable sequence length variation in number of amino acids (alignment will be trimmed to mean +/- tolerance, default = 50)")
parser.add_argument("--output", dest="outputfile", default = 'FilteredAln.fa', help="specify an outputfile name")
options = parser.parse_args()
headers, seqs = sca.readAlg(options.alignment)
seqLen = np.zeros((len(seqs),1)).astype(int)
for i,k in enumerate(seqs):
seqLen[i] = len(k)
avgLen = seqLen.mean()
print ("Average sequence length: %i" % avgLen)
print ("Min: %i, Max %i" % (seqLen.min(), seqLen.max()))
minsz = avgLen - options.tol;
maxsz = avgLen + options.tol;
print ("Keeping sequences in the range: %i - %i" % (minsz, maxsz))
keepSeqs = list()
keepHeaders = list()
for i,k in enumerate(seqLen):
if (k > minsz) & (k < maxsz):
keepSeqs.append(seqs[i])
# Collect records with lineage information
print_("Collecting taxonomy information...")
start = time.clock()
records = list()
for i, k in enumerate(taxID):
try:
handle = Entrez.efetch(db="taxonomy", id=k, retmode="xml")
temp_rec = Entrez.read(handle)
handle.close()
records.append(temp_rec[0])
print_("{}".format(temp_rec[0]['Lineage']))
print_("{}".format(temp_rec[0]['ScientificName']))
except:
records.append('')
end = time.clock()
print_("Look up for taxonomy information complete. Time: {}".format(end - start))
# Write to the output fasta file.
s_records = list()
[hd, seqs] = sca.readAlg(options.Input_MSA)
with open(options.output, 'w') as f:
for i, k in enumerate(seqs):
try:
hdnew = hd[i] + '|' + records[i]['ScientificName'] + '|' + ','.join(records[i]['Lineage'].split(';'))
except:
hdnew = hd[i] + '| unknown '
print_("Unable to add taxonomy information for seq: {}".formathd[i])
print_('>{}'.format(hdnew, file=f))
print_('{}'.format(k, file=f))
import scaTools as sca
import argparse
if __name__ =='__main__':
#parse inputs
parser = argparse.ArgumentParser()
parser.add_argument("alignment_for_headers", help='Alignment that is providing the headers')
parser.add_argument("alignment_for_seqs", help ='ALignment that is providing the sequences')
parser.add_argument("--output", dest="outputfile", default = 'FixedHeaders.fa', help="specify an outputfile name")
options = parser.parse_args()
print ("WARNING: This script assumes that the headers of the two input fasta files are in IDENTICAL order. If this is NOT true, the script will give incorrect results");
headers1, seqs1 = sca.readAlg(options.alignment_for_headers)
headers2, seqs2 = sca.readAlg(options.alignment_for_seqs)
if (len(seqs2) != len(headers1)):
print ("ERROR: The length of the two alignments does not match.")
exit
f = open(options.outputfile, 'w')
for i,k in enumerate(headers1):
f.write('>%s\n' % k)
f.write('%s\n' % seqs2[i])
f.close()
from scipy.io import savemat
if __name__ =='__main__':
#parse inputs
parser = argparse.ArgumentParser()
parser = argparse.ArgumentParser()
parser.add_argument("alignment", help='Input Sequence Alignment')
parser.add_argument("-o","--refpos", dest = "refpos", help="reference positions, supplied as a text file with one position specified per line")
parser.add_argument("-i","--refindex", dest = "i_ref", type = int, help="reference sequence number in the alignment, COUNTING FROM 0")
parser.add_argument("--output", dest="outputfile", default = None, help="specify an outputfile name")
options = parser.parse_args()
# Read in initial alignment
headers_full, sequences_full = sca.readAlg(options.alignment)
print('Loaded alignment of %i sequences, %i positions.' % (len(headers_full), len(sequences_full[0])))
# Create the ATS
i_ref = options.i_ref
print "Reference sequence %i:" % (i_ref)
print headers_full[i_ref]
s_tmp = sequences_full[i_ref]
try:
f = open(options.refpos,'r')
ats_tmp = [line.rstrip('\n') for line in f]
print ats_tmp
f.close()
except:
sys.exit("Error!! Unable to read reference positions!")
