def test_AlignmentArray():
F = UtilityFunctions.FastaToDict("tests/test_fasta.fasta")
ali = UtilityFunctions.AlignmentArray(F.values())
comp = [['A', 'C', 'G', 'T', 'T', "-"], ['A', 'A', 'C', 'T'],
['C', 'T', 'A', 'G']]
comp = np.array(comp)
assert np.array_equal(comp, ali)
def test_reverseComplementAlignment():
F = UtilityFunctions.FastaToDict("tests/test_data/test_fasta.fasta")
ali = UtilityFunctions.AlignmentArray(F.values())
rcomp = [['-', 'A', 'A', 'C', 'G', 'T'], ['A', 'G', 'T', 'T'],
['C', 'T', 'A', 'G']]
rcomp = np.array(rcomp)
assert np.array_equal(UtilityFunctions.reverseComplementAlignment(ali),
rcomp)
def alignWithRef(currentD, reference_dict, pD, outdir):
for i in currentD:
query_seq = currentD[i]['consensus']
query_ali = currentD[i]['alignment']
query_names = currentD[i]['names']
q_matrix, nt_inds = Consensus.makeAlignmentMatrix(query_ali)
candidates = UtilityFunctions.FastaToDict(reference_dict)
for target_nam, target_seq in candidates.items():
qm = copy.copy(q_matrix)
target_ali = UtilityFunctions.AlignmentArray([target_seq])
# Align the query and target consensus sequences
result = Alignment.SWalign(query_seq, target_seq,
pD, useSub=True)
# Check the if the consensus sequences are a good match
is_match = Alignment.alignmentMeetsCriteria(result, query_seq,
target_seq, pD)
if is_match[0]:
result['alignment'] = is_match[1]
# get the full alignment for the two consensus sequences
result = Alignment.getAlignmentFull(result,
query_seq,
target_seq,
pD)
ali, matrix = Consensus.expandAlignment(result,
query_ali,
target_ali,
qm,
nt_inds)
cons = Consensus.collapseAlignment(matrix, nt_inds)
names = query_names + [target_nam]
result2 = Alignment.SWalign(query_seq, cons, pD, useSub=True)
is_match_2 = Alignment.alignmentMeetsCriteria(result2,
query_seq,
cons,
pD)
result2['alignment'] = is_match_2[1]
result2 = Alignment.getAlignmentFull(result2,
query_seq,
cons,
pD)
a2 = UtilityFunctions.AlignmentArray([query_seq])
ali, matrix = Consensus.expandAlignment(result2,
a2,
ali,
qm,
nt_inds)
names = ["*consensus_%s" % i] + names
path = "%s/final_clusters/consensus_%s_to_%s_ali.fasta" % (
outdir, i, target_nam.split(" ")[0])
out = open(path, "w")
for j, nam in enumerate(names):
out.write(">%s\n%s\n" % (nam,
"".join(list(ali[j]))))
out.close()
def main():
parser = configargparse.ArgumentParser(
description='''Compare two sequences and calculate the % identity''')
parser.add("--consensus",
dest="consensus",
type=str,
help="path to consensus sequence fasta file")
parser.add("--original",
dest="original",
type=str,
help="path to original input file")
parser.add("--orig_name",
dest="orig_name",
type=str,
help="original sequence name")
parser.add("--gap_open",
dest="alignment_gap_open",
type=int,
help="gap opening penalty",
default=5)
parser.add("--gap_extend",
dest="alignment_gap_extend",
type=int,
help="gap extension penalty",
default=2)
parser.add("--match_score",
dest="alignment_match_score",
type=int,
help="score for each match in SW algorithm",
default=5)
parser.add("--mismatch_score",
dest="alignment_mismatch_score",
type=int,
help="penalty for each mismatch in SW algorithm",
default=-4)
args = parser.parse_args()
consD = UtilityFunctions.FastaToDict(args.consensus)
origD = UtilityFunctions.FastaToDict(args.original)
cons_seq_f = list(consD.values())[0]
cons_seq_f = cons_seq_f.upper()
cons_seq_r = UtilityFunctions.reverseComplement(cons_seq_f)
orig_seq = origD[args.orig_name]
orig_seq = orig_seq.upper()
pD = {
'alignment_gap_open': args.alignment_gap_open,
'alignment_gap_extend': args.alignment_gap_extend,
'alignment_match_score': args.alignment_match_score,
'alignment_mismatch_score': args.alignment_mismatch_score
}
ali_f = Alignment.SWalign(cons_seq_f, orig_seq, pD)
ali_r = Alignment.SWalign(cons_seq_r, orig_seq, pD)
if ali_f['optimal_alignment_score'] > ali_r['optimal_alignment_score']:
ali = ali_f
cons_seq = cons_seq_f
else:
ali = ali_r
cons_seq = cons_seq_r
q, t, ident = Alignment.getAlignmentLocal(ali, cons_seq, orig_seq, pD)
cons_length = len(cons_seq)
orig_length = len(orig_seq)
cons_perc_aligned = (ali['query_end'] - ali['query_start']) / cons_length
orig_perc_aligned = (ali['target_end'] - ali['target_start']) / orig_length
print(ident, cons_perc_aligned, orig_perc_aligned)
def runCandidates(Z, fasta_dict, seqdict, candfile, pD, outdir, rround,
currentD=None):
'''
Allows the user to specify a set of reference sequences - in the first
round of clustering, only contigs which align to these references
(meeting the same minimum criteria as for normal clustering) are
selected. In the second round, the fragments identified in the query
file which matched the reference sequence are used to identify
further fragments. From this point clustering of consensus
sequences continues as normal.
Parameters
----------
Z: list
List of two item tuples where the first element is an integer and
the second the sequence name for all sequences in the main input file
fasta_dict: pyfaidx.Fasta
pyfaidx indexed Fasta object containing the main input file of contigs
seqdict: dict
A dictionary where keys are sequence IDs and values are empty
dictionaries - these are used to store CIAlign logs for sequences
later but it is not run at this stage when candidate sequences are
used
candfile: str
Path to a file containing the reference sequences to match the contigs
to in the first round of clustering
pD: dict
Dictionary containing the initial parameters set by the user
outdir: str
Path to directory in which to save all output files
rround: int
Round number - which round of clustering is this - used to
determine where to save the output
currentD: dict
Dictionary containing the results of previous rounds of clustering
used in this case to expand consensus sequences from round 1
Returns
-------
D: dict
Updated version of currentD containing the results of this
round of clustering
'''
X = copy.copy(Z)
candidates = UtilityFunctions.FastaToDict(candfile)
D = dict()
k = 0
# iterate through the reference sequences
for c_nam, c_seq in candidates.items():
current = dict()
# store candidate name and sequence in the results dictionary
current['name'] = c_nam
current['consensus'] = c_seq
if rround == 1:
# in the first round, none of the input sequences are
# consensus sequences
current['alignment'] = UtilityFunctions.AlignmentArray([c_seq])
current['seqdict'] = seqdict
current['names'] = [c_nam]
elif rround == 2:
# in the second round, expand the consensus sequences based
# on the output of the previous round
consn = int(c_nam.replace("*consensus_", ""))
current['alignment'] = currentD[consn]['alignment']
current['seqdict'] = currentD[consn]['seqdict']
current['names'] = currentD[consn]['names']
current['matrix'], current['nt_inds'] = Consensus.makeAlignmentMatrix(
current['alignment'])
k += 1
X, C = AlignmentSW.buildCluster(Z, fasta_dict, current, pD, k,
candidate=True, skip=True)
D.setdefault(k, dict())
D[k]['consensus'] = C['current_consensus']
D[k]['alignment'] = C['current_alignment']
D[k]['names'] = C['current_names']
D[k]['seqdict'] = C['seqdict']
Alignment.writeFastas(D[k], k, rround, outdir, candidates=True,
reference=candidates)
if rround == 2:
Alignment.mergeFastas(2, len(D), outdir)
return(D)
def main():
parser = configargparse.ArgumentParser(
description='''Generate pseudo fragmented transcripts with different \
degress of variation and insertions / deletions''')
parser.add_argument("--infile",
dest="infile",
type=str,
help="path to input fasta file")
parser.add_argument("--outfile",
dest="outfile",
type=str,
help="path to output fasta file")
parser.add_argument("--config",
dest="config",
type=str,
help='path to config file',
is_config_file=True)
parser.add_argument("--min_fragment_length",
dest="min_fragment_length",
type=int,
help="minimum fragment length")
parser.add_argument("--max_fragment_length",
dest="max_fragment_length",
type=int,
help="maximum fragment length")
parser.add_argument("--min_n_fragments",
dest="min_n_fragments",
type=int,
help="minimum number of fragments")
parser.add_argument("--max_n_fragments",
dest="max_n_fragments",
type=int,
help="maximum number of fragments")
parser.add_argument('--min_diversity',
dest='min_diversity',
type=float,
help='minimum proportion of diversity to introduce')
parser.add_argument('--max_diversity',
dest='max_diversity',
type=float,
help='maximum proportion of diversity to introduce')
parser.add_argument("--min_n_insertions",
dest='min_n_insertions',
type=int,
help="minimum number of insertions to introduce")
parser.add_argument("--max_n_insertions",
dest='max_n_insertions',
type=int,
help="maximum number of insertions to introduce")
parser.add_argument("--min_insertion_size",
dest="min_insertion_size",
type=int,
help='minimum size insertion to introduce')
parser.add_argument("--max_insertion_size",
dest="max_insertion_size",
type=int,
help='maximum size insertion to introduce')
parser.add_argument("--min_n_deletions",
dest='min_n_deletions',
type=int,
help="minimum number of deletions to introduce")
parser.add_argument("--max_n_deletions",
dest='max_n_deletions',
type=int,
help="maximum number of deletions to introduce")
parser.add_argument("--min_deletion_size",
dest="min_deletion_size",
type=int,
help='minimum size deletion to introduce')
parser.add_argument("--max_deletion_size",
dest="max_deletion_size",
type=int,
help='maximum size deletion to introduce')
args = parser.parse_args()
F = UtilityFunctions.FastaToDict(args.infile)
Fnew = dict()
for nam, seq in F.items():
freqs = getNucFreqs(seq)
fragments = chopSequence(seq, nam, args.min_n_fragments,
args.max_n_fragments,
args.min_fragment_length,
args.max_fragment_length)
for fnam, fragment in fragments.items():
fragment = addSNPs(fragment, freqs, args.min_diversity,
args.max_diversity)
fragment = addIndels(fragment,
freqs,
args.min_n_insertions,
args.max_n_insertions,
args.min_insertion_size,
args.max_insertion_size,
typ='insertion')
fragment = addIndels(fragment,
freqs,
args.min_n_deletions,
args.max_n_deletions,
args.min_deletion_size,
args.max_deletion_size,
typ='deletion')
rc = np.random.choice([True, False])
if rc:
fragment = UtilityFunctions.reverseComplement(fragment)
Fnew[fnam] = fragment
out = open(args.outfile, "w")
for key, val in Fnew.items():
out.write(">%s\n%s\n" % (key, val))
out.close()
def test_FastaToDict():
T = UtilityFunctions.FastaToDict("tests/test_fasta.fasta")
assert T == {"Seq_1": "ACGTT-", "Seq_2": "AACT", "Seq_3": "CTAG"}
