def fetch_restriction_sites(self, enzymes="Common"):
"""
Spike in target variant first, generate list
restriction enzymes that will work.
"""
if enzymes == "ALL":
enzyme_group = AllEnzymes
elif enzymes == "Common":
enzyme_group = CommOnly
elif enzymes == "HF":
enzyme_group = high_fidelity
else:
enzyme_group = RestrictionBatch(enzymes.split(","))
# Filter ambiguous cutters
enzyme_group = RestrictionBatch(
[x for x in enzyme_group if x.is_ambiguous() is False])
# Calculate rflps for ALT sites only
self.ref_sites = dict(list(enzyme_group.search(self.ref_seq).items()))
self.primary_variant_sites = dict(
list(enzyme_group.search(self.primary_variant_seq).items()))
self.rflps = {
k: (self.ref_sites[k], self.primary_variant_sites[k])
for k, v in list(self.ref_sites.items())
if len(v) > 0 and len(v) <= 3
and self.ref_sites[k] != self.primary_variant_sites[k]
}
def digest_genome(genome_fp, restriction_enzyme, output_dir, linear=False):
base_fp = os.path.basename(genome_fp)
if '.' in base_fp:
base_fp = '{}.{}.fragments.bed'.format(base_fp[:base_fp.rfind('.')],
restriction_enzyme)
else:
base_fp = '{}.{}.fragments.bed'.format(base_fp, restriction_enzyme)
base_fp = os.path.join(output_dir, base_fp)
if os.path.isfile(base_fp):
overwrite = input(
'WARNING: Overwriting existing fragment BED {}. Continue? [y/N]'.
format(base_fp))
if not overwrite.lower() == 'y':
print("Did not overwrite existing fragment BED.")
return
os.remove(base_fp)
print("Digesting")
genome = None
if "fasta" in genome_fp or "fa" in genome_fp:
genome = SeqIO.parse(open(genome_fp, "rU"), format='fasta')
else:
genome = SeqIO.parse(open(genome_fp, "rU"), format='genbank')
for chromosome in genome:
print('{}\t{}'.format(chromosome.id, len(chromosome.seq)))
# Digest the sequence data and return the cut points
enzyme = RestrictionBatch([restriction_enzyme])
for enzyme, cutpoints in enzyme.search(chromosome.seq,
linear=linear).items():
if len(cutpoints) == 0:
print('No restriction sites found for {}'.format(
chromosome.id))
continue
df = pd.DataFrame(cutpoints, columns=['cutpoint'])
df['end'] = df.cutpoint - 1
df['start'] = df.end - (df.cutpoint.diff())
df.loc[0, 'start'] = 0
df['start'] = df['start'].astype('Int64')
if len(df) > 1:
last_fragment = pd.DataFrame({
'start': [df.loc[len(df) - 1, 'end']],
'end': [len(chromosome.seq)],
'cutpoint': [-1]
})
df = df.append(last_fragment, ignore_index=True)
else:
df.loc[len(df) - 1, 'end'] = len(chromosome.seq)
df['frag_id'] = df.index
# chromosome has 'chr'
accession = chromosome.id
version = ''
if "." in chromosome.id:
accession, version = chromosome.id.split(".")
if not accession.startswith("chr"):
accession = "chr" + accession
df['chr'] = accession
df[['chr', 'start', 'end', 'frag_id']].to_csv(base_fp,
index=False,
sep='\t',
mode='a',
header=None)
def REsearch(goi='', goiFile='', mcs='', mcsFile=''):
rb = RestrictionBatch(suppliers=[
'C', 'B', 'E', 'I', 'K', 'J', 'M', 'O', 'N', 'Q', 'S', 'R', 'V', 'Y',
'X'
])
goi = Seq(goi, IUPACUnambiguousDNA()) if goi else read_seq(goiFile)
if not goi:
raise Exception('Please provide a GOI sequence!')
mcs = Seq(mcs, IUPACUnambiguousDNA()) if mcs else read_seq(mcsFile)
if not mcs:
raise Exception('Please provide a MCS sequence!')
result_mcs = rb.search(mcs)
result_goi = rb.search(goi)
REs = set([e for e in result_mcs.keys() if result_mcs[e]]) - set(
[e for e in result_goi.keys() if result_goi[e]])
# ana = Analysis(RestrictionBatch(list(REs)), mcs)
# REs_sorted = sorted(REs, key=lambda e: result_mcs[e])
# result = {e: result_mcs[e] for e in REs_sorted}
r = []
for e in REs:
for site in result_mcs[e]:
r.append((str(e), site, "blunt" if e.is_blunt() else e.elucidate(),
' '.join(e.suppl)))
r.sort(key=lambda i: i[1])
return r
def has_restriction_site(seq):
from Bio.Seq import Seq
from Bio.Restriction import RestrictionBatch
mix = RestrictionBatch(restriction_sites)
hits = mix.search(Seq(seq))
return any(hits.values())
def test_batch_analysis(self):
"""Sequence analysis with a restriction batch."""
seq = Seq("AAAA" + EcoRV.site + "AAAA" + EcoRI.site + "AAAA")
batch = RestrictionBatch([EcoRV, EcoRI])
hits = batch.search(seq)
self.assertEqual(hits[EcoRV], [8])
self.assertEqual(hits[EcoRI], [16])
def test_batch_analysis(self):
"""Sequence analysis with a restriction batch."""
seq = Seq("AAAA" + EcoRV.site + "AAAA" + EcoRI.site + "AAAA",
IUPACAmbiguousDNA())
batch = RestrictionBatch([EcoRV, EcoRI])
hits = batch.search(seq)
self.assertEqual(hits[EcoRV], [8])
self.assertEqual(hits[EcoRI], [16])
def re_sites(self, sequence):
seq = Seq(sequence, IUPACAmbiguousDNA)
# Set up analysis class with our enzymes and seq
rb = RestrictionBatch(self.enzyme_set)
# Do digest and reformat to dict of {site: enz, site:enz}
re_sites = {}
for enzyme, cutsites in rb.search(seq).items():
for cut in cutsites:
cut = cut + enzyme.fst3 - 1
re_sites[cut] = enzyme
return sorted(re_sites.items())
def restriction_sites_present(spacer: str, rsb: RestrictionBatch) -> List[int]:
"""Determine if and where a set of restriction sites are present in a
sequence\f
Parameters
----------
spacer : `str`
Spacer sequence to examine for restriction sites.
Returns
-------
:class:`typing.List`[`int`]
"""
sites = bool([_ for results in rsb.search(Seq(spacer)).values() for _ in results])
return sites
def calc_digest_products(seq, enzymes, *, is_circular):
from more_itertools import pairwise, flatten
from Bio.Restriction import RestrictionBatch
from Bio.Seq import Seq
if not enzymes:
raise UsageError("no enzymes specified", enzymes=enzymes)
enzymes = [re.sub('-HF(v2)?$', '', x) for x in enzymes]
try:
batch = RestrictionBatch(enzymes)
except ValueError:
raise ConfigError(
lambda e: f"unknown enzyme(s): {','.join(map(repr, e.enzymes))}",
enzymes=enzymes,
) from None
sites = [x - 1 for x in flatten(batch.search(Seq(seq)).values())]
if not sites:
raise ConfigError(
lambda e:
f"{','.join(map(repr, e.enzymes))} {plural(enzymes):/does/do} not cut template.",
enzymes=enzymes,
seq=seq,
)
sites += [] if is_circular else [0, len(seq)]
sites = sorted(sites)
seqs = []
for i, j in pairwise(sorted(sites)):
seqs.append(seq[i:j])
if is_circular:
wrap_around = seq[sites[-1]:] + seq[:sites[0]]
seqs.append(wrap_around)
return seqs
def find_spacers(target=None, outfile=None, refgenome=None, restriction_sites=[], largeIndex=False, cutoff=0,
offtargetcutoff=0, trim=False, logging=False, nuclease='Cas9', return_limit=9, reject=False):
with open(target, 'rU') as infile:
# Use our modified FastaIterator instead of, perhaps the more proper, SeqIO.parse() method
# allows us to trim the UTR sequences off
if trim:
# If the 'trim' option is enabled, the header for each entry must be
# GENEID | TRANSCRIPTID | EXON RANK | CONSTITUTIVE EXON | 5' UTR END | 3' UTR STOP | EXON START | EXON END
try:
itemiter = m_FastaIterator(infile)
except IOError as e:
print("I/O error({0}): {1}".format(e.errno, e.strerror))
else:
try:
itemiter = SeqIO.parse(infile, 'fasta')
except IOError as e:
print("I/O error({0}): {1}".format(e.errno, e.strerror))
itemlist = [temp for temp in itemiter]
spacerlist = []
# This will find our 20N-NGG target sequence plus the -4->-3 and +1->+3 nucleotides for scoring
if nuclease == 'Cas9':
PAM = r'(?i)[ACGT]{25}[G]{2}[ACGT]{3}'
elif nuclease == 'Cpf1':
PAM = r'(?i)[T]{2,}[A-Z]{25}'
rsb = RestrictionBatch(restriction_sites)
#spacerlist = map(lambda item: find_each_spacer(item, rsb, cutoff, PAM), itemlist)
seen = []
print("{} sequences to search for spacers.".format(len(itemlist)))
widgets = ['Examining sequence: ', progressbar.Counter(), ' ', progressbar.Percentage(), ' ',
progressbar.Bar(), progressbar.Timer()]
progress = progressbar.ProgressBar(widgets=widgets, maxval=len(itemlist)).start()
spacer_re = regex.compile(PAM)
#pol3stop = regex.compile(r'(?i)[T]{4,}')
for item in itemlist:
# Find all of the potential protospacer sequences, i.e. any 21 nucleotide sequence that precedes a double g
progress.update(itemlist.index(item)+1)
spacerMatch = (spacer_re.findall(str(item.seq), overlapped=True) +
spacer_re.findall(str(item.reverse_complement().seq), overlapped=True))
for ps in spacerMatch:
# Note that ps[4:24] is the actual protospacer. I need the rest of the sequence for scoring
ps_seq = Seq(ps[4:24], IUPAC.unambiguous_dna)
rs = rsb.search(ps_seq)
# on_target_score_calculator only works if the sequence is in uppercase
# otherwise, it returns a value of 0.193313360829 for some reason
score = calc_score(ps.upper())
# Get rid of anything with T(4+) as those act as RNAPIII terminators
#if bool(pol3stop.findall(ps[4:24])):
if "TTTT" in ps[4:24]:
# TODO Should this also eliminate anything with G(4)?
pass
# Get rid of anything that has the verboten restriction sites
elif bool([y for y in rs.values() if y != []]):
pass
# Eliminate potentials with a GC content <20 or >80%
elif GC(ps_seq) <= 20 or GC(ps_seq) >= 80:
pass
elif float(score) < cutoff:
# explicitly converting cutoff to a float because otherwise it 'sometimes' fails
# (epecially if you set cutoff to 0.5 on the commandline)
pass
# keep everthing else
else:
if ps[4:24] not in seen:
position = int(str(item.seq).find(ps)) + int(item.description.split("|")[7])
keys = ['description','position','score','spacer','offtargetscore','name']
values = [item.description, int(position), score, ps[4:24], 100]
# because of duplicated sequences or whatever, spacelist can end up with duplicate entries
# so let's take care of them
# For future!
#spacer = ProtoSpacer(description=item.description, position=int(position), score=score, spacerseq=ps[4:24], offtargetscore=100)
#if ps[4:24] not in seen:
# spacerset.update(spacer)
# seen.append(ps[4:24])
spacerlist.append(dict(zip(keys,values)))
seen.append(ps[4:24])
progress.finish()
if len(spacerlist) == 0:
print("Sorry, no spacers matching that criteria were found")
return 0
else:
print("Finished finding spacers. {} spacers found. Begining Bowtie alignment...".format(len(spacerlist)))
# write out a file to pass off to Bowtie to use for off-target analysis
with open('temp.fa', 'w') as tempfile:
for entry in spacerlist:
tempfile.writelines(">%s %s %s\n%s\n" % (entry['description'], entry['position'],
entry['score'], entry['spacer']))
# delete lists we are not going to use in the future to save on some memory
del(itemlist)
del(seen)
# Use Bowtie to find if this particular sequence has any potential off targets (i. e. two or fewer mismatches)
# As current, Bowtie is set to return all everything that a particular spacer matches within the reference genome
# with two or fewer mismatches.
# TODO switch to Bowtie2 so we can account for gaps in mismatches
# TODO can we modify this setup to account for NAG PAMs or do we even need to? (i. e. are we already?)
program = 'bowtie'
cpus = "-p" + str(cpu_count())
# maybe tell bowtie to stop looking after a set number of matches
if reject:
if largeIndex:
subprocess.check_output([program, '-a', "--suppress", "3,5,6,7", cpus, '-k', reject, '--large-index',
refgenome, '-f', 'temp.fa', 'offtargets.fa'])
else:
subprocess.check_output([program, '-a', "--suppress", "3,5,6,7", cpus, '-k', reject, refgenome, '-f',
'temp.fa', 'offtargets.fa'])
else:
if largeIndex:
subprocess.check_output([program, '-a', "--suppress", "3,5,6,7", cpus, '--large-index',
refgenome, '-f', 'temp.fa', 'offtargets.fa'])
else:
subprocess.check_output([program, '-a', "--suppress", "3,5,6,7", cpus, refgenome, '-f',
'temp.fa', 'offtargets.fa'])
print("Bowtie finished. Begining offtarget analysis...")
bowtie_results_file = 'offtargets.fa'
oftcount = 1
# This count is slow and probably unnecessary
total_lines = sum(1 for line in open(bowtie_results_file))
print("Total alignments from Bowtie: {}".format(total_lines))
new_widgets = ['Scoring for off-targets. Examining: ', progressbar.Counter(), ' ', progressbar.Percentage(),
' ', progressbar.Bar(), progressbar.Timer(), progressbar.ETA()]
new_progress = progressbar.ProgressBar(widgets=new_widgets, maxval=total_lines).start()
prunedlist = [] # List to hold spacers whose off-target score is above the minimum cutoff
mmpos = '[0-9]{1,}'
mmpos_re = regex.compile(mmpos)
with open(bowtie_results_file) as offtargetsfile: # parse all the bowtie results into something we can use
# Read in the first line and parse.
keys = ['readname', 'strand', 'position', 'mmpositions']
values = offtargetsfile.readline().strip('\n').split('\t')
previous_entry = dict(zip(keys,values))
current_set_of_offtargets = []
# Read in the next line in the list.
for line in offtargetsfile:
line_values = line.strip('\n').split('\t')
next_entry = dict(zip(keys,line_values))
new_progress.update(oftcount)
oftcount += 1
if next_entry['readname'] == previous_entry['readname']:# Check to see if it is for the same spacer
current_set_of_offtargets.append(next_entry) # group them together.
else: # If it isn't, it is time to score that set and move to the next
# Extract the off-target positions from each entry
mmlist = []
badcount = 0
for entry in current_set_of_offtargets:
pos = mmpos_re.findall(entry['mmpositions'])
if len(pos) == 0: # Bowtie returns a match for the spacer itself in the genome
# if we have two such matches, we should indicate that there is a perfect off-target
badcount += 1
elif entry['strand'] == '+': mmlist.append([int(w) for w in pos])
elif entry['strand'] == '-': mmlist.append([19-int(w) for w in pos])
# Find the spacer in spacerlist to which these off-targets belong and set that spacer's offtarget score
matching_spacer = next((spacer for spacer in spacerlist if (previous_entry['readname'] ==
'{} {} {}'.format(spacer['description'], spacer['position'],str(spacer['score'])))), None)
# Tally up the offtarget score for the set of off targets and set the spacer's off-target score
if badcount > 2:
matching_spacer['offtargetscore'] = 0
# Speed this up by rejecting things with over a certain set of matching off-targets
elif reject and len(mmlist) > reject:
matching_spacer['offtargetscore'] = 0
else:
matching_spacer['offtargetscore'] = sumofftargets(mmlist)
if float(matching_spacer['offtargetscore']) >= float(offtargetcutoff):
prunedlist.append(matching_spacer)
# Dump the previous set.
current_set_of_offtargets = []
# Start a new set of off-targets using this new line
previous_entry = next_entry
current_set_of_offtargets.append(next_entry)
new_progress.finish()
print("\nFinished scoring off-targets")
finallist = []
if len(prunedlist) == 0:
print("No spacers were found that correspond to the parameters you set.")
else:
if len(prunedlist[0]['description'].split('|')) == 9: # need to make sure the header format is correct
for entry in prunedlist:
finallist.append(FormattedResult(entry))
# Create a set of all the GeneIDs in our list
geneset = set([y.GeneID for y in finallist])
toplist = []
for z in geneset:
all_spacers_for_gene = [a for a in finallist if a.GeneID == z]
ranked_spacers = sorted(all_spacers_for_gene, key=attrgetter('score','offtargetscore'), reverse=True)
if return_limit == 'all':
for w in ranked_spacers: toplist.append(w)
elif len(ranked_spacers) > int(return_limit):
for w in range(0,int(return_limit)): toplist.append(ranked_spacers[w])
else:
for w in range(0,len(ranked_spacers)-1): toplist.append(ranked_spacers[w])
olist = map(lambda entry: [entry.GeneID, entry.GeneName, entry.seq, entry.GC, entry.position,
entry.score, entry.offtargetscore], toplist)
headerlist = ['GeneID', 'GeneName', 'seq','%GC','position', 'score', 'off-target score']
else: # if it isn't, just dump all the spacers we found into a file
finallist = spacerlist
olist = map(lambda entry: [entry.id.split(' ')[0], entry.seq, GC(entry.seq), entry.position.split(' ')[1],
entry.score.split(' ')[2]], finallist)
headerlist = ['ID', 'seq', '%GC','position', 'score']
print("Writing file.")
try:
with open(outfile, 'w') as ofile:
output = csv.writer(ofile, dialect='excel')
output.writerows([headerlist])
output.writerows(olist)
except IOError:
print("There is trouble writing to the file. Perhaps it is open in another application?")
choice = input("Would you like to try again? [y/n]")
if choice == 'y' or choice == 'Y':
try:
with open(outfile, 'w') as ofile:
output = csv.writer(ofile, dialect='excel')
output.writerows([headerlist])
output.writerows(olist)
except:
print("Sorry, still was unable to write to the file")
else:
return 0
print("Finished.")
class DigestedSequence:
def __init__(self, enzymes, sequence, is_linear=True):
self.enzymes = enzymes
self.sequence = sequence
self.res_batch = RestrictionBatch(enzymes)
self.is_linear = is_linear
self.site_dict = self.res_batch.search(self.sequence.seq, is_linear)
def get_sites(self):
"""
Return the set of sites for a given contig, ordered by increasing position.
:return: list of CutSites
"""
cutSites = []
for e_name, ctg_locs in self.site_dict.iteritems():
for loc in ctg_locs:
cutSites.append(CutSite(e_name, loc))
return sorted(cutSites)
def get_fragments(self):
"""
Return the genomic fragments resulting from the digestion.
:return: list of SeqRecords.
"""
sites = self.get_sites()
seq = self.sequence
if len(sites) == 0:
return seq
frags = []
for idx in xrange(1, len(sites)):
a = sites[idx - 1]
b = sites[idx]
frg = seq[a:b]
frg.id = "{0}:{1}:{2}".format(frg.id, a, b)
frg.name = frg.id
frg.description = "restriction digest fragment from {0} to {1}".format(a, b)
frags.append(frg)
return frags
@staticmethod
def digestion_sites(seq_list, enzyme_names=[], min_sites=1):
"""
Return a list of sites per sequence, preserving the input list order.
:param seq_list: list of sequences to analyze
:param enzyme_names: enzyme used in digestion
:param min_sites: minimum sites required for a sequence to be included.
:param min_length: minimum sequence length to be included.
:return: list of sites per sequence
"""
sites = []
for seq in seq_list:
if seq["excluded"]:
continue
ds = DigestedSequence(enzyme_names, seq["record"])
seq_sites = ds.get_sites()
if len(seq_sites) < min_sites:
print "\tExcluded {0} (length {1}) with only {2} sites".format(
seq["record"].id, len(seq["record"]), len(seq_sites)
)
# continue
sites.append({"name": seq["record"].id, "pos": seq_sites})
return sites
#
# Created: 11/04/2013
#-------------------------------------------------------------------------------
from Bio import Entrez
from Bio import SeqIO
from Bio.Restriction import Restriction
from Bio.Restriction import RestrictionBatch
email="*****@*****.**"
Entrez.email = email
fetch_seq = Entrez.efetch(db="nucleotide", rettype="fasta",retmode="text", id="294489415")
seq_record = SeqIO.read(fetch_seq, "fasta")
fetch_seq.close()
# To see how a specific restriction enzyme (Sau3AI) would digest your sequence:
print("Restriction site is", Restriction.Sau3AI.site)
digest = Restriction.Sau3AI.catalyse(seq_record.seq)
print ("Number of fragments is", len(digest))
print "------\nLengths of each fragment\n------"
for lengths in digest:
print len(lengths)
# Run every restriction enzyme in the New England Biolabs database against the sequence
rb_supp = RestrictionBatch(first=[], suppliers=['N'])
for rest in rb_supp.search(seq_record.seq):
# The code commented out below will only show restriction enzymes that created a number of fragments between 10 and 40
#if len(rb_supp.search(seq_record.seq)[rest]) > 10 and len(rb_supp.search(seq_record.seq)[rest]) < 40:
# This will show every restriction ezyme that was able to digest the sequence in some way.
if len(rb_supp.search(seq_record.seq)[rest]) > 0:
print rest, ":", rb_supp.search(seq_record.seq)[rest]
class DigestedSequence:
def __init__(self, enzymes, sequence, is_linear=True):
self.enzymes = enzymes
self.sequence = sequence
self.res_batch = RestrictionBatch(enzymes)
self.is_linear = is_linear
self.site_dict = self.res_batch.search(self.sequence.seq, is_linear)
def get_sites(self):
"""
Return the set of sites for a given contig, ordered by increasing position.
:return: list of CutSites
"""
cutSites = []
for e_name, ctg_locs in self.site_dict.iteritems():
for loc in ctg_locs:
cutSites.append(CutSite(e_name, loc))
return sorted(cutSites)
def get_fragments(self):
"""
Return the genomic fragments resulting from the digestion.
:return: list of SeqRecords.
"""
sites = self.get_sites()
seq = self.sequence
if len(sites) == 0:
return seq
frags = []
for idx in xrange(1, len(sites)):
a = sites[idx - 1]
b = sites[idx]
frg = seq[a:b]
frg.id = '{0}:{1}:{2}'.format(frg.id, a, b)
frg.name = frg.id
frg.description = 'restriction digest fragment from {0} to {1}'.format(
a, b)
frags.append(frg)
return frags
@staticmethod
def digestion_sites(seq_list, enzyme_names=[], min_sites=1):
"""
Return a list of sites per sequence, preserving the input list order.
:param seq_list: list of sequences to analyze
:param enzyme_names: enzyme used in digestion
:param min_sites: minimum sites required for a sequence to be included.
:param min_length: minimum sequence length to be included.
:return: list of sites per sequence
"""
sites = []
for seq in seq_list:
if seq['excluded']:
continue
ds = DigestedSequence(enzyme_names, seq['record'])
seq_sites = ds.get_sites()
if len(seq_sites) < min_sites:
print '\tExcluded {0} (length {1}) with only {2} sites'.format(
seq['record'].id, len(seq['record']), len(seq_sites))
#continue
sites.append({'name': seq['record'].id, 'pos': seq_sites})
return sites
def _catalyze(record: SeqRecord,
enzymes: List[RestrictionType],
linear=True) -> List[Tuple[str, SeqRecord, str]]:
"""Catalyze a SeqRecord and return all post-digest SeqRecords with overhangs.
Overhangs are returned as the overhang plus the position of the cut
in the 5' end (^) and 3' end (_). So a 5' overhang may be:
^AAAA_. But a 3' overhang may be: _AAAA^.
Args:
record: The SeqRecord to digest with enzymes
enzymes: List of enzymes to digest the input records with
Keyword Args:
linear: Whether the record to catalyze is linear or circular
Returns:
Tuple with: (left overhang, cut fragment, right overhang)
"""
record = record.upper()
batch = RestrictionBatch(enzymes)
batch_sites = batch.search(record.seq, linear=linear)
# order all cuts with enzymes based on index
cuts_seen: Set[int] = set()
enzyme_cuts: List[Tuple[RestrictionType, int]] = []
for enzyme, cuts in batch_sites.items():
for cut in cuts:
if cut in cuts_seen:
continue
cuts_seen.add(cut)
enzyme_cuts.append((enzyme, cut - 1)) # revert to 0-based
enzyme_cuts = sorted(enzyme_cuts, key=lambda x: x[1])
# list of left/right overhangs for each fragment
frag_w_overhangs: List[Tuple[str, SeqRecord, str]] = []
for i, (enzyme, cut) in enumerate(enzyme_cuts):
if i == len(enzyme_cuts) - 1 and linear:
continue
next_enzyme, next_cut = enzyme_cuts[(i + 1) % len(enzyme_cuts)]
enzyme_len = len(enzyme.ovhgseq)
next_enzyme_len = len(next_enzyme.ovhgseq)
# shift cuts left for 3overhang enzymes
if enzyme.is_3overhang():
cut -= enzyme_len
if next_enzyme.is_3overhang():
next_cut -= next_enzyme_len
cut_rc = cut if enzyme.is_3overhang() else cut + enzyme_len
next_cut_rc = (next_cut if next_enzyme.is_3overhang() else next_cut +
next_enzyme_len)
# find the cutsite sequences
left = record[cut:cut + enzyme_len]
right = record[next_cut:next_cut + next_enzyme_len]
left_rc = right.reverse_complement()
right_rc = left.reverse_complement()
left = str(left.seq)
right = str(right.seq)
left_rc = str(left_rc.seq)
right_rc = str(right_rc.seq)
if enzyme.is_3overhang():
left += "^"
right_rc += "^"
else:
left = "^" + left
right_rc = "^" + right_rc
if next_enzyme.is_3overhang():
right += "^"
left_rc += "^"
else:
right = "^" + right
left_rc = "^" + left_rc
# shift cuts right again for 3overhang enzymes
if enzyme.is_3overhang():
cut += enzyme_len
if next_enzyme.is_3overhang():
next_cut += next_enzyme_len
frag = record[cut:next_cut]
frag_rc = record[cut_rc:next_cut_rc].reverse_complement()
frag_rc.id = record.id
if next_cut < cut: # wraps around the zero-index
frag = (record + record)[cut:next_cut + len(record)]
frag.id = record.id
frag_rc = (record + record)[cut_rc:next_cut_rc +
len(record)].reverse_complement()
frag_rc.id = record.id
frag_w_overhangs.append((left, frag, right))
frag_w_overhangs.append((left_rc, frag_rc, right_rc))
return frag_w_overhangs
def redigest_code():
argscheck()
### making outfile
# output file
if entry2_input.get() == "":
outfile = 'redigest.'+ TIME + '.out'
else:
outfile=entry2_input.get()
out_file = open(outfile, 'wt+')
### processing gene sequences
if entry7_input.get() == "Multifasta gene file":
genomeSeq = "N"
elif entry7_input.get() == "Single genome sequence":
genomeSeq = "Y"
if genomeSeq == 'N':
### making report file
verbosity = 'Y'
report_file = outfile + '.csv'
# open report file
RF = open(report_file, 'wt+')
# reverse complement the reverse primer
if entry6_input.get() == "":
reverse = ""
else:
reverse = entry6_input.get()
reverse=str(Seq(reverse).reverse_complement())
# counter for the NAME
count=1
### iterating sequences
input_file = entry1_input.get()
infile= open(input_file, 'r')
# input file format
if entry8_input.get() == "Fasta":
informat = "fasta"
elif entry8_input.get() == "Genbank":
informat = "genbank"
for record in SeqIO.parse(infile, informat):
header=record.id
array=str(record.seq)
NAME=str('RED' + TIME + str(count))
#
if informat == 'genbank':
desc=str(', '.join(list(record.annotations["taxonomy"])))
else:
desc = ''
## adding primer sequence if provided
if entry5_input.get() == "":
forward = ""
else:
forward = entry5_input.get()
if forward is not None:
Farray=''.join(forward + array)
else:
Farray=array
### adding primer sequence if provided
if entry6_input.get() == "":
reverse = ""
else:
reverse = entry6_input.get()
if reverse is not None:
FarrayR=''.join(Farray.strip('\n') + reverse)
else:
FarrayR=Farray
### orientation based on tagged
if entry4_input.get() == "Forward":
tagg = str("F")
elif entry4_input.get() == "Reverse":
tagg = str("R")
tagged=tagg.upper()
if tagged == 'R':
FarrayRseqFR=str(Seq(FarrayR).reverse_complement())
SubFeat="TRF_RevComp"
else:
FarrayRseqFR=str(FarrayR)
SubFeat="TRF"
### Restriction Enzyme check from list
enzyme = entry3_input.get()
enzyme_RE = RestrictionBatch([enzyme])
### search the restriction sites position in sequence
FarrayRseqFR_RE=enzyme_RE.search(Seq(FarrayRseqFR))
### convert the dict to the list and indexing
index=list(FarrayRseqFR_RE.values())[0]
### checking if restriction site is present or sequence will be uncut
if not index:
fragment=len(FarrayRseqFR)
else:
fragment=index[0]
### adding size to header and trimming sequence to terminal fragment length
if not index:
### non-cut fragment header
FastaHeader=NAME + "|" + str(len(FarrayRseqFR)) + "_bp" + "|" + header
### non-cut fragment sequence
FastaSeq=FarrayRseqFR[:len(FarrayRseqFR)]
Feat=SeqFeature(FeatureLocation(start=0, end=len(FarrayRseqFR)), type="REDigest", ref=SubFeat)
else:
### cut fragment header
FastaHeader=NAME + "|" + str(fragment) + "_bp" + "|" + header
### cut fragment sequence and slicing to the fragment length
FastaSeq=FarrayRseqFR[:fragment]
Feat=SeqFeature(FeatureLocation(start=0, end=fragment), type="REDigest", ref=SubFeat)
### terminal-screen output, info about sequence header and all the fragments
### based of verbosity
if verbosity == 'Y':
print(" ", FastaHeader, '\t', FarrayRseqFR_RE)
### counter for the locus name
count +=1
### seq object
FastaSequence = SeqRecord(Seq(FastaSeq, IUPAC.IUPACAmbiguousDNA()), FastaHeader, description=desc, name=NAME)
### append features to seqobject
FastaSequence.features.append(Feat)
### seq object
if entry9_input.get() == "Fasta":
outformat = "fasta"
elif entry9_input.get() == "Genbank":
outformat = "genbank"
if outformat == 'genbank':
SeqIO.write(FastaSequence, out_file, outformat)
else:
SeqIO.write(FastaSequence, out_file, "fasta-2line")
### writing progress to file too
print(FastaHeader, '\t', FarrayRseqFR_RE, file=RF)
#####################
############################################################### Genome
else:
### parsing genome sequence
### making report file
if entry9_input.get() == "Fasta":
outformat = "fasta"
elif entry9_input.get() == "Genbank":
outformat = "genbank"
if entry2_input.get() == "":
outfile = 'redigest.'+ TIME + '.out'
else:
outfile=entry2_input.get()
report_file = outfile + '_RF.csv'
# open report file
RF = open(report_file, 'wt+')
print("Individual restriction fragments", file=RF)
print("[WRITING:] Individual restriction fragments to file:", report_file)
input_file = entry1_input.get()
infile= open(input_file, 'r')
# input file format
if entry8_input.get() == "Fasta":
informat = "fasta"
elif entry8_input.get() == "Genbank":
informat = "genbank"
for record in SeqIO.parse(infile, informat):
Gen_header=record.id
Gen_array=str(record.seq)
#
if informat == 'genbank':
desc=str(', '.join(list(record.annotations["taxonomy"])))
else:
desc = ''
### Restriction Enzyme check from list
enzyme = entry3_input.get()
enzyme_RE = RestrictionBatch([enzyme])
### search the restriction sites position in sequence
Gen_array_RE=enzyme_RE.search(Seq(Gen_array))
Gen_array_RE_V = list(Gen_array_RE.values())[0]
#
ID0 = 0
ID_min = min(Gen_array_RE_V)
ID_max = max(Gen_array_RE_V)
ID1 = 0
ID2 = 1
# first fragment from first nt to first cut
GenFastaSeq=Gen_array[0:ID_min]
GenFastaSeqLen = len(GenFastaSeq)
GenFastaHeader=Gen_header + "|" + str(GenFastaSeqLen) + "_bp|" + Gen_header
# verbosity
verbosity = "Y"
if verbosity == 'Y':
print(" ", GenFastaHeader)
# seq object
GenSeqRec = SeqRecord(Seq(GenFastaSeq, IUPAC.IUPACAmbiguousDNA()), GenFastaHeader, description=desc)
### seq object to file
if outformat == 'genbank':
SeqIO.write(GenSeqRec, out_file, outformat)
elif outformat == 'fasta':
SeqIO.write(GenSeqRec, out_file, outformat)
# report to file
print(GenFastaHeader, file=RF)
#
for GenomeFragment in Gen_array_RE_V:
while ID2 < len(Gen_array_RE_V):
GenFastaSeq=Gen_array[Gen_array_RE_V[ID1]:Gen_array_RE_V[ID2]]
GenFastaSeqLen = len(GenFastaSeq)
GenFastaHeader=Gen_header + "|" + str(GenFastaSeqLen) + "_bp|" + Gen_header
# verbosity
if verbosity == 'Y':
print(" ", GenFastaHeader)
# increment value for index
ID1 += 1
ID2 += 1
# seq object
GenSeqRec = SeqRecord(Seq(GenFastaSeq, IUPAC.IUPACAmbiguousDNA()), GenFastaHeader, description=desc)
### seq object to file
if outformat == 'genbank':
SeqIO.write(GenSeqRec, out_file, outformat)
elif outformat == 'fasta':
SeqIO.write(GenSeqRec, out_file, outformat)
# report to file
print(GenFastaHeader, file=RF)
# last fragment from last cut to last nt
GenFastaSeq=Gen_array[ID_max:]
GenFastaSeqLen = len(GenFastaSeq)
GenFastaHeader=Gen_header + "|" + str(GenFastaSeqLen) + "_bp|" + Gen_header
# verbosity
if verbosity == 'Y':
print(" ", GenFastaHeader)
# seq object
GenSeqRec = SeqRecord(Seq(GenFastaSeq, IUPAC.IUPACAmbiguousDNA()), GenFastaHeader, description=desc)
### seq object to file
if outformat == 'genbank':
SeqIO.write(GenSeqRec, out_file, outformat)
else:
SeqIO.write(GenSeqRec, out_file, outformat)
# report to file
print(GenFastaHeader, file=RF)
# getting all sequences from first nt to respective cut
report_file2 = outfile + '_TRF.csv'
# open report file
TRF2 = open(report_file2, 'wt+')
print("Terminal restriction fragments: from nucleotide 1 to respective cuts", file=TRF2)
print("[WRITING:] Terminal restriction fragments, from nucleotide 1 to respective cuts to file:", report_file2)
for GenomeFragment in Gen_array_RE_V:
GenFastaHeader=Gen_header + "|" + str(GenomeFragment) + "_bp|" + Gen_header
GenFastaSeq=Gen_array[:GenomeFragment]
### seq object
GenFastaSequence = SeqRecord(Seq(GenFastaSeq, IUPAC.IUPACAmbiguousDNA()), GenFastaHeader,
description=desc)
### terminal-screen output, info about sequence header and all the fragments
### based of verbosity
if verbosity == 'Y':
print(" ", GenFastaHeader)
### writing progress to file too
print(GenFastaHeader, file=TRF2)
## close files
TRF2.close()
RF.close()
# final close
out_file.close()
infile.close()
