def check_primer_list(primerlist: list):
"""docstring."""
pl = primerlist
unique_seqs = set(str(p.seq).lower() for p in pl)
msg = f"{len(pl)} primers, {len(unique_seqs)} unique primer sequences\n"
defined = [p for p in pl if set(p.seq.lower()) != set("n")]
msg += f"{len(pl) - len(defined)} primer(s) without sequence (N)"
for i, p in enumerate(pl):
if not p.name.startswith(str(i)):
msg += f"\nWrong number: {i} {p.format('tab')}"
dct = _defaultdict(list)
for u in unique_seqs:
for p in defined:
if u == str(p.seq).lower():
dct[u].append(p.name)
for seq, names in dct.items():
if len(names) > 1:
msg += " ".join(names)
msg += f" {seq}\n"
return _pretty_str(msg.strip())
def list_features(self):
"""Print ASCII table with all features.
Examples
--------
>>> from Bio.Seq import Seq
>>> from pydna.seqrecord import SeqRecord
>>> a=SeqRecord(Seq("atgtaa"))
>>> a.add_feature(2,4)
>>> print(a.list_features())
+-----+---------------+-----+-----+-----+-----+------+------+
| Ft# | Label or Note | Dir | Sta | End | Len | type | orf? |
+-----+---------------+-----+-----+-----+-----+------+------+
| 0 | L:ft2 | --> | 2 | 4 | 2 | misc | no |
+-----+---------------+-----+-----+-----+-----+------+------+
"""
x = _PrettyTable([
"Ft#", "Label or Note", "Dir", "Sta", "End", "Len", "type", "orf?"
])
x.align["Ft#"] = "r" # Left align
x.align["Label or Note"] = "l" # Left align
x.align["Len"] = "r"
x.align["Sta"] = "l"
x.align["End"] = "l"
x.align["type"] = "l"
x.padding_width = 1 # One space between column edges and contents
for i, sf in enumerate(self.features):
try:
lbl = sf.qualifiers["label"]
except KeyError:
try:
lbl = sf.qualifiers["note"]
except KeyError:
lbl = "nd"
else:
lbl = "N:{}".format(" ".join(lbl).strip())
else:
lbl = "L:{}".format(" ".join(lbl).strip())
x.add_row([
i,
lbl[:16],
{
1: "-->",
-1: "<--",
0: "---",
None: "---"
}[sf.strand],
sf.location.start,
sf.location.end,
len(sf),
sf.type,
{
True: "yes",
False: "no"
}[self.extract_feature(i).isorf()
or self.extract_feature(i).reverse_complement().isorf()],
])
return _pretty_str(x)
def delete_cache(delete=[ "amplify", "assembly", "genbank", "web", "synced" ]):
msg = ""
for file_ in delete:
msg += file_
try:
_os.remove( _os.path.join( _os.environ["pydna_data_dir"], file_) )
msg += " deleted.\n"
except OSError as e:
if e._errno == _errno.ENOENT:
msg += " no file to delete.\n"
return _pretty_str(msg)
def program(amplicon, tm=tm_default, ta=ta_default):
r"""Returns a string containing a text representation of a suggested
PCR program using Taq or similar polymerase.
::
|95°C|95°C | |tmf:59.5
|____|_____ 72°C|72°C|tmr:59.7
|5min|30s \ 59.1°C _____|____|30s/kb
| | \______/ 0:32|5min|GC 51%
| | 30s | |1051bp
"""
# Taq polymerase extension rate is set to 30 nt/s
# see https://www.thermofisher.com/pt/en/home/life-science/pcr/pcr-enzymes-master-mixes/taq-dna-polymerase-enzymes/taq-dna-polymerase.html
taq_extension_rate = 30 # seconds/kB PCR product length
extension_time_taq = int(taq_extension_rate * len(amplicon) / 1000) # seconds
f = _textwrap.dedent(
r"""
|95°C|95°C | |tmf:{tmf:.1f}
|____|_____ 72°C|72°C|tmr:{tmr:.1f}
|5min|30s \ {ta:.1f}°C _____|____|{rate}s/kb
| | \______/{0:2}:{1:2}|5min|GC {GC_prod}%
| | 30s | |{size}bp
"""[
1:-1
].format(
rate=taq_extension_rate,
size=len(amplicon.seq),
ta=round(
ta(
amplicon.forward_primer.footprint,
amplicon.reverse_primer.footprint,
amplicon.seq,
),
1,
),
tmf=tm(amplicon.forward_primer.footprint),
tmr=tm(amplicon.reverse_primer.footprint),
GC_prod=int(amplicon.gc()),
*map(int, divmod(extension_time_taq, 60)),
)
)
return _pretty_str(f)
def prepend_primerlist(newprimers: list, oldprimers: list):
"""docstring."""
new = []
found = []
no = len(oldprimers)
oldstrs = [str(p.seq).upper() for p in oldprimers]
for p in newprimers[::-1]:
try:
i = oldstrs.index(str(p.seq).upper())
except ValueError:
i = no + len(new)
suff = p.id.split(str(i))[-1]
suff.lstrip("_")
newprimer = _copy.copy(p)
newprimer.id = f"{i}_{suff}"
new.append(newprimer)
else:
found.append(oldprimers[i])
new = new[::-1]
return found[::-1] or _pretty_str("\n".join([p.format("fasta") for p in new]))
try:
del findsubstrings_suffix_arrays_python
except NameError:
pass
def delete_cache(delete=[ "amplify", "assembly", "genbank", "web", "synced" ]):
msg = ""
for file_ in delete:
msg += file_
try:
_os.remove( _os.path.join( _os.environ["pydna_data_dir"], file_) )
msg += " deleted.\n"
except OSError, e:
if e._errno == _errno.ENOENT:
msg += " no file to delete.\n"
return _pretty_str(msg)
def open_cache_folder():
_open_folder( _os.environ["pydna_data_dir"] )
def open_config_folder():
_open_folder( _os.environ["pydna_config_dir"] )
def open_log_folder():
_open_folder( _os.environ["pydna_log_dir"] )
def _open_folder(pth):
if _sys.platform=='win32':
_subprocess.Popen(['start', pth], shell= True)
