pydna 5.5.5__py3-none-any.whl → 5.5.6__py3-none-any.whl

pydna/__init__.py

@@ -49,23 +49,27 @@ functions with a lowercase letter:
          ├── amplify
          │         ├── Anneal
          │         └── pcr
+         │
          ├── assembly
          │          └── Assembly
+         │
          ├── design
          │        ├── assembly_fragments
          │        └── primer_design
-         ├── download
-         │          └── download_text
+         │
          ├── dseqrecord
          │            └── Dseqrecord
          ├── gel
          │     └── Gel
+         │
          ├── genbank
          │         ├── genbank
          │         └── Genbank
+         │
          ├── parsers
          │         ├── parse
          │         └── parse_primers
+         │
          └── readers
                    ├── read
                    └── read_primers
@@ -143,7 +147,7 @@ __license__ = "BSD"
 __maintainer__ = "Björn Johansson"
 __email__ = "bjorn_johansson@bio.uminho.pt"
 __status__ = "Development"  # "Production" #"Prototype"
-__version__ = "5.5.5"
+__version__ = "5.5.6"
 
 
 class _PydnaWarning(Warning):

pydna/all.py

@@ -18,7 +18,7 @@ ttt
 Dseqrecord(-3)
 >>> from pydna.all import __all__
 >>> __all__
-['Anneal', 'pcr', 'Assembly', 'genbank', 'Genbank', 'download_text', 'Dseqrecord',
+['Anneal', 'pcr', 'Assembly', 'genbank', 'Genbank', 'Dseqrecord',
 'Dseq', 'read', 'read_primer', 'parse', 'parse_primers', 'primer_design', 'assembly_fragments', 'eq', 'gbtext_clean']
 >>>
 """
@@ -30,20 +30,16 @@ __all__ = [
     "Assembly",
     "genbank",
     "Genbank",
-    "download_text",
     "Dseqrecord",
     "Dseq",
     "read",
     "read_primer",
     "parse",
     "parse_primers",
-    # "ape",
     "primer_design",
     "assembly_fragments",
-    # "circular_assembly_fragments",
     "eq",
     "gbtext_clean",
-    # "PrimerList",
 ]
 
 
@@ -52,20 +48,13 @@ from pydna.amplify import pcr
 from pydna.assembly import Assembly
 from pydna.genbank import genbank
 from pydna.genbank import Genbank
-from pydna.download import download_text
 from pydna.dseqrecord import Dseqrecord
 from pydna.dseq import Dseq
 from pydna.readers import read
 from pydna.readers import read_primer
 from pydna.parsers import parse
 from pydna.parsers import parse_primers
-
-# from pydna.editor import ape
 from pydna.design import primer_design
 from pydna.design import assembly_fragments
-
-# from pydna.design import circular_assembly_fragments
 from pydna.utils import eq
 from pydna.genbankfixer import gbtext_clean
-
-# from pydna.myprimers import PrimerList

pydna/assembly2.py

@@ -357,7 +357,18 @@ def common_sub_strings(
     return [r for r in results if r not in shifted_matches]
 
 
-def gibson_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
+def _get_trim_end_info(
+    end_info: tuple[str, str], trim_ends: str, is_five_prime: bool
+) -> int | None:
+    """Utility function to get the trim information for terminal_overlap."""
+    if end_info[0] == trim_ends:
+        return len(end_info[1]) if is_five_prime else len(end_info[1]) * -1
+    return 0 if is_five_prime else None
+
+
+def terminal_overlap(
+    seqx: Dseqrecord, seqy: Dseqrecord, limit=25, trim_ends: None | str = None
+):
     """
     Assembly algorithm to find terminal overlaps (e.g. for Gibson assembly).
     The order matters, we want alignments like:
@@ -382,6 +393,9 @@ def gibson_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
         The second sequence
     limit : int
         Minimum length of the overlap
+    trim_ends : str
+        The ends to trim, either '5' or '3'
+        If None, no trimming is done
 
     Returns
     -------
@@ -389,32 +403,64 @@ def gibson_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
         A list of overlaps between the two sequences
 
     >>> from pydna.dseqrecord import Dseqrecord
-    >>> from pydna.assembly2 import gibson_overlap
+    >>> from pydna.assembly2 import terminal_overlap
     >>> x = Dseqrecord("ttactaAAAAAA")
     >>> y = Dseqrecord("AAAAAAcgcacg")
-    >>> gibson_overlap(x, y, limit=5)
+    >>> terminal_overlap(x, y, limit=5)
     [(6, 0, 6), (7, 0, 5)]
-    >>> gibson_overlap(y, x, limit=5)
+    >>> terminal_overlap(y, x, limit=5)
+    []
+
+    Trimming the ends:
+    >>> from pydna.dseq import Dseq
+    >>> from pydna.dseqrecord import Dseqrecord
+    >>> from pydna.assembly2 import terminal_overlap
+    >>> x = Dseqrecord(Dseq.from_full_sequence_and_overhangs("aaaACGT", 0, 3))
+    >>> y = Dseqrecord(Dseq.from_full_sequence_and_overhangs("ACGTccc", 3, 0))
+    >>> terminal_overlap(x, y, limit=4)
+    [(3, 0, 4)]
+    >>> terminal_overlap(x, y, limit=4, trim_ends="5'")
+    [(3, 0, 4)]
+    >>> terminal_overlap(x, y, limit=4, trim_ends="3'")
     []
     """
 
-    # Because Gibson enzymes remove 5' overhangs, we remove them from the sequence
-    # when looking for homology, then we shift the location of the second fragment accordingly.
-    # This is only relevant for linear fragments, so we don't need to worry about
-    # shifting locations for circular fragments.
-    trim_x_left = -seqx.seq.ovhg if seqx.seq.ovhg < 0 else 0
-    trim_x_right = seqx.seq.watson_ovhg if seqx.seq.watson_ovhg < 0 else None
-    trim_y_left = -seqy.seq.ovhg if seqy.seq.ovhg < 0 else 0
-    trim_y_right = seqy.seq.watson_ovhg if seqy.seq.watson_ovhg < 0 else None
-
-    stringx = str(seqx.seq[trim_x_left:trim_x_right]).upper()
-    stringy = str(seqy.seq[trim_y_left:trim_y_right]).upper()
+    if trim_ends is not None and trim_ends not in ["5'", "3'"]:
+        raise ValueError("trim_ends must be '5' or '3'")
+
+    if trim_ends is None:
+        trim_x_left, trim_x_right, trim_y_left, trim_y_right = (0, None, 0, None)
+        stringx = str(seqx.seq).upper()
+        stringy = str(seqy.seq).upper()
+    else:
+        trim_x_right = _get_trim_end_info(
+            seqx.seq.three_prime_end(), trim_ends, is_five_prime=False
+        )
+        trim_y_left = _get_trim_end_info(
+            seqy.seq.five_prime_end(), trim_ends, is_five_prime=True
+        )
+
+        # I actually don't think these two are needed, since only the terminal
+        # join between x_right and y_left is tested, but maybe there is some edge-case
+        # that I am missing, so keeping them just in case.
+        trim_x_left = _get_trim_end_info(
+            seqx.seq.five_prime_end(), trim_ends, is_five_prime=True
+        )
+        trim_y_right = _get_trim_end_info(
+            seqy.seq.three_prime_end(), trim_ends, is_five_prime=False
+        )
+
+        stringx = str(seqx.seq[trim_x_left:trim_x_right]).upper()
+        stringy = str(seqy.seq[trim_y_left:trim_y_right]).upper()
+
     # We have to convert to list because we need to modify the matches
     matches = [
         list(m)
         for m in common_sub_strings_str(stringx, stringy, limit)
         if (m[1] == 0 and m[0] + m[2] == len(stringx))
     ]
+
+    # Shift the matches if the left end has been trimmed
     for match in matches:
         match[0] += trim_x_left
         match[1] += trim_y_left
@@ -423,6 +469,31 @@ def gibson_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
     return [tuple(m) for m in matches]
 
 
+def gibson_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
+    """
+    Assembly algorithm to find terminal overlaps for Gibson assembly.
+    It is a wrapper around terminal_overlap with trim_ends="5'".
+    """
+
+    return terminal_overlap(seqx, seqy, limit, trim_ends="5'")
+
+
+def in_fusion_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
+    """
+    Assembly algorithm to find terminal overlaps for in-fusion assembly.
+    It is a wrapper around terminal_overlap with trim_ends="3'".
+    """
+    return terminal_overlap(seqx, seqy, limit, trim_ends="3'")
+
+
+def pcr_fusion_overlap(seqx: Dseqrecord, seqy: Dseqrecord, limit=25):
+    """
+    Assembly algorithm to find terminal overlaps for PCR fusion assembly.
+    It is a wrapper around terminal_overlap with trim_ends=None.
+    """
+    return terminal_overlap(seqx, seqy, limit, trim_ends=None)
+
+
 def sticky_end_sub_strings(seqx: Dseqrecord, seqy: Dseqrecord, limit: bool = False):
     """
     Assembly algorithm for ligation of sticky ends.
@@ -1578,8 +1649,9 @@ class Assembly:
             fragment2[f2_1_start:f2_2_end]
         )
 
-        if overlap_diff == 0:
-            assert False, "Overlap is 0"
+        # Safeguard
+        if overlap_diff == 0:  # pragma: no cover
+            raise AssertionError("Overlap is 0")
 
         if overlap_diff > 0:
             new_loc_f1_1 = create_location(
@@ -2077,7 +2149,9 @@ def in_fusion_assembly(
         List of assembled DNA molecules
     """
 
-    products = gibson_assembly(frags, limit)
+    products = common_function_assembly_products(
+        frags, limit, in_fusion_overlap, circular_only
+    )
     return _recast_sources(products, InFusionSource)
 
 
@@ -2101,7 +2175,9 @@ def fusion_pcr_assembly(
     list[Dseqrecord]
         List of assembled DNA molecules
     """
-    products = gibson_assembly(frags, limit)
+    products = common_function_assembly_products(
+        frags, limit, pcr_fusion_overlap, circular_only
+    )
     return _recast_sources(products, OverlapExtensionPCRLigationSource)
 
 

pydna/dseq.py

@@ -1601,9 +1601,8 @@ class Dseq(Seq):
             DESCRIPTION.
 
         """
-        recessed = copy.deepcopy(self)
         n += max(0, self.ovhg or 0)
-        recessed = Dseq(
+        return Dseq(
             self._data[:n]
             .translate(dscode_to_crick_table)
             .translate(complement_table_for_dscode)
@@ -1611,7 +1610,6 @@ class Dseq(Seq):
             .lstrip()
             + self._data[n:]
         )
-        return recessed
 
     def nibble_five_prime_right(self: DseqType, n: int = 1) -> DseqType:
         """
@@ -1668,18 +1666,16 @@ class Dseq(Seq):
         gatc
         ctag
         """
-        recessed = copy.deepcopy(self)
         n = len(self) - n
         ovhg = len(self) if self.right_ovhg is None else self.right_ovhg
         n -= max(0, ovhg)
-        recessed = Dseq(
+        return Dseq(
             self._data[:n]
             + self._data[n:]
             .translate(dscode_to_watson_table)
             .translate(dscode_to_watson_tail_table)
             .lstrip()
         )
-        return recessed
 
     exo1_front = nibble_five_prime_left  # TODO: consider using the new names
     exo1_end = nibble_five_prime_right  # TODO: consider using the new names
@@ -1745,14 +1741,13 @@ class Dseq(Seq):
         """
         ovhg = len(self) if self.ovhg is None else self.ovhg
         n -= min(0, ovhg)
-        recessed = Dseq(
+        return Dseq(
             self._data[:n]
             .translate(dscode_to_watson_table)
             .translate(dscode_to_watson_tail_table)
             .lstrip()
             + self._data[n:]
         )
-        return recessed
 
     def nibble_three_prime_right(self: DseqType, n=1) -> DseqType:
         """
@@ -1812,7 +1807,7 @@ class Dseq(Seq):
         n = len(self) - n
         ovhg = len(self) if self.right_ovhg is None else self.right_ovhg
         n += min(0, ovhg)
-        recessed = Dseq(
+        return Dseq(
             self._data[:n]
             + self._data[n:]
             .translate(dscode_to_crick_table)
@@ -1820,7 +1815,6 @@ class Dseq(Seq):
             .translate(dscode_to_crick_tail_table)
             .lstrip()
         )
-        return recessed
 
     def no_cutters(
         self, batch: Union[RestrictionBatch, None] = None
@@ -1878,7 +1872,7 @@ class Dseq(Seq):
             """docstring."""
             w = f"{self.ovhg * '-'}{self.watson}{'-' * (-self.ovhg + len(self.crick) - len(self.watson))}".upper()
             c = f"{'-' * (self.ovhg + len(self.watson) - len(self.crick))}{self.crick}{-self.ovhg * '-'}".upper()
-            cs = ldseguid(w, c, alphabet="{DNA-extended}")
+            cs = ldseguid(w, c, alphabet="{DNA-extended},AU")
         return cs
 
     def isblunt(self) -> bool:
@@ -2250,7 +2244,7 @@ class Dseq(Seq):
             # argument is probably a RestrictionBatch
             enzymes = [e for e in enzymes[0]]
 
-        enzymes = flatten(enzymes)
+        enzymes = list(dict.fromkeys(flatten(enzymes)))  # remove duplicate enzymes
         out = list()
         for e in enzymes:
             # Positions of the cut on the watson strand. They are 1-based, so we subtract

pydna/dseqrecord.py

@@ -26,7 +26,7 @@ from Bio.SeqFeature import CompoundLocation
 from Bio.SeqFeature import SimpleLocation
 from pydna.seqrecord import SeqRecord
 from Bio.Seq import translate
-from pydna.utils import identifier_from_string
+from Bio.Seq import Seq as BPSeq
 import copy
 import operator
 import os
@@ -453,9 +453,23 @@ class Dseqrecord(SeqRecord):
             feature.location += len(nucleotides)
         return newseq
 
-    def format(self, f="gb"):
+    def format(self, format: str = "gb"):
         """Returns the sequence as a string using a format supported by Biopython
         SeqIO [#]_. Default is "gb" which is short for Genbank.
+        Allowed Formats are for example:
+
+        * "fasta": The standard FASTA format.
+        * "fasta-2line": No line wrapping and exactly two lines per record.
+        * "genbank" (or "gb"): The GenBank flat file format.
+        * "embl": The EMBL flat file format.
+        * "imgt": The IMGT variant of the EMBL format.
+
+        The format string can be modified with the keyword "dscode" if
+        the underlying dscode string is desired in the output. for example:
+        ::
+
+            Dseqrecord("PEXIGATCQFZJ").format("fasta-2line dscode")
+
 
         Examples
         --------
@@ -477,6 +491,12 @@ class Dseqrecord(SeqRecord):
         ORIGIN
                 1 aaa
         //
+        >>> print(Dseqrecord("PEXIGATCQFZJ").format("fasta-2line"))
+        >id description
+        GATCGATCGATC
+        >>> print(Dseqrecord("PEXIGATCQFZJ").format("fasta-2line dscode"))
+        >id description
+        PEXIGATCQFZJ
 
 
         References
@@ -486,13 +506,19 @@ class Dseqrecord(SeqRecord):
 
 
         """
-
         record = copy.deepcopy(self)
-        if f in ("genbank", "gb") and self.circular:
+        if "dscode" in format:
+            format = format.replace("dscode", "")
+            obj = BPSeq("")
+            obj._data = record.seq._data
+            record.seq = obj
+        format = format.strip(" -")
+        if format in ("genbank", "gb") and self.circular:
             record.annotations["topology"] = "circular"
         else:
             record.annotations["topology"] = "linear"
-        return SeqRecord.format(record, f).strip()
+
+        return SeqRecord.format(record, format).strip()
 
     def write(self, filename=None, f="gb"):
         """Writes the Dseqrecord to a file using the format f, which must
@@ -851,15 +877,6 @@ class Dseqrecord(SeqRecord):
             return self.apply_cut(cut, cut)
         else:
             answer = Dseqrecord("")
-        identifier = "part_{id}".format(id=self.id)
-        if answer.features:
-            sf = max(answer.features, key=len)  # default
-            if "label" in sf.qualifiers:
-                identifier = " ".join(sf.qualifiers["label"])
-            elif "note" in sf.qualifiers:
-                identifier = " ".join(sf.qualifiers["note"])
-        answer.id = identifier_from_string(identifier)[:16]
-        answer.name = identifier_from_string("part_{name}".format(name=self.name))[:16]
         return answer
 
     def __eq__(self, other):

{pydna-5.5.5.dist-info → pydna-5.5.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pydna
-Version: 5.5.5
+Version: 5.5.6
 Summary: Representing double stranded DNA and functions for simulating cloning and homologous recombination between DNA molecules.
 License: BSD
 License-File: LICENSE.txt

{pydna-5.5.5.dist-info → pydna-5.5.6.dist-info}/RECORD

@@ -1,21 +1,20 @@
-pydna/__init__.py,sha256=0XgYsIw5cCxYJaKvV4B9TEp-pqU2m3O47qfAtSXsBCo,7082
+pydna/__init__.py,sha256=4u9wd3RbQkivNRKpEGXHT7Lrk7W7G5V64PJLOiSXKAk,7086
 pydna/_pretty.py,sha256=S3J0z_czeP1HpR-lj5fXQo9OeZc3ONsvxEGAc-Oqvjo,885
 pydna/_thermodynamic_data.py,sha256=ctOCzI0SclCBQVk7tG01bDv76fMeOROrp_WdVG5jp20,10885
-pydna/all.py,sha256=xwkbR5Hn52xVfgLAXaEfIgtNwaBiGDbJFTQfa3Zi6HQ,1781
+pydna/all.py,sha256=jPeYTAPh5uNXnqsK-HfMFzlVXE6sSqsonHCgmt6lf2I,1502
 pydna/alphabet.py,sha256=NOWIcsVjdPSR9aAZx5wzWD8061Pq2fOE1qAKfjqDzGg,29654
 pydna/amplicon.py,sha256=zql6MVqoKu9XEDlEmqxCQa5oZMDk3pyayP536k-yS38,5135
 pydna/amplify.py,sha256=DsMDJi6bRmP1CMku-jZ1_QXQ3-gbQ_P2M9kHR30zJ-Y,18738
 pydna/assembly.py,sha256=1bAaFZDAEAlz_LB31sjAPRtAkIFK_VIXpMIQpTf_8xU,19291
-pydna/assembly2.py,sha256=KLTkSqTONF3TOc26IrjhaJaUhLLCvnntQBC2E1RUUR8,106216
+pydna/assembly2.py,sha256=WmzygtYKLONRoccaqHM5O3xjbNzaSeOHR15EH-tVOmk,108764
 pydna/codon.py,sha256=AZb8DjrS5lBAzNhL32GvE_P9V5DvSBbc7w9TaSeQHlc,2553
 pydna/common_sub_strings.py,sha256=pnSx3OAjwf2uclYxv-90XYZT3bMl_d8ZTDeoGtlgtWs,11467
 pydna/contig.py,sha256=yBF4TMq1pLL0Pe3tefl2sDzNFaeSddBpytN-z-xBeSw,14971
 pydna/cre_lox.py,sha256=sOj9R8_oFPGWs68vc4jf6LqWOXjMsVSwtJaeKl6ZF2M,4476
 pydna/crispr.py,sha256=iwu0Cjskzdb2r-In9633QIxQYKGmSNVOEM_dLK6lC54,3619
 pydna/design.py,sha256=GQTyH4fKsvd6fSel0uC8DNQIulq3HMg-jYHxqsQzoLw,31743
-pydna/download.py,sha256=IX3-8CQNszzVkJdPaNxLGeGWxKRjUjK69MI9vxKpqE8,636
-pydna/dseq.py,sha256=1wSPDB2rf9lFk_UV8Fp4iaHLW4gJAbY9EZjQwOYLeHA,83462
-pydna/dseqrecord.py,sha256=z3N_0DRDJZd-nLmk5bwemSioGJ-naMGSdZsCkTBaXIc,49080
+pydna/dseq.py,sha256=cZN1Micwlgt8L73WjaIUlblb9KuQBxLzhM91cd5ijKo,83324
+pydna/dseqrecord.py,sha256=jzo8jr6i4zZ6SdJJfbabdkGh_6U8PI0Ywa9LCdn91XE,49598
 pydna/fakeseq.py,sha256=uxyu1PXF-sVasEqhmyhMcsbpTy84uUtubDiZuxHNb9c,1174
 pydna/fusionpcr.py,sha256=tfIfGGkNoZjg_dodcEx9wTc12aLRnC7J3g-Vg3Jg1uA,2821
 pydna/gateway.py,sha256=2AluaHCvgWwIq3f4ICK27iX1uSSpg97F3c_xv4o0lQM,8651
@@ -37,7 +36,7 @@ pydna/threading_timer_decorator_exit.py,sha256=D91kqjKSavWDnXyc1Fo-CwPYtbmR2DjTX
 pydna/tm.py,sha256=kM31byeBog17xi-NnVL6yXPLyZrzpXRY9J6XfEAJa9I,11083
 pydna/types.py,sha256=W1qY6TSRv1nIj9dxEwTlc4XB3778arSeMg713fPnT9U,1337
 pydna/utils.py,sha256=vYJJnJlaSTVxmbusv-WDNid54nBUqs8pTFDcJG_I7tA,24989
-pydna-5.5.5.dist-info/METADATA,sha256=7ws-79_ESLjR_OmYQ4_xKtmXroc7N8M9v93WhT6dsVQ,24626
-pydna-5.5.5.dist-info/WHEEL,sha256=3ny-bZhpXrU6vSQ1UPG34FoxZBp3lVcvK0LkgUz6VLk,88
-pydna-5.5.5.dist-info/licenses/LICENSE.txt,sha256=u8QfcsnNXZM0UCexerK_MvyA2lPWgeGyUtSYXvLG6Oc,6119
-pydna-5.5.5.dist-info/RECORD,,
+pydna-5.5.6.dist-info/METADATA,sha256=jUQ1ZJ5NYSJe71DHPnRWDYF1_pUeWqoMeOcLvYjitFE,24626
+pydna-5.5.6.dist-info/WHEEL,sha256=3ny-bZhpXrU6vSQ1UPG34FoxZBp3lVcvK0LkgUz6VLk,88
+pydna-5.5.6.dist-info/licenses/LICENSE.txt,sha256=u8QfcsnNXZM0UCexerK_MvyA2lPWgeGyUtSYXvLG6Oc,6119
+pydna-5.5.6.dist-info/RECORD,,

pydna/download.py

@@ -1,23 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-# Copyright 2013-2023 by Björn Johansson.  All rights reserved.
-# This code is part of the Python-dna distribution and governed by its
-# license.  Please see the LICENSE.txt file that should have been included
-# as part of this package.
-"""Provides a function for downloading online text files."""
-
-import textwrap
-
-from pydna._pretty import pretty_str as ps
-
-
-def download_text(url):
-    """docstring."""
-    import requests
-
-    req = requests.get(url)
-
-    result = textwrap.dedent(req.text).strip()
-    result = result.replace("\r\n", "\n").replace("\r", "\n")
-
-    return ps(result)