14225235949

Committed 02 Apr 2025 04:56PM UTC coverage: 90.508% (+0.5%) from 90.054%

Build # 14225235949

Build Type

push

github

Committed by

veghp

Commit Message

Bump to v3.2.14

Run Details

1 of 1 new or added line in 1 file covered. (100.0%)

101 existing lines in 35 files now uncovered.

2994 of 3308 relevant lines covered (90.51%)

0.91 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

90.91

/dnachisel/builtin_specifications/codon_optimization/CodonOptimize.py

from .HarmonizeRCA import HarmonizeRCA
from .MatchTargetCodonUsage import MatchTargetCodonUsage
from .MaximizeCAI import MaximizeCAI


def CodonOptimize(
    species=None,
    method="use_best_codon",
    location=None,
    codon_usage_table=None,
    original_species=None,
    original_codon_usage_table=None,
    boost=1.0,
):
    """Codon-optimize a coding sequence using a user-selected method.

    This pseudo-specification is actually a function which returns an instance
    of another specification class depending on the selected "method":

    - For method="use_best_codon", every codon will be replaced by the "best"
      (i.e. most frequent) synonymous codon in the target organism. This is
      equivalent to Codon Adaptation Index (CAI) optimization.
    - For method="match_codon_usage", the final sequence's codon usage will
      match as much as possible the codon usage profile of the target species
      (this method is used throughout the literature, see for instance Hale
      and Thomson 1998).
    - For method="harmonize_rca", Each codon will be replaced by a synonymous
      codon whose usage in the target organism matches the usage of the
      original codon in its host organism (as per Claassens 2017).

    Warning: always use this specification with an EnforceTranslation constraint
    defined over the same location, to preserve the amino acid sequence.


    Parameters
    ==========
    species
      Species for which the sequence will be codon-optimized.
      Either a TaxID (this requires a web connection as the corresponding table
      will be downloaded from the internet) or the name of the species to
      codon-optimize for (the name must be supported by ``python_codon_tables``
      e.g. ``e_coli``, ``s_cerevisiae``, ``h_sapiens``, ``c_elegans``,
      ``b_subtilis``, ``d_melanogaster``).
      Note that a ``codon_usage_table`` can be provided instead, or even in
      addition, for species whose codon usage table cannot be auto-imported.

    method
      Either 'use_best_codon', 'match_codon_usage', or 'harmonize_rca'
      (see above for details)

    location
      Either a DnaChisel Location or a tuple of the form (start, end, strand)
      or just (start, end), with strand defaulting to +1, indicating the
      position of the gene to codon-optimize. If not provided, the whole
      sequence is considered as the gene. The location should have a length
      that is a multiple of 3. The location strand is either 1 if the gene is
      encoded on the (+) strand, or -1 for antisense.

    codon_usage_table
      Optional codon usage table of the species for which the sequence will be
      codon-optimized, which can be provided instead of ``species``. A dict of
      the form ``{'*': {"TGA": 0.112, "TAA": 0.68}, 'K': ...}`` giving the codon
      frequency table (relative usage of each codon; frequencies add up to 1,
      separately for each amino acid). See parameter ``species`` above.

    original_species
      When the method is 'harmonize_rca', this is the native species of the
      original coding sequence. Same characteristics as parameter ``species``
      above.

    original_codon_usage_table
      Optional codon usage table of the original sequence's native species.
      A dict of the form ``{'*': {"TGA": 0.112, "TAA": 0.68}, 'K': ...}``
      giving the codon usage table.

    References
    ==========

    Claassens et. al., Improving heterologous membrane protein
    production in Escherichia coli by combining transcriptional tuning and
    codon usage algorithms. PLOS One, 2017

    Hale and Thompson, Codon Optimization of the Gene Encoding a
    Domain from Human Type 1 Neurofibromin Protein... Protein Expression and
    Purification 1998.

    """
    if method == "use_best_codon":
        return MaximizeCAI(
            species=species,
            location=location,
            codon_usage_table=codon_usage_table,
            boost=boost,
        )

    elif method == "match_codon_usage":
        return MatchTargetCodonUsage(
            species=species,
            location=location,
            codon_usage_table=codon_usage_table,
            boost=boost,
        )
    elif method == "harmonize_rca":
        return HarmonizeRCA(
            species=species,
            location=location,
            codon_usage_table=codon_usage_table,
            original_species=original_species,
            original_codon_usage_table=original_codon_usage_table,
            boost=boost,
        )
    raise ValueError(
        "`method` must be 'use_best_codon', 'match_codon_usage' "
        f"or 'harmonize_rca', not {method!r}"
    )

1	from .HarmonizeRCA import HarmonizeRCA	1✔
2	from .MatchTargetCodonUsage import MatchTargetCodonUsage	1✔
3	from .MaximizeCAI import MaximizeCAI	1✔
4
5
6	def CodonOptimize(	1✔
7	species=None,
8	method="use_best_codon",
9	location=None,
10	codon_usage_table=None,
11	original_species=None,
12	original_codon_usage_table=None,
13	boost=1.0,
14	):
15	"""Codon-optimize a coding sequence using a user-selected method.
16
17	This pseudo-specification is actually a function which returns an instance
18	of another specification class depending on the selected "method":
19
20	- For method="use_best_codon", every codon will be replaced by the "best"
21	(i.e. most frequent) synonymous codon in the target organism. This is
22	equivalent to Codon Adaptation Index (CAI) optimization.
23	- For method="match_codon_usage", the final sequence's codon usage will
24	match as much as possible the codon usage profile of the target species
25	(this method is used throughout the literature, see for instance Hale
26	and Thomson 1998).
27	- For method="harmonize_rca", Each codon will be replaced by a synonymous
28	codon whose usage in the target organism matches the usage of the
29	original codon in its host organism (as per Claassens 2017).
30
31	Warning: always use this specification with an EnforceTranslation constraint
32	defined over the same location, to preserve the amino acid sequence.
33
34
35	Parameters
36	==========
37	species
38	Species for which the sequence will be codon-optimized.
39	Either a TaxID (this requires a web connection as the corresponding table
40	will be downloaded from the internet) or the name of the species to
41	codon-optimize for (the name must be supported by ``python_codon_tables``
42	e.g. ``e_coli``, ``s_cerevisiae``, ``h_sapiens``, ``c_elegans``,
43	``b_subtilis``, ``d_melanogaster``).
44	Note that a ``codon_usage_table`` can be provided instead, or even in
45	addition, for species whose codon usage table cannot be auto-imported.
46
47	method
48	Either 'use_best_codon', 'match_codon_usage', or 'harmonize_rca'
49	(see above for details)
50
51	location
52	Either a DnaChisel Location or a tuple of the form (start, end, strand)
53	or just (start, end), with strand defaulting to +1, indicating the
54	position of the gene to codon-optimize. If not provided, the whole
55	sequence is considered as the gene. The location should have a length
56	that is a multiple of 3. The location strand is either 1 if the gene is
57	encoded on the (+) strand, or -1 for antisense.
58
59	codon_usage_table
60	Optional codon usage table of the species for which the sequence will be
61	codon-optimized, which can be provided instead of ``species``. A dict of
62	the form ``{'*': {"TGA": 0.112, "TAA": 0.68}, 'K': ...}`` giving the codon
63	frequency table (relative usage of each codon; frequencies add up to 1,
64	separately for each amino acid). See parameter ``species`` above.
65
66	original_species
67	When the method is 'harmonize_rca', this is the native species of the
68	original coding sequence. Same characteristics as parameter ``species``
69	above.
70
71	original_codon_usage_table
72	Optional codon usage table of the original sequence's native species.
73	A dict of the form ``{'*': {"TGA": 0.112, "TAA": 0.68}, 'K': ...}``
74	giving the codon usage table.
75
76	References
77	==========
78
79	Claassens et. al., Improving heterologous membrane protein
80	production in Escherichia coli by combining transcriptional tuning and
81	codon usage algorithms. PLOS One, 2017
82
83	Hale and Thompson, Codon Optimization of the Gene Encoding a
84	Domain from Human Type 1 Neurofibromin Protein... Protein Expression and
85	Purification 1998.
86
87	"""
88	if method == "use_best_codon":	1✔
89	return MaximizeCAI(	1✔
90	species=species,
91	location=location,
92	codon_usage_table=codon_usage_table,
93	boost=boost,
94	)
95
96	elif method == "match_codon_usage":	1✔
97	return MatchTargetCodonUsage(	1✔
98	species=species,
99	location=location,
100	codon_usage_table=codon_usage_table,
101	boost=boost,
102	)
103	elif method == "harmonize_rca":	1✔
104	return HarmonizeRCA(	1✔
105	species=species,
106	location=location,
107	codon_usage_table=codon_usage_table,
108	original_species=original_species,
109	original_codon_usage_table=original_codon_usage_table,
110	boost=boost,
111	)
UNCOV 112	raise ValueError(	×
113	"`method` must be 'use_best_codon', 'match_codon_usage' "
114	f"or 'harmonize_rca', not {method!r}"
115	)

Edinburgh-Genome-Foundry / DnaChisel / 14225235949

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous