Fix #68

README.rst

@@ -169,7 +169,7 @@ DNA Chisel requires Python 3, and can be installed via a pip command:
 The full installation using ``dnachisel[reports]`` downloads heavier libraries
 (Matplotlib, PDF reports, sequenticon) for report generation, but is highly
 recommended to use DNA Chisel interactively via Python scripts. Also install
-`Geneblocks<https://edinburgh-genome-foundry.github.io/Geneblocks>`_ and its
+`GeneBlocks <https://edinburgh-genome-foundry.github.io/Geneblocks>`_ and its
 dependencies if you wish to include a plot of sequence edits in the report.
 
 Alternatively, you can unzip the sources in a folder and type

dnachisel/SequencePattern/SequencePattern.py

@@ -16,7 +16,7 @@
 
 
 class SequencePattern:
- """Pattern/ that will be looked for in a DNA sequence.
+ """Pattern that will be looked for in a DNA sequence.
 
  Use this class for matching regular expression patterns, and
  DnaNotationPattern for matching explicit sequences or sequences using Ns
@@ -32,22 +32,21 @@ class SequencePattern:
  ----------
 
  expression
- Any string or regular expression for matching ATGC nucleotides.
- Note that multi-nucleotides symbols such as "N" (for A-T-G-C), or "K"
+ Any string or regular expression (regex) for matching ATGC nucleotides.
+ Note that multi-nucleotide symbols such as "N" (for A-T-G-C), or "K"
  are not supported by this class, see DnaNotationPattern instead.
 
  size
- Size of the pattern, in number of characters (if none provided, the size
- of the ``pattern`` string is used).
- The ``size`` is used to determine the size of windows when performing
- local optimization and constraint solving.
- It can be important to provide the size when the
+ Size of the pattern, in number of characters. The ``size`` is used to
+ determine the size of windows when performing local optimization and
+ constraint solving. It can be important to provide the size when the
  ``pattern`` string provided represents a complex regular expression whose
  maximal matching size cannot be easily evaluated.
+ For example, if a regex is used to actively remove sites, then a size
+ should be provided to inform DNA Chisel during optimization.
 
  name
- Name of the pattern (will be displayed e.g. when the pattern is printed)
-
+ Name of the pattern (will be displayed e.g. when the pattern is printed).
  """
 
  registered_string_pattern_classes = []
@@ -100,11 +99,10 @@ def find_matches(self, sequence, location=None, forced_strand=None):
 
  # THE FUNCTION HAS BEEN CALLED WITH A LOCATION AND A FORCED STRAND
  if forced_strand is not None:
- subsequence = sequence[location.start: location.end]
+ subsequence = sequence[location.start : location.end]
  if forced_strand == 1:
  return [
- (loc + location.start)
- for loc in self.find_matches(subsequence)
+ (loc + location.start) for loc in self.find_matches(subsequence)
  ]
  if forced_strand == -1:
  subsequence = reverse_complement(subsequence)
@@ -129,7 +127,7 @@ def find_matches(self, sequence, location=None, forced_strand=None):
  else:
  return self.find_matches(sequence, location, -1)
  if strand == 0:
- matches =  self.find_matches(sequence, location, 1)
+ matches = self.find_matches(sequence, location, 1)
  if not self.is_palyndromic:
  matches += self.find_matches(sequence, location, -1)
  return matches
@@ -158,9 +156,7 @@ def find_matches_in_string(self, sequence):
  ]
 
  def __str__(self):
- return self.expression + (
- "" if self.name is None else " (%s)" % self.name
- )
+ return self.expression + ("" if self.name is None else " (%s)" % self.name)
 
  @classmethod
  def from_string(cls, string):

dnachisel/biotools/genbank_operations.py

@@ -123,7 +123,7 @@ def annotate_differences(record, reference, feature_type="misc_feature", prefix=
  else:
  locations.append([ind, ind])
  new_record = deepcopy(record)
- for (start, end) in locations:
+ for start, end in locations:
  annotate_record(
  new_record,
  location=(start, end + 1),
@@ -144,7 +144,7 @@ def annotate_pattern_occurrences(
  A Biopython record.
 
  pattern
- A DnaChisel SequencePattern object (such as DnaPAttern).
+ A DNA Chisel SequencePattern object. See SequencePattern documentation.
 
  feature_type
  Type of the annotations in the returned record.

dnachisel/builtin_specifications/AvoidPattern.py

@@ -15,7 +15,9 @@ class AvoidPattern(Specification):
  ----------
 
  pattern
- A SequencePattern or DnaNotationPattern
+ A SequencePattern or DnaNotationPattern. If a ``str`` is given, it will
+ be converted. Note that providing ``size`` may be necessary for certain
+ patterns. See SequencePattern documentation for more details.
 
  location
  Location of the DNA segment on which to enforce the pattern e.g.

dnachisel/builtin_specifications/EnforcePatternOccurence.py

@@ -22,7 +22,7 @@ class EnforcePatternOccurence(Specification):
  ----------
  pattern
  A SequencePattern or DnaNotationPattern or a string such as "AATTG",
- "BsmBI_site", etc.
+ "BsmBI_site", etc. See SequencePattern documentation for more details.
 
  occurences
  Desired number of occurrences of the pattern.
@@ -87,7 +87,10 @@ def initialized_on_problem(self, problem, role=None):
 
  def evaluate(self, problem):
  """Score the difference between expected and observed n_occurences."""
- matches = self.pattern.find_matches(problem.sequence, self.location,)
+ matches = self.pattern.find_matches(
+ problem.sequence,
+ self.location,
+ )
  score = -abs(len(matches) - self.occurences)
 
  if score == 0: