Permalink
Browse files

Assorted fixes for typos, duplicate words etc.

  • Loading branch information...
1 parent 316c42a commit 723313c427f4a6d8289124db8399479b95dce49a @cbrueffer cbrueffer committed with peterjc Dec 13, 2012
View
@@ -117,7 +117,7 @@ def build_hsp():
if tool in ["TFASTX"] and len(match_seq) == len(q):
m = match_seq
#Quick hack until I can work out how -, * and / characters
- #and the apparent mix of aa and bp coordindates works.
+ #and the apparent mix of aa and bp coordinates works.
else:
m = _extract_alignment_region(match_seq, match_tags)
assert len(q) == len(m)
View
@@ -299,7 +299,7 @@ def parse(handle, format, seq_count=None, alphabet=None):
Arguments:
- handle - handle to the file, or the filename as a string
- (note older verions of Biopython only took a handle).
+ (note older versions of Biopython only took a handle).
- format - string describing the file format.
- alphabet - optional Alphabet object, useful when the sequence type
cannot be automatically inferred from the file itself
@@ -376,7 +376,7 @@ def read(handle, format, seq_count=None, alphabet=None):
Arguments:
- handle - handle to the file, or the filename as a string
- (note older verions of Biopython only took a handle).
+ (note older versions of Biopython only took a handle).
- format - string describing the file format.
- alphabet - optional Alphabet object, useful when the sequence type
cannot be automatically inferred from the file itself
@@ -217,7 +217,7 @@ def __init__(self, cmd="blastall",**kwargs):
self.parameters = [
#Sorted in the same order as the output from blastall --help
#which should make it easier to keep them up to date in future.
- #Note that some arguments are defined the the base clases (above).
+ #Note that some arguments are defined in the base classes (above).
_Option(["-p", "program"],
"The blast program to use (e.g. blastp, blastn).",
is_required=True,
View
@@ -20,7 +20,7 @@ def function_population(new_genome, num_organisms, fitness_calculator):
o num_organisms - The number of individuals we want in the population.
- o fitness_calculator -- A funtion that will calculate the fitness
+ o fitness_calculator -- A function that will calculate the fitness
of the organism when given the organisms genome.
"""
all_orgs = []
@@ -46,7 +46,7 @@ def random_population(genome_alphabet, genome_size, num_organisms,
o num_organism -- The number of organisms we want in the population.
- o fitness_calculator -- A funtion that will calculate the fitness
+ o fitness_calculator -- A function that will calculate the fitness
of the organism when given the organisms genome.
"""
all_orgs = []
@@ -105,7 +105,7 @@ def __init__(self, genome, fitness_calculator, start_fitness = None):
o genome -- A MutableSeq object representing the sequence of the
genome.
- o fitness_calculator -- A funtion that will calculate the fitness
+ o fitness_calculator -- A function that will calculate the fitness
of the organism when given the organisms genome.
o start_fitness - the starting fitness corresponding with the
@@ -591,7 +591,7 @@ def __init__(self, bp_length, features,
Note we require 0 <= start <= end <= bp_length, and within the vertical
space allocated to this segmenet lines will be places according to the
- start/end coordindates (starting from the top).
+ start/end coordinates (starting from the top).
Positive stand features are drawn on the right, negative on the left,
otherwise all the way across.
@@ -731,7 +731,7 @@ def _draw_segment(self, cur_drawing):
cap_wedge.fillColor = self.fill_color
cur_drawing.add(cap_wedge)
- #Now draw an arc for the the curved edge of the wedge,
+ #Now draw an arc for the curved edge of the wedge,
#omitting the flat end.
cap_arc = ArcPath()
cap_arc.addArc(center_x, center_y, width / 2,
View
@@ -3,7 +3,7 @@
# license. Please see the LICENSE file that should have been included
# as part of this package.
-"""handles true random numbers supplied from the the web server of
+"""handles true random numbers supplied from the web server of
fourmilab. Based on atmospheric noise. The motivation is to
support biosimulations that rely on random numbers.
"""
View
@@ -181,7 +181,7 @@ def _parse_coordinates(self, coords_trailer):
z = float(line[46:54])
except:
# Should we allow parsing to continue in permissive mode?
- # If so, what coordindates should we default to? Easier to abort!
+ # If so, what coordinates should we default to? Easier to abort!
raise PDBConstructionException("Invalid or missing coordinate(s) at line %i."
% global_line_counter)
coord = numpy.array((x, y, z), "f")
View
@@ -117,7 +117,7 @@ def __init__(self, filename):
f.close()
def __getitem__(self, key):
- """ Return an item from the indexed file. """
+ """Return an item from the indexed file."""
position = dict.__getitem__(self,key)
f = open(self.filename, "rU")
View
@@ -4,7 +4,7 @@
# as part of this package.
-""" Handle the SCOP HIErarchy files, which describe the SCOP hierarchy in
+"""Handle the SCOP HIErarchy files, which describe the SCOP hierarchy in
terms of SCOP unique identifiers (sunid).
The file format is described in the scop
@@ -21,7 +21,7 @@ class Record(object):
sunid -- SCOP unique identifiers of this node
- parent -- Parents sunid
+ parent -- Parents sunid
children -- Sequence of childrens sunids
"""
View
@@ -18,7 +18,7 @@ class Residues(object):
"""A collection of residues from a PDB structure.
This class provides code to work with SCOP domain definitions. These
- are concisely expressed as a one or more chain fragments. For example,
+ are concisely expressed as one or more chain fragments. For example,
"(1bba A:10-20,B:)" indicates residue 10 through 20 (inclusive) of
chain A, and every residue of chain B in the pdb structure 1bba. The pdb
id and brackets are optional. In addition "-" indicates every residue of
@@ -36,7 +36,7 @@
- Cigar line - 'exonerate-cigar' - parsing, indexing
On Exonerate, these output formats are not exclusive to one another. For
-example, you may have both plain text and vulgar ouput in the same file.
+example, you may have both plain text and vulgar output in the same file.
ExonerateIO can only handle one of these at a time, however. If you have a file
containing both plain text and vulgar lines, for example, you have to pick
either 'exonerate-text' or 'exonerate-vulgar' to parse it.
@@ -44,7 +44,7 @@
accordingly to fit SearchIO's object model. If HmmerIO sees that the output file
to parse was written by hmmsearch or phmmer, all 'hmm' coordinates will be the
hit coordinates and 'ali' coordinates will be the query coordinates. Conversely,
-if the the HMMER flavor is hmmscan, 'hmm' will be query and 'ali' will be hit.
+if the HMMER flavor is hmmscan, 'hmm' will be query and 'ali' will be hit.
This is why the 'hmmer3-domtab' format has to be specified with the source HMMER
flavor. The parsers need to know which is the hit and which is the query.
@@ -192,7 +192,7 @@ def _parse_hit(self, qid):
'bitscore': float(row[1]),
'bias': float(row[2]),
# row[3:6] is not parsed, since the info is available
- # at the the HSP level
+ # at the HSP level
'domain_exp_num': float(row[6]),
'domain_obs_num': int(row[7]),
'description': row[9],
@@ -34,7 +34,7 @@ class HSP(_BaseHSP):
with one HSPFragments are BLAST, HMMER, and FASTA. Other programs such as
BLAT or Exonerate may produce HSPs containing more than one HSPFragment.
However, their native terminologies may differ: in BLAT these fragments
- are called 'blocks' while in in Exonerate they are called exons or NER.
+ are called 'blocks' while in Exonerate they are called exons or NER.
Here are examples from each type of HSP. The first one comes from a BLAST
search:
@@ -165,7 +165,7 @@ class QueryResult(_BaseSearchObject):
Hit(id='gi|301171322|ref|NR_035857.1|', query_id='33211', 2 hsps)
If you need access to all the hits in a QueryResult object, you can get
- them in a list using the `hits` property. Similary, access to all hit IDs is
+ them in a list using the `hits` property. Similarly, access to all hit IDs is
available through the `hit_keys` property.
>>> qresult.hits
View
@@ -73,7 +73,7 @@ class SeqFeature(object):
o ref_db - A different database for the reference accession number.
Note this is a shortcut for the reference property of the location
o qualifiers - A dictionary of qualifiers on the feature. These are
- analagous to the qualifiers from a GenBank feature table. The keys of
+ analogous to the qualifiers from a GenBank feature table. The keys of
the dictionary are qualifier names, the values are the qualifier
values.
o sub_features - Additional SeqFeatures which fall under this 'parent'
@@ -529,8 +529,8 @@ class FeatureLocation(object):
Note that for a parent sequence of length n, the FeatureLocation
start and end must satisfy the inequality 0 <= start <= end <= n.
This means even for features on the reverse strand of a nucleotide
- sequence, we expect the 'start' coordindate to be less than the
- 'end' coordindate.
+ sequence, we expect the 'start' coordinate to be less than the
+ 'end' coordinate.
>>> from Bio.SeqFeature import FeatureLocation
>>> r = FeatureLocation(122, 150, strand=-1)
@@ -947,7 +947,7 @@ class WithinPosition(int, AbstractPosition):
This allows dealing with a position like ((1.4)..100). This
indicates that the start of the sequence is somewhere between 1
- and 4. Since this is a start coordindate, it should acts like
+ and 4. Since this is a start coordinate, it should acts like
it is at position 1 (or in Python counting, 0).
>>> p = WithinPosition(10,10,13)
View
@@ -403,7 +403,7 @@ def _write_single_line(self, tag, text):
text.replace("\n", " ")))
def _write_multi_line(self, tag, text):
- """Used in the the 'header' of each GenBank record."""
+ """Used in the 'header' of each GenBank record."""
#TODO - Do the line spliting while preserving white space?
max_len = self.MAX_WIDTH - self.HEADER_WIDTH
lines = self._split_multi_line(text, max_len)
View
@@ -451,7 +451,7 @@ def parse(handle, format, alphabet=None):
r"""Turns a sequence file into an iterator returning SeqRecords.
- handle - handle to the file, or the filename as a string
- (note older verions of Biopython only took a handle).
+ (note older versions of Biopython only took a handle).
- format - lower case string describing the file format.
- alphabet - optional Alphabet object, useful when the sequence type
cannot be automatically inferred from the file itself
@@ -561,7 +561,7 @@ def read(handle, format, alphabet=None):
"""Turns a sequence file into a single SeqRecord.
- handle - handle to the file, or the filename as a string
- (note older verions of Biopython only took a handle).
+ (note older versions of Biopython only took a handle).
- format - string describing the file format.
- alphabet - optional Alphabet object, useful when the sequence type
cannot be automatically inferred from the file itself
View
@@ -86,7 +86,7 @@ def GC123(seq):
def GC_skew(seq, window = 100):
- """Calculates GC skew (G-C)/(G+C) for multuple windows along the sequence.
+ """Calculates GC skew (G-C)/(G+C) for multiple windows along the sequence.
Returns a list of ratios (floats), controlled by the length of the sequence
and the size of the window.
@@ -93,9 +93,9 @@ class Reference(object):
Members:
number Number of reference in an entry.
- positions Describes extent of work. list of strings.
+ positions Describes extent of work. List of strings.
comments Comments. List of (token, text).
- references References. List of (dbname, identifier)
+ references References. List of (dbname, identifier).
authors The authors of the work.
title Title of the work.
location A citation for the work.
View
@@ -447,7 +447,7 @@ def _get_taxon_id_from_ncbi_lineage(self, taxonomic_lineage):
- ScientificName (string)
(and that is all at the time of writing)
- This method will record all the lineage given, returning the the taxon id
+ This method will record all the lineage given, returning the taxon id
(database key, not NCBI taxon id) of the final entry (the species).
"""
ncbi_taxon_id = taxonomic_lineage[-1]["TaxId"]
View
@@ -59,7 +59,7 @@ and removed in Release 1.59.
Bio.Parsers and Bio.Parsers.spark
=================================
This module was a copy of John Aycock's SPARK parser included with Biopython
-soley for use in Bio.GenBank.LocationParser. Declared obsolete in Release
+solely for use in Bio.GenBank.LocationParser. Declared obsolete in Release
1.55, deprecated in Release 1.56, and removed in Release 1.59.
Bio.Restriction.DNAUtils and check_bases
@@ -398,7 +398,7 @@ Function 'reverse' in Bio.SeqUtils was deprecated in Release 1.54, and
removed in Release 1.58. Instead just use the string's slice method with
a step of minus one.
-Funtions GC_Frame, fasta_uniqids, apply_on_multi_fasta, and
+Functions GC_Frame, fasta_uniqids, apply_on_multi_fasta, and
quicker_apply_on_multi_fasta were deprecated in Release 1.55, and removed
in Release 1.58.
@@ -424,7 +424,7 @@ Use Bio.SeqUtils instead.
Bio.SVM
=======
Deprecated as of Release 1.30, removed in Release 1.42.
-The Support Vector Machine code in Biopython has been superceeded by a
+The Support Vector Machine code in Biopython has been superseded by a
more robust (and maintained) SVM library, which includes a python
interface. We recommend using LIBSVM:
Oops, something went wrong.

0 comments on commit 723313c

Please sign in to comment.