Package schrodinger :: Package application :: Package msv :: Package domain :: Module alignment :: Class BaseAlignment

Class BaseAlignment

object --+
         |
        BaseAlignment

Known Subclasses:

ProteinAlignment

Abstract base class for classes which handle alignment of various sequences and corresponding annotations.

This is a pure domain object intended to make it easy to work with aligned collections of sequences.

Some methods are decorated with @msv_utils.const in order to make it easy to write a wrapper for this class that supports undo/redo operations.

Instance Methods

[hide private]

__init__(self, sequences=None)
x.__init__(...) initializes x; see help(type(x)) for signature

__len__(self)
Returns the number of sequences in the alignment

__iter__(self)
Returns an iterable of the sequences held in the alignment

__contains__(self, seq)
Returns whether the sequence is present in the alignment

__getitem__(self, index)
Returns the sequence at the index in the alignment

_getTextFormattedAlignment(self)
Returns a formatted list of strings with detailed alignment information

_getAlignmentDescription(self)
Returns a formatted description of the alignment

__str__(self)
Returns a str representation of the alignment

str

__repr__(self)
Returns: A str representation of the alignment

__add__(self, other)
Adds another alignment to this one

__deepcopy__(self, memo)
We should be able to copy an alignment, getting back an alignment with all the essential data in the original alignment and sharing no references with it

getResidueData(self, seqnum, index, annotation=None)
Returns residue-level data for the specified sequence at the specified index in the alignment, or None if no data is available.

iterResidues(self)
Yields a sequence of schrodinger.application.msv.domain.residue.Residue objects in the alignment, omitting gaps.

getGlobalAnnotationData(self, index, annotation)
Returns column-level annotation data at an index in the alignment

notifyResidueSelection(self, residues)
Notify any listeners of a residue selection by emitting a ResidueSelection.

list of int

getVisibleSeqIndices(self)
Return a list of the indices of all visible sequences in the alignment.

list of int

getHiddenSeqIndices(self)
Return a list of the indices of all sequences in the alignment that have an associated PT entry ID but are not currently visible in the Workspace.

notifyResDisplayChanged(self, displayed, undisplayed)
Notify any listeners of a residue display change by emitting a signal.

notifySequenceVisibilityChanged(self, seq, display=True)
Notify any listeners that a request to change visibility of an entire sequence has been made.

int

getSeqIndex(self, seq)
Returns: The index of the requested sequence

reorderSequences(self, seq_indices)
Reorder the sequences in the alignment using the specified list of indices

int or NoneType

_recalculateLength(self, omit, extra_length=None)
Determine what the length of the alignment would be if we removed one sequence.

_monitorSequence(self, seq)
Monitor changes in the specified sequence, which has been stored at the specified index in self._sequences.

_stopMonitoringSequence(self, seq, slots)
Stop monitoring for changes in the specified sequence

_sequenceLengthAboutToChange(self, seq, old_seq_length, new_seq_length)
Respond to a sequence lengthAboutToChange signal by emitting signals.alignmentLengthAboutToChange if necessary.

_sequenceLengthChanged(self, seq, old_seq_length, new_seq_length)
Respond to a sequence lengthChanged signal by emitting signals.alignmentLengthChanged and signals.sequenceResiduesChanged as necessary.

int or NoneType

_checkAlignmentLength(self, seq, old_seq_length, new_seq_length)
Determine what the length of the alignment will be if we changed the length of the specified sequence

addSeq(self, seq, index=None)

addSeqs(self, sequences, start=None)
Add multiple sequences to the alignment

addSeqsByIndices(self, seq_index_map)
Insert a sequences at the specified indices in the alignment.

removeSeq(self, seq)
Remove a sequence from the alignment

removeSeqs(self, seqs)
Remove multiple sequences from the alignment

removeSeqByIndex(self, index)
Remove a Sequence from the alignment

replaceSeq(self, seq, index)
Replace the sequence at the specified index with the elements in the specified sequence

tuple of dict and list

_getAddOrReplaceSeqs(self, seqs, identifier_func)
Inspect an iterable of seqs and use an identifier_func to return a two member tuple consisting of (to_replace, to_add).

addOrReplaceSeqs(self, seqs, identifier_func)
Given seqs and an identifier_func, replaces seqs in the alignment matching the identifier_func and appends any additional seqs to the alignment

removeAllSeqs(self)
Clears the entire alignment of sequences

setQuerySeq(self, seq)
Set the specified sequence as the query sequence.

Sequence or None

getQuerySeq(self)
Returns the sequence that has been set as query sequence or None if there is no query sequence.

bool

isQuerySeq(self, seq)
Return whether or not a sequence is set as a query sequence.

list of (sequence index, residue index) tuples

getResidueIndices(self, residues)
Returns the indices (in the alignment) of the specified residues

ResidueSelection

makeResidueSelection(self, residues)
Returns a residue selection object matching the specified residues

_removeResidues(self, selection)
Given a selection, removes the residues in the alignment matching it

removeResidues(self, residues)
Removes the specified residues from the alignment and emits the signals.residuesRemoved signal with the selection

mutateResidues(self, mutations)
Mutate the residues at the specified locations in the alignment

replaceResiduesWithGaps(self, residues)
Replaces the specified residues with gaps

addResidues(self, selection)
Adds the specified residues to the alignment

BaseAligment

getSubalignment(self, start, end)
Return another alignment containing the elements within the specified start and end indices

removeSubalignment(self, start, end)
Remove a block of the subalignment from the start to end points, including column locks in that region

insertSubalignment(self, aln, start)
Insert an alignment into the current alignment at the specified index

appendSubalignment(self, aln)
Append an alignment to this one

replaceSubalignment(self, aln, start, end)
Replace a subsection of the alignment indicated by start and end indices with the specified alignment

list

getGaps(self)
Returns a list of gap indices lists

list

getGapsByKeyFunc(self, key_func)
Given a key function to uniquely identify residues, build a list of lists with gap information for each sequence in the alignment

list of lists of int

getGapIndicesByKeyFunc(self, gap_info, key_func)
Converts a gap_info list and key func into a list of gap indices

list

getTerminalGaps(self)
Returns the indices of terminal gaps in all the sequences

removeGaps(self, gap_indices)

removeAllGaps(self)
Removes all the gaps of the sequences in the alignment.

removeTerminalGaps(self)
Removes the gaps from the ends of every sequence in the alignment

_validateGapIndices(self, gap_indices)
Check for gaps in locked columns

_adjustGapsInSubalignments(self, method_name, gap_indices)
Utility method that iterates through alternating locked and unlocked stretches of an alignment in reverse order and calling the specified method on the sub regions, padding all but the last region.

addGaps(self, gap_indices)
Adds gaps to the alignment

setGaps(self, gap_indices)
Sets gaps on the alignment

list

_getGapOnlyColumns(self)
Returns a list of lists of indices for unlocked columns that contain only gaps

minimizeAlignment(self)
Minimizes the alignment, i.e.

list

getColumn(self, index, omit_gaps=False)
Returns single alignment column at index position.

columns(self, omit_gaps=False)
Returns a range of alignment columns or all columns if indices are not specified.

_updateColumnSameResCache(self)
Update the cache of whether each column has all the same residue or not

bool

columnHasAllSameResidues(self, index)
Return whether or not the column at a specified index has all the same residues (excluding gaps).

_updateResMatchesQueryResCache(self)
Update the cache of whether a given residue matches the query residue at that column in the alignment.

bool

resMatchesQueryRes(self, row_index, col_index)
Return True if the residue of a sequence at a column in the alignment matches the query residue.

set

lockedColumns(self)
Returns a set with indices of locked columns.

setLockedColumns(self, columns, lock=True, reset=False)
Sets the columns to the specified lock state

bool

alignmentLocked(self)
Whether every column in the alignment is locked

setAllLocks(self, lock=True)
Convenience method to set all the locks to the specified lock state at once

list

_getRegions(self)
Returns a list of _Region objects containing information of locked and unlocked stretches of the alignment

getIdentities(self, omit_gaps=True)
Returns an alignment-length list of bools indicating which columns have identical residues

getSimilarityScore(self, seq)
Returns a sequence length array of similarity scores against the query sequence

getAlignedBlocks(self)
Returns the indices of aligned blocks (regions without gaps).

getFrequencies(self, exclude=None, consider_gaps=False)
Returns a dict mapping residues types to the frequency in the alignment

getEntropy(self, frequencies)
Returns an alignment length array of residue entropy scores

list

findPattern(self, pattern)
Finds a specified PROSITE pattern in all sequences.

list of int

getRedundantSequences(self, value)
Returns the indices of sequences below a specified identity threshold value.

calculateMatrix(self)
Calculates a substitution matrix based on the current alignment.

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__, __sizeof__, __subclasshook__

Class Methods

[hide private]

_insertGaps(cls, sequences, gap_boundaries)
Inserts gaps represented as "gap boundaries" (indices of residues that immediately follow the gaps) to a list of sequences.

mergePairwiseAlignments(cls, sequence_pairs)
Merges several pairwise alignments into one flat alignment while preserving relative residue positions.

Static Methods

[hide private]

list of int

getReversedSequenceOrdering(seq_indices)
Given a new ordering for sequences in an alignment, return an ordering that will restore the original order of sequences.

padAlignment(aln)
Insert gaps into an alignment so that it forms a rectangular block

Properties

[hide private]

global_annotations
Returns the alignment-level annotations available for the alignment

seq_annotations
Returns the sequence-level annotations available for sequences held in the alignment

all_annotations
Return a list of all annotations types in this alignment

max_length

Inherited from object: __class__

Method Details

[hide private]

init(self, sequences=None)
(Constructor)

x.__init__(...) initializes x; see help(type(x)) for signature

Parameters:

sequences (list) - An optional iterable of sequences

Overrides: object.__init__

len(self)
(Length operator)

Returns the number of sequences in the alignment

Decorators:

@msv_utils.const

iter(self)

Returns an iterable of the sequences held in the alignment

Decorators:

@msv_utils.const

contains(self, seq)
(In operator)

Returns whether the sequence is present in the alignment

Decorators:

@msv_utils.const

getitem(self, index)
(Indexing operator)

Returns the sequence at the index in the alignment

Decorators:

@msv_utils.const

_getTextFormattedAlignment(self)

Returns a formatted list of strings with detailed alignment information

Decorators:

@msv_utils.const

_getAlignmentDescription(self)

Returns a formatted description of the alignment

Decorators:

@msv_utils.const

str(self)
(Informal representation operator)

Returns a str representation of the alignment

This is fairly detailed since it is very useful for debugging

Decorators:

@msv_utils.const

Overrides: object.__str__

repr(self)
(Representation operator)

repr(x)

Returns: str

A str representation of the alignment

Decorators:

@msv_utils.const

Overrides: object.__repr__

add(self, other)
(Addition operator)

Adds another alignment to this one

Parameters:

other (schrodinger.application.msv.domain.alignment.Alignment
NOTE: Undo is currently not supported for this operation
) - Another alignment with the same number of sequences

Decorators:

@msv_utils.const

getResidueData(self, seqnum, index, annotation=None)

Returns residue-level data for the specified sequence at the specified index in the alignment, or None if no data is available.

If annotation is specified, the residue-level information for the residue is returned. If not, the residue object itself is returned.

Parameters:

seqnum (int) - The index of the sequence in the alignment
index (int) - The index of the residue in the sequence
annotation (enum.Enum) - An enum representing the requested annotation, if any

Decorators:

@msv_utils.const

iterResidues(self)

Yields a sequence of schrodinger.application.msv.domain.residue.Residue objects in the alignment, omitting gaps.

Decorators:

@msv_utils.const

getGlobalAnnotationData(self, index, annotation)

Returns column-level annotation data at an index in the alignment

Parameters:

index (int) - The index in the alignment
annotation (enum.Enum) - An enum representing the requested annotation, if any

Decorators:

@msv_utils.const

notifyResidueSelection(self, residues)

Notify any listeners of a residue selection by emitting a ResidueSelection.

Parameters:

residues (list of schrodinger.application.msv.domain.residue. Residue) - A list of selected residues

Decorators:

@msv_utils.const

getVisibleSeqIndices(self)

Return a list of the indices of all visible sequences in the alignment.

Returns: list of int

List of visible sequence indices

Decorators:

@msv_utils.const

getHiddenSeqIndices(self)

Return a list of the indices of all sequences in the alignment that have an associated PT entry ID but are not currently visible in the Workspace.

Returns: list of int

List of hidden sequence indices

Decorators:

@msv_utils.const

notifyResDisplayChanged(self, displayed, undisplayed)

Notify any listeners of a residue display change by emitting a signal.

Parameters:

displayed (list of schrodinger.application.msv.domain.residue. Residue) - A list of residues that have been displayed
undisplayed (list of schrodinger.application.msv.domain.residue. Residue) - A list of undisplayed residues

Decorators:

@msv_utils.const

notifySequenceVisibilityChanged(self, seq, display=True)

Notify any listeners that a request to change visibility of an entire sequence has been made.

Parameters:

seq (sequence.Sequence) - Sequence whose visibility is changing
display (bool) - Whether the sequence is being displayed.

Decorators:

@msv_utils.const

getSeqIndex(self, seq)

Parameters:

seq (sequence.Sequence) - The requested sequence

Returns: int

The index of the requested sequence

Decorators:

@msv_utils.const

getReversedSequenceOrdering(seq_indices)
Static Method

Given a new ordering for sequences in an alignment, return an ordering that will restore the original order of sequences.

Given a an alignment [a, b, c, d, e] an ordering of [3, 1, 4, 2, 0] will rearrange the sequences into [d, b, e, c, a]. We need an ordering of [4, 1, 3, 0, 2] to restore the original arrangement of [a, b, c, d, e]. This method is used in undo operations.

Parameters:

seq_indices - A list with the new indices for sequences

Returns: list of int

An ordering list that will restore the original arrangement of sequences in the alignment

reorderSequences(self, seq_indices)

Reorder the sequences in the alignment using the specified list of indices

In the undoable version of this class, the private function is needed to perform the operation in an undoable operation.

Parameters:

seq_indices - A list with the new indices for sequences

Raises:

ValueError - In the event that the list of indices does not match the length of the alignment

_recalculateLength(self, omit, extra_length=None)

Determine what the length of the alignment would be if we removed one sequence.

Parameters:

omit (sequence.Sequence) - The sequence to omit
extra_length (int) - An additional sequence length to include in the calculation

Returns: int or NoneType

The calculated alignment length if the length is going to change. None otherwise.

Decorators:

@msv_utils.const

_monitorSequence(self, seq)

Monitor changes in the specified sequence, which has been stored at the specified index in self._sequences.

Parameters:

seq (sequence.Sequence) - The sequence to monitor

_stopMonitoringSequence(self, seq, slots)

Stop monitoring for changes in the specified sequence

Parameters:

seq (sequence.Sequence) - The sequence to stop monitoring
slots (tuple) - A tuple containing all slots to disconnect

_sequenceLengthAboutToChange(self, seq, old_seq_length, new_seq_length)

Respond to a sequence lengthAboutToChange signal by emitting signals.alignmentLengthAboutToChange if necessary.

Parameters:

seq (sequence.Sequence) - The sequence that's about to be modified
old_seq_length (int) - The current length of the sequence
new_seq_length (int) - The new length of the sequence

_sequenceLengthChanged(self, seq, old_seq_length, new_seq_length)

Respond to a sequence lengthChanged signal by emitting signals.alignmentLengthChanged and signals.sequenceResiduesChanged as necessary.

Parameters:

seq (sequence.Sequence) - The sequence that's been modified
old_seq_length (int) - The old length of the sequence
new_seq_length (int) - The current length of the sequence

_checkAlignmentLength(self, seq, old_seq_length, new_seq_length)

Determine what the length of the alignment will be if we changed the length of the specified sequence

Parameters:

seq (sequence.Sequence) - The sequence that will change length
old_seq_length (int) - The old length of the sequence
new_seq_length (int) - The new length of the sequence

Returns: int or NoneType

If the alignment will change length, returns the new alignment length. Otherwise, returns None.

addSeq(self, seq, index=None)

Parameters:

seq (sequence.Sequence) - The sequence to add
start (int) - The index at which to insert; if None, seq is appended

addSeqs(self, sequences, start=None)

Add multiple sequences to the alignment

Parameters:

sequences (list of sequence.Sequence) - Sequences to add
start (int) - The index at which to insert; if None, seq is appended

addSeqsByIndices(self, seq_index_map)

Insert a sequences at the specified indices in the alignment. The sequences will be added from lowest to highest to allow for specification of indexes that may be out of range of the current alignment until lower-indexed sequences have been added. Note that indexes that remain out of range will result in their corresponding sequence simply being appended to the end of the alignment.

Parameters:

seq_index_map - Map of insertion indices to sequences to be added. @type seq_index_map dict of {int: sequence.Sequence}

removeSeq(self, seq)

Remove a sequence from the alignment

Parameters:

seq (sequence.Sequence) - The sequence to remove

removeSeqByIndex(self, index)

Remove a Sequence from the alignment

Parameters:

index (int) - The index of the sequence to remove

replaceSeq(self, seq, index)

Replace the sequence at the specified index with the elements in the specified sequence

Note that this leaves the original sequence itself intact so that it continues to be monitored

Parameters:

seq (iterable of schrodinger.application.msv.domain.residue. Residue) - The sequence whose elements we use
index (int) - The index of the sequence to replace

_getAddOrReplaceSeqs(self, seqs, identifier_func)

Inspect an iterable of seqs and use an identifier_func to return a two member tuple consisting of (to_replace, to_add).

to_replace is a dictionary mapping sequence indices with new sequences to_add is a list of sequences to append to the alignment

Parameters:

seqs (iterable of schrodinger.application.msv.domain.sequence. Sequence) - The sequences to inspect
identifier_func (callable) - A key function that takes a sequence and returns a unique identifier for it

Returns: tuple of dict and list

A tuple of to_replace dict and to_add list

Decorators:

@msv_utils.const

addOrReplaceSeqs(self, seqs, identifier_func)

Given seqs and an identifier_func, replaces seqs in the alignment matching the identifier_func and appends any additional seqs to the alignment

Parameters:

seqs (iterable of schrodinger.application.msv.domain.sequence. Sequence) - The sequences to add to the alignment
identifier_func (callable) - A key function to uniquely identify sequences

setQuerySeq(self, seq)

Set the specified sequence as the query sequence.

Parameters:

seq (sequence) - Sequence to set as query sequence

getQuerySeq(self)

Returns the sequence that has been set as query sequence or None if there is no query sequence.

Returns: Sequence or None

The query sequence or None

Decorators:

@msv_utils.const

isQuerySeq(self, seq)

Return whether or not a sequence is set as a query sequence.

Parameters:

seq (Sequence) - Sequence to check

Returns: bool

True if a query sequence has been set, False otherwise.

Decorators:

@msv_utils.const

getResidueIndices(self, residues)

Returns the indices (in the alignment) of the specified residues

Parameters:

residues ()

Returns: list of (sequence index, residue index) tuples

A list of (int, int)

Decorators:

@msv_utils.const

makeResidueSelection(self, residues)

Returns a residue selection object matching the specified residues

Parameters:

residues (list) - A list of residues

Returns: ResidueSelection

An object containing selection information

Decorators:

@msv_utils.const

_removeResidues(self, selection)

Given a selection, removes the residues in the alignment matching it

Parameters:

selection (ResidueSelection) - A selection of residues

removeResidues(self, residues)

Removes the specified residues from the alignment and emits the signals.residuesRemoved signal with the selection

Parameters:

residues (list) - The residues to remove

mutateResidues(self, mutations)

Mutate the residues at the specified locations in the alignment

Note that the individual sequences will emit a signal announcing the mutation

Parameters:

mutations (list of tuples (seq_i, res_i, replacement))

replaceResiduesWithGaps(self, residues)

Replaces the specified residues with gaps

Parameters:

residues (list) - A list of residues to replace with gaps

addResidues(self, selection)

Adds the specified residues to the alignment

Parameters:

selection (ResidueSelection) - A selection of residues

getSubalignment(self, start, end)

Return another alignment containing the elements within the specified start and end indices

Parameters:

start (int) - The index at which the subalignment should start
end (int) - The index at which the subalignment should end

Returns: BaseAligment

An alignment corresponding to the start and end point specified

Decorators:

@msv_utils.const

removeSubalignment(self, start, end)

Remove a block of the subalignment from the start to end points, including column locks in that region

Parameters:

start (int) - The start index of the columns to remove
end (int) - The end index of the columns to remove

insertSubalignment(self, aln, start)

Insert an alignment into the current alignment at the specified index

Parameters:

aln (BaseAlignment) - The alignment to insert
start (int) - The index at which to insert the alignment

appendSubalignment(self, aln)

Append an alignment to this one

Parameters:

aln (BaseAlignment or list of Sequence) - The alignment to append

replaceSubalignment(self, aln, start, end)

Replace a subsection of the alignment indicated by start and end indices with the specified alignment

Parameters:

aln (BaseAlignment) - The alignment to insert
start (int) - The index at which to insert the alignment

getGaps(self)

Returns a list of gap indices lists

Returns: list

A list of lists of ints

Decorators:

@msv_utils.const

getGapsByKeyFunc(self, key_func)

Given a key function to uniquely identify residues, build a list of lists with gap information for each sequence in the alignment

Gap information consists of (key for residue, number of gaps preceding it)

Parameters:

key_func (function) - callable that takes a residue and returns a key

Returns: list

A list of lists with gaps information for each sequence in the alignment

Decorators:

@msv_utils.const

getGapIndicesByKeyFunc(self, gap_info, key_func)

Converts a gap_info list and key func into a list of gap indices

Gap information consists of (key for residue, number of gaps preceding it)

Parameters:

gap_info (list) - list of list of tuples
key_func (function) - callable that takes a residue and returns a key

Returns: list of lists of int

A list of gaps for each sequence in the alignment

Decorators:

@msv_utils.const

getTerminalGaps(self)

Returns the indices of terminal gaps in all the sequences

Returns: list

A list of lists of ints

Decorators:

@msv_utils.const

removeGaps(self, gap_indices)

Parameters:

gap_indices (list of list of ints) - Indices of gaps to remove

removeAllGaps(self)

Removes all the gaps of the sequences in the alignment. This also unlocks all columns

_validateGapIndices(self, gap_indices)

Check for gaps in locked columns

Parameters:

gap_indices (list of lists) - A list of lists of gap indices

Decorators:

@msv_utils.const

_adjustGapsInSubalignments(self, method_name, gap_indices)

Utility method that iterates through alternating locked and unlocked stretches of an alignment in reverse order and calling the specified method on the sub regions, padding all but the last region.

Parameters:

method_name (str) - the requested operation
gap_indices (list of lists of integers
Suppose we have the following alignment:

A C G T A P ~ G T A ~ P A ~ G T A G

If we wish to insert a gap at 0 in the first sequence, at 1 in the second, and at 4 in the third, the result will look like this:

~ A C G T A P ~ ~ G T A ~ P A ~ G T ~ A G

Suppose we lock column 3 (T A T). The alignment is now divided into three subalignments that need to be preserved:

[A C G] [T] [A P] [~ G T] [A] [~ P] [A ~ G] [T] [A G]

This complicates gap insertion: We now need to pad the region before the lock in the third sequence in order to preserve the regions intact:

[~ A C G] [T] [A P] [~ ~ G T] [A] [~ P] [A ~ G ~] [T] [~ A G]

Adding the padding at position 3 in the third sequence requires us to change the gap index of 4 to 5.

To handle this, we iterate through the different alternating locked and unlocked regions of the alignment from back to front, padding all but the last region in order to preserve the regions intact.
) - indices of gaps used by method

addGaps(self, gap_indices)

Adds gaps to the alignment

Parameters:

gap_indices - A list of lists of gap indices, one for each sequence in the alignment.

Note: the length of the gap_indices list must match the number of sequences in the alignment.

setGaps(self, gap_indices)

Sets gaps on the alignment

Parameters:

gap_indices - A list of lists of gap indices, one for each sequence in the alignment.

padAlignment(aln)
Static Method

Insert gaps into an alignment so that it forms a rectangular block

Parameters:

aln (schrodinger.application.msv.domain.Alignment) - An alignment to pad

_getGapOnlyColumns(self)

Returns a list of lists of indices for unlocked columns that contain only gaps

Returns: list

List of list of indices

Decorators:

@msv_utils.const

minimizeAlignment(self)

Minimizes the alignment, i.e. removes all gaps from the gap-only columns.

_insertGaps(cls, sequences, gap_boundaries)
Class Method

Inserts gaps represented as "gap boundaries" (indices of residues that immediately follow the gaps) to a list of sequences. The gap indices correspond to first sequence in the list, but they come from a different alignment.

Parameters:

sequences (List of sequences to add gaps to.) - list of Sequence
gaps (list of int) - List of gaps.

mergePairwiseAlignments(cls, sequence_pairs)
Class Method

Merges several pairwise alignments into one flat alignment while preserving relative residue positions. The original sequences are modified. After executing this function, all query sequences (first pair members) will be identical.

Example. Let's assume we have three pairwise query/template alignments:

Q1: ACDEFGHI T1: ~~DEF~~~

Q2: ~~~ACDEFGHI T2: TTT~~DE~~H~

Q3: ACDEF~~GHI~ T3: ACD~~PPGH~Y

Note the query sequence is identical in all cases, but it has gaps in different positions. After running mergePairwiseAlignments, the result is:

Q1: ~~~ACDEF~~GHI T1: ~~~~~DEF~~~~~

Q2: ~~~ACDEF~~GHI T2: TTT~~DE~~~~H~

Q3: ~~~ACDEF~~GHI~ T3: ~~~ACD~~PPGH~Y

Now the queries have gaps in identical positions, and aligned residues are in positions equivalent to these in original alignments.

Parameters:

sequence_pairs (list of list of sequences) - List of [query, template] pairs.

getColumn(self, index, omit_gaps=False)

Returns single alignment column at index position. Optionally, filters out gaps if omit_gaps is True.

Parameters:

index (int) - The index in the alignment
omit_gaps (bool) - Whether to omit the gaps

Returns: list

Single alignment column at index position.

Decorators:

@msv_utils.const

columns(self, omit_gaps=False)

Returns a range of alignment columns or all columns if indices are not specified.

Parameters:

omit_gaps (bool) - Whether to omit gaps

Decorators:

@msv_utils.const

columnHasAllSameResidues(self, index)

Return whether or not the column at a specified index has all the same residues (excluding gaps).

Note that if any unknown residues are present, the column will not be considered to be of all the same residue type.

Parameters:

index (int) - Index to check for uniformity

Returns: bool

True if the column is of uniform identity, False otherwise.

Decorators:

@msv_utils.const

_updateResMatchesQueryResCache(self)

Update the cache of whether a given residue matches the query residue at that column in the alignment.

Note that if a residue of the query sequence at a given index is unknown, no other residues will be seen as matching the query at that index.

resMatchesQueryRes(self, row_index, col_index)

Return True if the residue of a sequence at a column in the alignment matches the query residue.

Parameters:

row_index (int) - Index of the sequence containing the residue to check
col_index (int) - Column of the residue to check

Returns: bool

True if the residue at the specified index matches the reference, False otherwise.

Decorators:

@msv_utils.const

lockedColumns(self)

Returns a set with indices of locked columns.

Returns: set

A set of indices

The set is a copy of our internal set, so modifying it has no effect on our private attribute

Decorators:

@msv_utils.const

setLockedColumns(self, columns, lock=True, reset=False)

Sets the columns to the specified lock state

Parameters:

columns (iterable) - an iterable of columns to set, specified by index
lock (bool) - Whether to lock or unlock columns
reset (bool) - Whether to reset the locks or add to existing ones

alignmentLocked(self)

Whether every column in the alignment is locked

Returns: bool

Whether the alignment is locked

Decorators:

@msv_utils.const

setAllLocks(self, lock=True)

Convenience method to set all the locks to the specified lock state at once

Parameters:

lock (bool) - Whether to lock or unlock the specified columns

_getRegions(self)

Returns a list of _Region objects containing information of locked and unlocked stretches of the alignment

Returns: list

A list of _Region objects

Decorators:

@msv_utils.const

getIdentities(self, omit_gaps=True)

Returns an alignment-length list of bools indicating which columns have identical residues

Parameters:

omit_gaps (bool) - Whether gaps should be excluded from a column.

Decorators:

@msv_utils.const

getSimilarityScore(self, seq)

Returns a sequence length array of similarity scores against the query sequence

Gaps in the sequences are coded as None values.

Decorators:

@msv_utils.const

getAlignedBlocks(self)

Returns the indices of aligned blocks (regions without gaps).

Decorators:

@msv_utils.const

getFrequencies(self, exclude=None, consider_gaps=False)

Returns a dict mapping residues types to the frequency in the alignment

Parameters:

exclude (list) - A list of sequences to exclude
consider_gaps (bool) - Whether to consider gaps in calculating frequences

Decorators:

@msv_utils.const

getEntropy(self, frequencies)

Returns an alignment length array of residue entropy scores

Decorators:

@msv_utils.const

findPattern(self, pattern)

Finds a specified PROSITE pattern in all sequences.

Parameters:

pattern (basestring) - The pattern to find

Returns: list

A list of pattern matches

Decorators:

@msv_utils.const

getRedundantSequences(self, value)

Returns the indices of sequences below a specified identity threshold value.

Returns: list of int

The indices of sequences in the alignment below specified identity threshold

Decorators:

@msv_utils.const

calculateMatrix(self)

Calculates a substitution matrix based on the current alignment.

Decorators:

@msv_utils.const

Property Details

[hide private]

global_annotations

Returns the alignment-level annotations available for the alignment

Get Method:: unreachable.global_annotations(self) - Returns the alignment-level annotations available for the alignment

seq_annotations

Returns the sequence-level annotations available for sequences held in the alignment

Get Method:: unreachable.seq_annotations(self) - Returns the sequence-level annotations available for sequences held in the alignment

all_annotations

Return a list of all annotations types in this alignment

Get Method:: unreachable.all_annotations(self) - Return a list of all annotations types in this alignment

max_length

Get Method:: unreachable.max_length(self)

Class BaseAlignment

__init__(self, sequences=None) (Constructor)

__len__(self) (Length operator)

__iter__(self)

__contains__(self, seq) (In operator)

__getitem__(self, index) (Indexing operator)

_getTextFormattedAlignment(self)

_getAlignmentDescription(self)

__str__(self) (Informal representation operator)

__repr__(self) (Representation operator)

__add__(self, other) (Addition operator)

getResidueData(self, seqnum, index, annotation=None)

iterResidues(self)

getGlobalAnnotationData(self, index, annotation)

notifyResidueSelection(self, residues)

getVisibleSeqIndices(self)

getHiddenSeqIndices(self)

notifyResDisplayChanged(self, displayed, undisplayed)

notifySequenceVisibilityChanged(self, seq, display=True)

getSeqIndex(self, seq)

getReversedSequenceOrdering(seq_indices) Static Method

reorderSequences(self, seq_indices)

_recalculateLength(self, omit, extra_length=None)

_monitorSequence(self, seq)

_stopMonitoringSequence(self, seq, slots)

_sequenceLengthAboutToChange(self, seq, old_seq_length, new_seq_length)

_sequenceLengthChanged(self, seq, old_seq_length, new_seq_length)

_checkAlignmentLength(self, seq, old_seq_length, new_seq_length)

addSeq(self, seq, index=None)

addSeqs(self, sequences, start=None)

addSeqsByIndices(self, seq_index_map)

removeSeq(self, seq)

removeSeqByIndex(self, index)

replaceSeq(self, seq, index)

_getAddOrReplaceSeqs(self, seqs, identifier_func)

addOrReplaceSeqs(self, seqs, identifier_func)

setQuerySeq(self, seq)

getQuerySeq(self)

isQuerySeq(self, seq)

getResidueIndices(self, residues)

makeResidueSelection(self, residues)

_removeResidues(self, selection)

removeResidues(self, residues)

mutateResidues(self, mutations)

replaceResiduesWithGaps(self, residues)

addResidues(self, selection)

getSubalignment(self, start, end)

removeSubalignment(self, start, end)

insertSubalignment(self, aln, start)

appendSubalignment(self, aln)

replaceSubalignment(self, aln, start, end)

getGaps(self)

getGapsByKeyFunc(self, key_func)

getGapIndicesByKeyFunc(self, gap_info, key_func)

getTerminalGaps(self)

removeGaps(self, gap_indices)

removeAllGaps(self)

_validateGapIndices(self, gap_indices)

_adjustGapsInSubalignments(self, method_name, gap_indices)

addGaps(self, gap_indices)

setGaps(self, gap_indices)

padAlignment(aln) Static Method

_getGapOnlyColumns(self)

minimizeAlignment(self)

_insertGaps(cls, sequences, gap_boundaries) Class Method

mergePairwiseAlignments(cls, sequence_pairs) Class Method

getColumn(self, index, omit_gaps=False)

columns(self, omit_gaps=False)

columnHasAllSameResidues(self, index)

_updateResMatchesQueryResCache(self)

resMatchesQueryRes(self, row_index, col_index)

lockedColumns(self)

setLockedColumns(self, columns, lock=True, reset=False)

alignmentLocked(self)

setAllLocks(self, lock=True)

_getRegions(self)

getIdentities(self, omit_gaps=True)

getSimilarityScore(self, seq)

getAlignedBlocks(self)

getFrequencies(self, exclude=None, consider_gaps=False)

init(self, sequences=None)
(Constructor)

len(self)
(Length operator)

iter(self)

contains(self, seq)
(In operator)

getitem(self, index)
(Indexing operator)

str(self)
(Informal representation operator)

repr(self)
(Representation operator)

add(self, other)
(Addition operator)

getReversedSequenceOrdering(seq_indices)
Static Method

padAlignment(aln)
Static Method

_insertGaps(cls, sequences, gap_boundaries)
Class Method

mergePairwiseAlignments(cls, sequence_pairs)
Class Method