New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Position Frequency Matrix Featurizer #2896
Merged
Merged
Changes from 25 commits
Commits
Show all changes
27 commits
Select commit
Hold shift + click to select a range
726565a
hhblits/hhsearch wrapper, tests, tutorial, docs
tonydavis629 389a150
add missing example_db files
tonydavis629 a507a40
fixed test
tonydavis629 cddd32d
Merge branch 'master' into hhsuite
tonydavis629 df148c7
fix test
tonydavis629 302e463
Merge branch 'master' into hhsuite
tonydavis629 34d3285
fix doc test
tonydavis629 f998486
fix doctest
tonydavis629 29b0add
Merge branch 'master' into hhsuite
tonydavis629 fc03218
msa to dataset added
tonydavis629 90a58f3
seq_feat
tonydavis629 a1797ac
seq_feat
tonydavis629 2153025
Merge branch 'master' into seq_feat
tonydavis629 3152943
pfm featurizer
tonydavis629 d0b1be5
sequence featurizers group
tonydavis629 aa33db7
one_hot
tonydavis629 ab6a0e8
position freq matrix
tonydavis629 a3f0f17
pfm to ppm
tonydavis629 9896692
msa_to_dataset test complete
tonydavis629 4d9f505
move pfm_to_ppm to test_pfm
tonydavis629 feb8cd1
updated docs for PFM
tonydavis629 b4858fd
yapf, flake8, doctest
tonydavis629 52a6668
Merge branch 'master' into seq_feat
tonydavis629 c2277b9
remove bioconda from requirements channels
tonydavis629 d7c9d5b
lowecase bio
tonydavis629 d6cf7a3
move bio.seq import to function
tonydavis629 76c45df
fix base_classes.py formatting
tonydavis629 File filter
Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -498,3 +498,4 @@ def featurize(self, | |
the datapoints. | ||
""" | ||
return np.asarray(datapoints) | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,2 @@ | ||
# flake8: noqa | ||
from deepchem.feat.sequence_featurizers.position_frequency_matrix_featurizer import PFMFeaturizer |
93 changes: 93 additions & 0 deletions
93
deepchem/feat/sequence_featurizers/position_frequency_matrix_featurizer.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,93 @@ | ||
import numpy as np | ||
from deepchem.feat.molecule_featurizers import OneHotFeaturizer | ||
from deepchem.feat.base_classes import Featurizer | ||
from typing import List, Optional | ||
|
||
CHARSET = [ | ||
'A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', | ||
'S', 'T', 'V', 'W', 'Y', 'X', 'Z', 'B', 'U', 'O' | ||
] | ||
|
||
|
||
class PFMFeaturizer(Featurizer): | ||
""" | ||
Encodes a list position frequency matrices for a given list of multiple sequence alignments | ||
|
||
The default character set is 25 amino acids. If you want to use a different character set, such as nucleotides, simply pass in | ||
a list of character strings in the featurizer constructor. | ||
|
||
The max_length parameter is the maximum length of the sequences to be featurized. If you want to featurize longer sequences, modify the | ||
max_length parameter in the featurizer constructor. | ||
|
||
The final row in the position frequency matrix is the unknown set, if there are any characters which are not included in the charset. | ||
|
||
Examples | ||
-------- | ||
>>> from deepchem.feat.sequence_featurizers import PFMFeaturizer | ||
>>> from deepchem.data import NumpyDataset | ||
>>> msa = NumpyDataset(X=[['ABC','BCD'],['AAA','AAB']], ids=[['seq01','seq02'],['seq11','seq12']]) | ||
>>> seqs = msa.X | ||
>>> featurizer = PFMFeaturizer() | ||
>>> pfm = featurizer.featurize(seqs) | ||
>>> pfm.shape | ||
(2, 26, 100) | ||
|
||
""" | ||
|
||
def __init__(self, | ||
charset: List[str] = CHARSET, | ||
max_length: Optional[int] = 100): | ||
"""Initialize featurizer. | ||
|
||
Parameters | ||
---------- | ||
charset: List[str] (default CHARSET) | ||
A list of strings, where each string is length 1 and unique. | ||
max_length: int, optional (default 25) | ||
Maximum length of sequences to be featurized. | ||
""" | ||
if len(charset) != len(set(charset)): | ||
raise ValueError("All values in charset must be unique.") | ||
self.charset = charset | ||
self.max_length = max_length | ||
self.ohe = OneHotFeaturizer(charset=CHARSET, max_length=max_length) | ||
|
||
def _featurize(self, datapoint): | ||
"""Featurize a multisequence alignment into a position frequency matrix | ||
|
||
Use dc.utils.sequence_utils.hhblits or dc.utils.sequence_utils.hhsearch to create a multiple sequence alignment from a fasta file. | ||
|
||
Parameters | ||
---------- | ||
datapoint: np.ndarray | ||
MSA to featurize. A list of sequences which have been aligned and padded to the same length. | ||
|
||
Returns | ||
------- | ||
pfm: np.ndarray | ||
Position frequency matrix for the set of sequences with the rows corresponding to the unique characters and the columns corresponding to the position in the alignment. | ||
|
||
""" | ||
|
||
seq_one_hot = self.ohe.featurize(datapoint) | ||
|
||
seq_one_hot_array = np.transpose( | ||
np.array(seq_one_hot), (0, 2, 1) | ||
) # swap rows and columns to make rows the characters, columns the positions | ||
|
||
pfm = np.sum(seq_one_hot_array, axis=0) | ||
|
||
return pfm | ||
|
||
|
||
def PFM_to_PPM(pfm): | ||
""" | ||
Calculate position probability matrix from a position frequency matrix | ||
""" | ||
ppm = pfm.copy() | ||
for col in range(ppm.shape[1]): | ||
total_count = np.sum(ppm[:, col]) | ||
if total_count > 0: | ||
# Calculate frequency | ||
ppm[:, col] = ppm[:, col] / total_count | ||
return ppm |
34 changes: 34 additions & 0 deletions
34
deepchem/feat/tests/test_position_frequency_matrix_featurizer.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,34 @@ | ||
import unittest | ||
import numpy as np | ||
from deepchem.feat.sequence_featurizers.position_frequency_matrix_featurizer import PFMFeaturizer, CHARSET, PFM_to_PPM | ||
|
||
|
||
class TestPFMFeaturizer(unittest.TestCase): | ||
""" | ||
Test PFMFeaturizer. | ||
""" | ||
|
||
def setUp(self): | ||
""" | ||
Set up test. | ||
""" | ||
self.msa = np.array([['ABC', 'BCD'], ['AAA', 'AAB']]) | ||
self.featurizer = PFMFeaturizer() | ||
self.max_length = 100 | ||
|
||
def test_PFMFeaturizer_arbitrary(self): | ||
""" | ||
Test PFM featurizer for simple MSA. | ||
""" | ||
pfm = self.featurizer.featurize(self.msa) | ||
assert pfm.shape == (2, len(CHARSET) + 1, self.max_length) | ||
assert pfm[0][0][0] == 1 | ||
|
||
def test_PFM_to_PPM(self): | ||
""" | ||
Test PFM_to_PPM. | ||
""" | ||
pfm = self.featurizer.featurize(self.msa) | ||
ppm = PFM_to_PPM(pfm[0]) | ||
assert ppm.shape == (len(CHARSET) + 1, self.max_length) | ||
assert ppm[0][0] == .5 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This should be in a try except block or SeqIO should be imported locally in a function where it is used