def __init__(self, count_matrix, width, alphabet, motif_id, motif_name):
if count_matrix.empty:
errmsg = "\n\nERROR: attempt to initialize the motif object with an empty count matrix"
raise NotValidMotifMatrixException(errmsg)
if not isinstance(count_matrix, pd.DataFrame):
raise NoDataFrameException(
"\n\nERROR: the given value is not a pandas.DatFrame instance")
if not isinstance(width, int) or width < 0:
errmsg = "\n\nERROR: attempt to initialize motif without a valid width"
raise WrongMotifWidthException(errmsg)
if not isinstance(motif_id, str) or not motif_id:
raise WrongMotifIDException(
"\n\nERROR: cannot initialize the motif with the given ID")
if not isinstance(motif_name, str) or not motif_name:
raise WrongMotifNameException(
"\n\nERROR: cannot initialize the motif with the given name")
if not isinstance(alphabet, list) or not isListEqual(
alphabet, DNA_ALPHABET):
errmsg = "\n\nERROR: cannot initialize a motif object with a wrong alphabet"
raise NotValidAlphabetException(errmsg)
self._count_matrix = count_matrix
self._width = width
self._motif_id = motif_id
self._motif_name = motif_name
self._alphabet = alphabet
def setMotif_pval_matrix(self, pval_mat: np.array) -> None:
# empty or not valid p-value matrix
if len(pval_mat) == 0 or sum(pval_mat[:]) <= 0:
errmsg = "\n\nERROR: invalid p-value matrix"
raise NotValidMotifMatrixException(errmsg)
self._pval_matrix = pval_mat
def setMotif_pval_matrix(self, pval_mat):
if len(pval_mat) == 0 or sum(
pval_mat[:]) <= 0: # empty or not valid p-value matrix
raise NotValidMotifMatrixException(
"\n\nERROR: invalid p-value matrix")
self._pval_matrix = pval_mat
def setMotif_scoreMatrix(self, score_matrix):
if (not isinstance(score_matrix, np.ndarray)
and not isinstance(score_matrix, pd.DataFrame)):
errmsg = "\n\nERROR: the given data-structure is not an instance of numpy.ndarray or pandas.DataFrame"
raise ValueError(errmsg)
if isinstance(score_matrix, pd.DataFrame):
if score_matrix.empty:
errmsg = "\n\nERROR: attempt to use an empty score matrix"
raise NotValidMotifMatrixException(errmsg)
if isinstance(score_matrix, np.ndarray):
if score_matrix.size == 0:
errmsg = "\n\nERROR: attempt to use an empty score matrix"
raise NotValidMotifMatrixException(errmsg)
self._score_matrix = score_matrix
def setMotif_matrix(self, motif_matrix):
if motif_matrix.empty:
errmsg = "\n\nERROR: attempt to use an empty motif matrix"
raise NotValidMotifMatrixException(errmsg)
if not isinstance(motif_matrix, pd.DataFrame):
raise NoDataFrameException(
"\n\nERROR: the given value is not a pandas.DataFrame instance"
)
self._count_matrix = motif_matrix
def __init__(self, count_matrix: np.ndarray, width: int,
alphabet: List[str], motif_id: str, motif_name: str,
nucsmap: dict):
if not isinstance(count_matrix, np.ndarray):
errmsg = "\n\nERROR: Expected numpy.ndarray, got {}.\n"
raise TypeError(errmsg.format(type(count_matrix).__name__))
if count_matrix.size == 0 or sum(sum(count_matrix)) == 0:
errmsg = "\n\nERROR: Empty motif count matrix.\n"
raise NotValidMotifMatrixException(errmsg)
if not isinstance(width, int):
errmsg = "\n\nERROR: Expected int, got {}.\n"
raise TypeError(errmsg.format(type(width).__name__))
if width <= 0:
errmsg = "\n\nERROR: Forbidden motif width {}.\n"
raise ValueError(errmsg.format(width))
if not isinstance(motif_id, str):
errmsg = "\n\nERROR: Expected str, got {}.\n"
raise TypeError(errmsg.format(type(motif_id).__name__))
if not motif_id:
errmsg = "\n\nERROR: Not valid motif ID.\n"
raise ValueError(errmsg)
if not isinstance(motif_name, str):
errmsg = "\n\nERROR: Expected str, got {}.\n"
raise TypeError(errmsg.format(type(motif_name).__name__))
if not motif_name:
errmsg = "\n\nERROR: Not valid motif name.\n"
raise ValueError(errmsg)
if not isinstance(alphabet, list):
errmsg = "\n\nERROR: Expected list, got {}.\n"
raise TypeError(errmsg.format(type(alphabet).__name__))
if not isListEqual(alphabet, DNA_ALPHABET):
errmsg = "\n\nERROR: The motif is not built on DNA alphabet.\n"
raise ValueError(errmsg)
if not isinstance(nucsmap, dict):
errmsg = "\n\nERROR: Expected dict, got {}.\n"
raise TypeError(errmsg.format(type(nucsmap).__name__))
self._count_matrix = count_matrix
self._width = width
self._motif_id = motif_id
self._motif_name = motif_name
self._alphabet = alphabet
self._nucsmap = nucsmap
def scale_pwm(motif_matrix: pd.DataFrame, alphabet: List[str],
motif_width: int) -> Tuple[np.ndarray, int, int, int, np.double]:
"""Scale the log-odds values of the motif scoring matrix.
The values are scaled in the range [0, 1000]. The scaling improves
computational speed while computing the score for each motif
occurrence candidate, and allows a constant time computation of
the corresponding P-value.
Parameters
----------
motif_matrix : pd.DataFrame
motif log-odds matrix
alphabet: list
DNA motif alphabet
motif_width: int
motif width
Returns
-------
numpy.ndarray
scaled motif scoring matrix
int
minimum value of the scaled scoring matrix
int
maximum value of the scaled scoring matrix
int
scaling factor
numpy.double
scaling offset
"""
errmsg: str
if not isinstance(motif_matrix, pd.DataFrame):
errmsg = "\n\nERROR: The given motif matrix must be an instance of pandas.DataFrame"
raise NoDataFrameException(errmsg)
if motif_matrix.empty:
errmsg = "\n\nERROR: The given motif matrix is empty"
raise NotValidMotifMatrixException(errmsg)
if not isinstance(alphabet, list):
errmsg = "\n\nERROR: The alphabet given is not in a list"
raise NotValidAlphabetException(errmsg)
if not isListEqual(alphabet, DNA_ALPHABET):
errmsg = "\n\nERROR: The alphabet given is not a valid DNA alphabet"
raise NotValidAlphabetException(errmsg)
assert motif_width > 0
min_val: int
max_val: int
motif_matrix_sc: pd.DataFrame
min_val = min(motif_matrix.min())
max_val = max(motif_matrix.max())
motif_matrix_sc = pd.DataFrame(index=list(motif_matrix.index),
columns=list(motif_matrix.columns),
data=0)
lower: int = min_val
upper: int = max_val
if lower == upper: # all values are equal
lower = np.double(upper - 1)
offset: np.double
scale_factor: int
lower = np.floor(lower)
offset = np.round(np.floor(lower))
scale_factor = np.floor(RANGE / (upper - lower))
# values will be in [0, 1000]
for nuc in alphabet:
for j in range(motif_width):
scaled_score = np.round(
(motif_matrix.loc[nuc, j] - (offset)) * scale_factor)
motif_matrix_sc.loc[nuc, j] = scaled_score
# end for
# end for
# make sure the values are integers
motif_matrix_sc[:] = motif_matrix_sc[:].astype(int)
# now they are scaled
min_val = min(motif_matrix_sc.min())
max_val = max(motif_matrix_sc.max())
return motif_matrix_sc, min_val, max_val, int(scale_factor), offset
def scale_pwm(motif_matrix, alphabet, motif_width):
"""
Scale the motif matrix values
----
Parameters:
motif_matrix (str) : count matrix
alphabet (str) : motif alphabet
motif_width (int) : motif width
----
Returns:
motif_matrix_sc (np.ndarray) : scaled motif matrix
min_val (int) : lowest value in the scaled motif matrix
max_val (int) : higest value in the scaled motif matrix
scale_factor (int)
offset (int)
"""
if not isinstance(motif_matrix, pd.DataFrame):
raise NoDataFrameException(
"The given motif matrix must be an instance of pandas.DataFrame")
die(1)
if motif_matrix.empty:
raise NotValidMotifMatrixException("The given motif matrix is empty")
die(1)
if not isinstance(alphabet, list):
raise NotValidAlphabetException("The alphabet given is not in a list")
die(1)
if not isListEqual(alphabet, DNA_ALPHABET):
raise NotValidAlphabetException(
"The alphabet given is not a valid DNA alphabet")
die(1)
assert motif_width > 0
min_val = min(motif_matrix.min())
max_val = max(motif_matrix.max())
motif_matrix_sc = pd.DataFrame(index=list(motif_matrix.index),
columns=list(motif_matrix.columns),
data=0)
lower = min_val
upper = max_val
if lower == upper: # all values are equal
lower = np.double(upper - 1)
lower = np.floor(lower)
offset = np.round(np.floor(lower))
scale_factor = np.floor(RANGE / (upper - lower))
# values will be in [0, 1000]
for nuc in alphabet:
for j in range(motif_width):
scaled_score = np.round(
(motif_matrix.loc[nuc, j] - (offset)) * scale_factor)
motif_matrix_sc.loc[nuc, j] = scaled_score
# end for
# end for
# make sure the values are integers
motif_matrix_sc[:] = motif_matrix_sc[:].astype(int)
# now they are scaled
min_val = min(motif_matrix_sc.min())
max_val = max(motif_matrix_sc.max())
return motif_matrix_sc, min_val, max_val, int(scale_factor), offset