def equalize_lib_sizes(counts, groups, lib_size, dispersion=0, common_size=None):
""" Equalize the library sizes
"""
if not common_size:
common_size = np.exp(np.mean(np.log(lib_size)))
try: len(dispersion)
except TypeError: dispersion = np.repeat(dispersion,
counts.shape[0])
input_mean = np.empty(counts.shape, dtype=np.double)
output_mean = input_mean.copy()
for key, group in groups.iteritems():
beta = glm_one_group_numba(
np.ascontiguousarray(counts.ix[:,group].as_matrix(),
dtype=np.int32),
dispersion,
np.ascontiguousarray(np.log(lib_size[group]),
dtype=np.double)
)
beta = np.asarray(beta)
bn_lambda = np.exp(beta).T.reshape(len(beta),1)
temp_lib_size = np.array(lib_size[group]).reshape(1,
len(lib_size[group]))
out_size = np.repeat(common_size, len(group)).reshape(1,
len(group))
input_mean[:, group] = np.dot(bn_lambda, temp_lib_size)
output_mean[:, group] = np.dot(bn_lambda,
out_size)
pseudo = q2qnbinom(np.asarray(counts.as_matrix()),
input_mean, output_mean, dispersion)
pseudo[pseudo < 0] = 0
return pseudo, common_size
def equalize_lib_sizes(counts,
groups,
lib_size,
dispersion=0,
common_size=None):
""" Equalize the library sizes
"""
if not common_size:
common_size = np.exp(np.mean(np.log(lib_size)))
try:
len(dispersion)
except TypeError:
dispersion = np.repeat(dispersion, counts.shape[0])
input_mean = np.empty(counts.shape, dtype=np.double)
output_mean = input_mean.copy()
for key, group in groups.iteritems():
beta = glm_one_group_numba(
np.ascontiguousarray(counts.ix[:, group].as_matrix(),
dtype=np.int32), dispersion,
np.ascontiguousarray(np.log(lib_size[group]), dtype=np.double))
beta = np.asarray(beta)
bn_lambda = np.exp(beta).T.reshape(len(beta), 1)
temp_lib_size = np.array(lib_size[group]).reshape(
1, len(lib_size[group]))
out_size = np.repeat(common_size, len(group)).reshape(1, len(group))
input_mean[:, group] = np.dot(bn_lambda, temp_lib_size)
output_mean[:, group] = np.dot(bn_lambda, out_size)
pseudo = q2qnbinom(np.asarray(counts.as_matrix()), input_mean, output_mean,
dispersion)
pseudo[pseudo < 0] = 0
return pseudo, common_size
def average_cpm(y, lib_size = None, prior_count=2, dispersion=0.05):
"""
Parameters
---------
y: matrix of counts
lib_size:
prior_count:
dispersion:
"""
y = np.ascontiguousarray(y)
#if lib_size == None: np.sum(y, axis=0)
prior_counts_scaled = np.asarray(lib_size/np.mean(lib_size) *
prior_count, dtype=np.double).reshape(len(lib_size), 1)
offset = np.log(np.asarray(lib_size,
dtype=np.double).reshape(len(lib_size),1) + 2 * prior_counts_scaled)
dispersion = np.repeat(dispersion, y.shape[0])
abundence = glm_one_group_numba(np.ascontiguousarray((y.T +
prior_counts_scaled).T),
dispersion, offset.T[0])
return((np.asarray(abundence) + np.log(1e6))/np.log(2))
def average_cpm(y, lib_size=None, prior_count=2, dispersion=0.05):
"""
Parameters
---------
y: matrix of counts
lib_size:
prior_count:
dispersion:
"""
y = np.ascontiguousarray(y)
#if lib_size == None: np.sum(y, axis=0)
prior_counts_scaled = np.asarray(
lib_size / np.mean(lib_size) * prior_count,
dtype=np.double).reshape(len(lib_size), 1)
offset = np.log(
np.asarray(lib_size, dtype=np.double).reshape(len(lib_size), 1) +
2 * prior_counts_scaled)
dispersion = np.repeat(dispersion, y.shape[0])
abundence = glm_one_group_numba(
np.ascontiguousarray((y.T + prior_counts_scaled).T), dispersion,
offset.T[0])
return ((np.asarray(abundence) + np.log(1e6)) / np.log(2))
