In [1]: import numpy as np

In [2]: a = np.array(['x', 'y', 'y', 'x', 'y'])

In [3]: a == 'x'
Out[3]: array([ True, False, False,  True, False], dtype=bool)

字符串

一种更通用的方法，适用于多字母条件：

base_mask = lambda x: x == 'A' or x == 'a' or x == 'T' or x == 't'
vec_base_mask = np.vectorize(base_mask)
seq = 'TCTATcgGGa'
a = np.array([*seq])
masked_a = vec_base_mask(a)

# >>> masked_a
# array([ True, False,  True,  True,  True, False, False, False, False,
#         True])

字符串