anhima.loc - Locating variants, samples and genome regions

In [1]:

    

import numpy as np
np.random.seed(42)
import random
random.seed(1)
import matplotlib.pyplot as plt
%matplotlib inline
import sys
# import anhima
# dev imports
sys.path.insert(0, '..')
%reload_ext autoreload
%autoreload 1
%aimport anhima.loc


    

In [2]:

    

# simulate non-uniform variant positions
n_variants = 1000
p = 0
pos = []
for i in range(n_variants):
    gap = int(np.abs(np.cos(i/100))*100)
    p += gap
    pos.append(p)
pos = np.array(pos)


    

In [3]:

    

# plot variant locations
anhima.loc.plot_variant_locator(pos, step=10);


    

In [4]:

    

# plot variant locations with y axis inverted
anhima.loc.plot_variant_locator(pos, step=10, flip=True);


    

In [5]:

    

loc = anhima.loc.locate_interval(pos, 11000, 20000)
loc


    

    
Out[5]:





slice(204, 315, None)

In [6]:

    

pos[loc.start-1], pos[loc.start]


    

    
Out[6]:





(10999, 11044)

In [7]:

    

pos[loc.stop-1], pos[loc.stop]


    

    
Out[7]:





(19918, 20017)

In [8]:

    

# plot variant counts
anhima.loc.plot_windowed_variant_counts(pos, window_size=1000);


    

In [9]:

    

# plot variant counts
anhima.loc.plot_windowed_variant_counts(pos, window_size=5000);


    

In [10]:

    

# plot variant density
anhima.loc.plot_windowed_variant_density(pos, window_size=1000);


    

In [11]:

    

# plot variant density
anhima.loc.plot_windowed_variant_density(pos, window_size=5000);


    

In [12]: