Log In Sign Up
Models:
Marco Lenoir
MarcoTheBlack/
janggu
0
Downloads: 1
[2108ce]: / tests / test_gindexer.py

Download this file

130 lines (103 with data), 5.1 kB 

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import os



import matplotlib

import numpy as np

import pkg_resources

import pytest

import pandas as pd



from janggu.data import GenomicIndexer



matplotlib.use('AGG')



def test_gindexer_short_interval():

    data_path = pkg_resources.resource_filename('janggu', 'resources/')





    gi = GenomicIndexer.create_from_file(os.path.join(data_path,

                                                 'sample_equalsize.bed'),

                                    binsize=200, stepsize=200)

    assert len(gi) == 4

    gi = GenomicIndexer.create_from_file(os.path.join(data_path,

                                                 'sample_equalsize.bed'),

                                    binsize=180, stepsize=20)

    assert len(gi) == 8

    gi = GenomicIndexer.create_from_file(os.path.join(data_path,

                                                 'sample_equalsize.bed'),

                                    binsize=210, stepsize=20, zero_padding=False)

    assert len(gi) == 0



    gi = GenomicIndexer.create_from_file(os.path.join(data_path,

                                                 'sample_equalsize.bed'),

                                    binsize=210, stepsize=20, zero_padding=True)

    assert len(gi) == 4





def test_gindexer_short_interval_with_dataframe():

    data_path = pkg_resources.resource_filename('janggu', 'resources/')

    df = pd.read_csv(os.path.join(data_path, 'sample_equalsize.bed'),

                     sep='\t', header=None, names=['chrom', 'start', 'end'])



    gi = GenomicIndexer.create_from_file(df,

                                         binsize=200, stepsize=200)

    assert len(gi) == 4

    gi = GenomicIndexer.create_from_file(df,

                                         binsize=180, stepsize=20)

    assert len(gi) == 8

    gi = GenomicIndexer.create_from_file(df,

                                         binsize=210, stepsize=20,

                                         zero_padding=False)

    assert len(gi) == 0



    gi = GenomicIndexer.create_from_file(df,

                                         binsize=210, stepsize=20,

                                         zero_padding=True)

    assert len(gi) == 4





def test_gindexer_errors():

    data_path = pkg_resources.resource_filename('janggu', 'resources/')



    with pytest.raises(ValueError):

        GenomicIndexer.create_from_file(os.path.join(data_path,

                                                     'sample.bed'),

                                        binsize=0, stepsize=50)



    with pytest.raises(ValueError):

        GenomicIndexer.create_from_file(os.path.join(data_path,

                                                     'sample.bed'),

                                        binsize=10, stepsize=0)

    with pytest.raises(ValueError):

        # due to flank < 0

        GenomicIndexer.create_from_file(os.path.join(data_path, 'sample.bed'),

                                        binsize=200, stepsize=50, flank=-1)

    # due to unequal intervals

    gi=GenomicIndexer.create_from_file(os.path.join(data_path, 'scores.bed'),

                                    binsize=None, stepsize=None, flank=0)

    #print(len(gi))

    #for reg in gi:

    #    print(reg)

    GenomicIndexer.create_from_file(os.path.join(data_path, 'scores.bed'),

                                    binsize=200, stepsize=200, flank=0)



def test_gindexer_merged():

    data_path = pkg_resources.resource_filename('janggu', 'resources/')



    gi = GenomicIndexer.create_from_file(

        os.path.join(data_path, 'sample.bed'), binsize=200, stepsize=200)

    np.testing.assert_equal(len(gi), 100)

    gi2 = gi.filter_by_region(include='chr1')

    gi3 = gi.filter_by_region(include='chr10')

    gi4 = gi.filter_by_region(exclude='chr2')

    gi5 = gi.filter_by_region(exclude='chr10')





    np.testing.assert_equal(len(gi2), 50)



    np.testing.assert_equal(len(gi3), 0)

    np.testing.assert_equal(len(gi4), 50)

    np.testing.assert_equal(len(gi5), 100)





def test_gindexer_merged_variable_length_ranges():

    data_path = pkg_resources.resource_filename('janggu', 'resources/')



    # with fixed size

    gi = GenomicIndexer.create_from_file(

        os.path.join(data_path, 'sample.bed'), binsize=3000, stepsize=3000,

        zero_padding=False)

    np.testing.assert_equal(len(gi), 6)



    iv = gi[0]

    np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),

                            ('chr1', 15000, 18000, '+'))

    iv = gi[-1]

    np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),

                            ('chr2', 21000, 24000, '-'))



    # with variable size regions

    gi = GenomicIndexer.create_from_file(

        os.path.join(data_path, 'sample.bed'), binsize=3000,

        stepsize=3000, zero_padding=True)

    np.testing.assert_equal(len(gi), 8)



    iv = gi[0]

    np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),

                            ('chr1', 15000, 18000, '+'))

    iv = gi[-1]

    np.testing.assert_equal((iv.chrom, iv.start, iv.end, iv.strand),

                            ('chr2', 24000, 25000, '-'))