def background_chr1():
c = """Chromosome Start End Strand
chr1 1 4 +
chr1 2 5 -"""
return coverage(PyRanges(pd.read_table(StringIO(c), sep="\s+")))
def test_simple_bed_with_scores(simple_bed, expected_result_simple_bed_values):
result = coverage(simple_bed, value_col="Value")
print(result.runs, expected_result_simple_bed_values.runs)
print(result.values, expected_result_simple_bed_values.values)
assert list(result.runs) == list(expected_result_simple_bed_values.runs)
assert np.allclose(result.values, expected_result_simple_bed_values.values)
def chip_chr1():
c = """Chromosome Start End Strand
chr1 5 7 +
chr1 3 10 -"""
return coverage(PyRanges(pd.read_table(StringIO(c), sep="\s+")))
def test_coverage_simple(simple):
result = coverage(simple, value_col="Score")
print(result)
assert result == Rle([1, 2], [-1, 1])
def test_simple_bed(simple_bed, expected_result_simple_bed):
result = coverage(simple_bed)
print(result.runs, expected_result_simple_bed.runs)
print(result.values, expected_result_simple_bed.values)
assert list(result.runs) == list(expected_result_simple_bed.runs)
assert list(result.values) == list(expected_result_simple_bed.values)
def test_roundtrip_to_ranges_single_rle_teensy_duplicated(
teensy_duplicated, expected_result_teensy_duplicated):
gr = teensy_duplicated
cv = coverage(teensy_duplicated)
# print(cv.values)
starts, ends, values = _to_ranges(cv)
# print(gr)
# print(pr.PyRanges(gr.df.drop_duplicates()))
# print("len(starts)", len(starts))
# print("starts")
# print(starts[:5])
# print(starts[-5:])
# print("ends")
# print(ends[:5])
# print(ends[-5:])
assert list(starts) == [
0, 42058716, 42058741, 42130511, 42130536, 42593165, 42593190,
42635413, 42635438, 43357333, 43357358, 43854685
]
assert list(ends) == [
42058716, 42058741, 42130511, 42130536, 42593165, 42593190, 42635413,
42635438, 43357333, 43357358, 43854685, 43854710
]
def test_coverage(df, expected_result_coverage):
expected_runs, expected_values = expected_result_coverage
# result = coverage(df)
result = coverage(df)
print(result.runs)
print(result.values)
print(len(result.runs))
print(len(result.values))
print(expected_runs)
print(expected_values)
assert list(result.runs) == expected_runs
assert list(result.values) == expected_values
def test_roundtrip_to_ranges_single_rle_teensy(teensy):
cv = coverage(teensy, value_col="Score")
starts, ends, values = _to_ranges(cv)
df = pd.concat([pd.Series(a) for a in [starts, ends, values]], axis=1)
df.columns = "Start End Score".split()
df.insert(0, "Chromosome", "chr2")
gr = pr.PyRanges(df)
# print(", ".join(str(i) for i in starts))
# print(", ".join(str(f) for f in ends))
assert list(starts) == [
0, 13611, 13636, 32620, 32645, 33241, 33266, 1150665
]
assert list(ends) == [
13611, 13636, 32620, 32645, 33241, 33266, 1150665, 1150690
]
def test_roundtrip_to_ranges_single_rle_overlapping(overlapping_gr):
gr = overlapping_gr
print(gr)
cv = coverage(gr)
print(cv)
starts, ends, values = _to_ranges(cv)
df = pd.concat([pd.Series(a) for a in [starts, ends, cv.values]], axis=1)
df.columns = "Start End Score".split()
df.insert(0, "Chromosome", "chr2")
print(pr.PyRanges(df))
# print(gr)
# print(pr.PyRanges(gr.df.drop_duplicates()))
# print("len(starts)", len(starts))
# print("starts")
# print(starts[:5])
# print("ends")
# print(ends[:5])
assert list(starts) == [0, 1, 4, 7]
assert list(ends) == [1, 4, 7, 10]
def chip():
c = """Chromosome Start End Strand
chr2 1 3 +"""
return coverage(PyRanges(pd.read_table(StringIO(c), sep="\s+")))