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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
# from unittest import TestCase
import deeptools.computeMatrixOperations as cmo
import os
import hashlib
import gzip
import json
__author__ = 'Devon'
ROOT = os.path.dirname(os.path.abspath(__file__)) + "/test_data/"
def getHeader(fp):
s = fp.readline()
if isinstance(s, bytes):
s = s.decode()
s = s[1:]
return json.loads(s)
class TestComputeMatrixOperations(object):
def setUp(self):
self.root = ROOT
self.matrix = self.root + "computeMatrixOperations.mat.gz"
self.bed = self.root + "computeMatrixOperations.bed"
self.rbindMatrix1 = self.root + "somegenes.txt.gz"
self.rbindMatrix2 = self.root + "othergenes.txt.gz"
def testSubset(self):
"""
computeMatrixOperations subset
"""
dCorrect = {"verbose": True, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0, 0, 0, 0], "body": [1000, 1000, 1000, 1000], "sample_labels": ["SRR648667.forward", "SRR648668.forward", "SRR648669.forward", "SRR648670.forward"], "downstream": [0, 0, 0, 0], "unscaled 3 prime": [0, 0, 0, 0], "group_labels": ["genes"], "bin size": [10, 10, 10, 10], "upstream": [0, 0, 0, 0], "group_boundaries": [0, 196], "sample_boundaries": [0, 100, 200, 300, 400], "max threshold": None, "ref point": [None, None, None, None], "min threshold": None, "sort regions": "no", "proc number": 20, "bin avg type": "mean", "missing data as zero": False}
oname = "/tmp/subset.mat.gz"
args = "subset -m {} --sample SRR648667.forward SRR648668.forward SRR648669.forward SRR648670.forward -o {}".format(self.matrix, oname)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "edb3c8506c3f27ebb8c7ddf94d5ba594")
os.remove(oname)
def testRelabel(self):
"""
computeMatrixOperations relabel
"""
dCorrect = {"verbose": True, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0, 0, 0, 0, 0, 0, 0, 0], "body": [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000], "sample_labels": ["first", "sec ond", "3rd", "4th", "5th", "6th", "7th", "8th"], "downstream": [0, 0, 0, 0, 0, 0, 0, 0], "unscaled 3 prime": [0, 0, 0, 0, 0, 0, 0, 0], "group_labels": ["foo bar"], "bin size": [10, 10, 10, 10, 10, 10, 10, 10], "upstream": [0, 0, 0, 0, 0, 0, 0, 0], "group_boundaries": [0, 196], "sample_boundaries": [0, 100, 200, 300, 400, 500, 600, 700, 800], "max threshold": None, "ref point": [None, None, None, None, None, None, None, None], "min threshold": None, "sort regions": "no", "proc number": 20, "bin avg type": "mean", "missing data as zero": False}
oname = "/tmp/relabeled.mat.gz"
args = "relabel -m {} -o {} --sampleLabels first sec_ond 3rd 4th 5th 6th 7th 8th --groupLabels foo_bar".format(self.matrix, oname)
args = args.split()
args[7] = 'sec ond' # split mucks up spaces
args[-1] = 'foo bar'
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f)
assert(d == dCorrect)
f.close()
os.remove(oname)
def testfilterStrand(self):
"""
computeMatrixOperations filterStrand
"""
dCorrect = {"verbose": True, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0, 0, 0, 0, 0, 0, 0, 0], "body": [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000], "sample_labels": ["SRR648667.forward", "SRR648668.forward", "SRR648669.forward", "SRR648670.forward", "SRR648667.reverse", "SRR648668.reverse", "SRR648669.reverse", "SRR648670.reverse"], "downstream": [0, 0, 0, 0, 0, 0, 0, 0], "unscaled 3 prime": [0, 0, 0, 0, 0, 0, 0, 0], "group_labels": ["genes"], "bin size": [10, 10, 10, 10, 10, 10, 10, 10], "upstream": [0, 0, 0, 0, 0, 0, 0, 0], "group_boundaries": [0, 107], "sample_boundaries": [0, 100, 200, 300, 400, 500, 600, 700, 800], "max threshold": None, "ref point": [None, None, None, None, None, None, None, None], "min threshold": None, "sort regions": "no", "proc number": 20, "bin avg type": "mean", "missing data as zero": False}
oname = "/tmp/filterStrand1.mat.gz"
args = "filterStrand -m {} -o {} --strand +".format(self.matrix, oname)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "300f8000be5b5f51e803b57ef08f1c9e")
os.remove(oname)
dCorrect = {u'verbose': True, u'scale': 1, u'skip zeros': False, u'nan after end': False, u'sort using': u'mean', u'unscaled 5 prime': [0, 0, 0, 0, 0, 0, 0, 0], u'body': [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000], u'sample_labels': [u'SRR648667.forward', u'SRR648668.forward', u'SRR648669.forward', u'SRR648670.forward', u'SRR648667.reverse', u'SRR648668.reverse', u'SRR648669.reverse', u'SRR648670.reverse'], u'downstream': [0, 0, 0, 0, 0, 0, 0, 0], u'unscaled 3 prime': [0, 0, 0, 0, 0, 0, 0, 0], u'group_labels': [u'genes'], u'bin size': [10, 10, 10, 10, 10, 10, 10, 10], u'upstream': [0, 0, 0, 0, 0, 0, 0, 0], u'group_boundaries': [0, 89], u'sample_boundaries': [0, 100, 200, 300, 400, 500, 600, 700, 800], u'missing data as zero': False, u'ref point': [None, None, None, None, None, None, None, None], u'min threshold': None, u'sort regions': u'no', u'proc number': 20, u'bin avg type': u'mean', u'max threshold': None}
oname = "/tmp/filterStrand2.mat.gz"
args = "filterStrand -m {} -o {} --strand -".format(self.matrix, oname)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "0a6ca070a5ba4564f1ab950ac3b7c8f1")
os.remove(oname)
def testrbind(self):
"""
computeMatrixOperations rbind
"""
dCorrect = {"verbose": True, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0, 0, 0, 0, 0, 0, 0, 0], "body": [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000], "sample_labels": ["SRR648667.forward", "SRR648668.forward", "SRR648669.forward", "SRR648670.forward", "SRR648667.reverse", "SRR648668.reverse", "SRR648669.reverse", "SRR648670.reverse"], "downstream": [0, 0, 0, 0, 0, 0, 0, 0], "unscaled 3 prime": [0, 0, 0, 0, 0, 0, 0, 0], "group_labels": ["genes"], "bin size": [10, 10, 10, 10, 10, 10, 10, 10], "upstream": [0, 0, 0, 0, 0, 0, 0, 0], "group_boundaries": [0, 392], "sample_boundaries": [0, 100, 200, 300, 400, 500, 600, 700, 800], "max threshold": None, "ref point": [None, None, None, None, None, None, None, None], "min threshold": None, "sort regions": "no", "proc number": 20, "bin avg type": "mean", "missing data as zero": False}
oname = "/tmp/rbind.mat.gz"
args = "rbind -m {0} {0} -o {1}".format(self.matrix, oname)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "3dd96c7b05e0ca5ada21212defe57fba")
os.remove(oname)
def testrbind2(self):
"""
computeMatrixOperations rbind with different groups
"""
dCorrect = {"verbose": False, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0], "body": [2], "sample_labels": ["signal"], "downstream": [1], "unscaled 3 prime": [0], "group_labels": ["somegenes", "othergenes"], "bin size": [1], "upstream": [1], "group_boundaries": [0, 3, 7], "sample_boundaries": [0, 4], "max threshold": None, "ref point": [None], "min threshold": None, "sort regions": "keep", "proc number": 1, "bin avg type": "mean", "missing data as zero": True}
oname = "/tmp/rbind2.mat.gz"
args = "rbind -m {0} {1} -o {2}".format(self.rbindMatrix1, self.rbindMatrix2, oname)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "5d8b1517fc4c63d000b6b37f70ee163b")
os.remove(oname)
def testcbind(self):
"""
computeMatrixOperations cbind
"""
dCorrect = {"verbose": True, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "body": [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000], "sample_labels": ["SRR648667.forward", "SRR648668.forward", "SRR648669.forward", "SRR648670.forward", "SRR648667.reverse", "SRR648668.reverse", "SRR648669.reverse", "SRR648670.reverse", "SRR648667.forward", "SRR648668.forward", "SRR648669.forward", "SRR648670.forward", "SRR648667.reverse", "SRR648668.reverse", "SRR648669.reverse", "SRR648670.reverse"], "downstream": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "unscaled 3 prime": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "group_labels": ["genes"], "bin size": [10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10], "upstream": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], "group_boundaries": [0, 196], "sample_boundaries": [0, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1500, 1600], "max threshold": None, "ref point": [None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None], "min threshold": None, "sort regions": "no", "proc number": 20, "bin avg type": "mean", "missing data as zero": False}
oname = "/tmp/filterStrand.mat.gz"
args = "cbind -m {0} {0} -o {1}".format(self.matrix, oname)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "e55d89704bb16a11f366663a8fd90a47")
os.remove(oname)
def testsort(self):
"""
computeMatrixOperations sort
"""
dCorrect = {"verbose": True, "scale": 1, "skip zeros": False, "nan after end": False, "sort using": "mean", "unscaled 5 prime": [0, 0, 0, 0, 0, 0, 0, 0], "body": [1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000], "sample_labels": ["SRR648667.forward", "SRR648668.forward", "SRR648669.forward", "SRR648670.forward", "SRR648667.reverse", "SRR648668.reverse", "SRR648669.reverse", "SRR648670.reverse"], "downstream": [0, 0, 0, 0, 0, 0, 0, 0], "unscaled 3 prime": [0, 0, 0, 0, 0, 0, 0, 0], "group_labels": ["genes"], "bin size": [10, 10, 10, 10, 10, 10, 10, 10], "upstream": [0, 0, 0, 0, 0, 0, 0, 0], "group_boundaries": [0, 196], "sample_boundaries": [0, 100, 200, 300, 400, 500, 600, 700, 800], "max threshold": None, "ref point": [None, None, None, None, None, None, None, None], "min threshold": None, "sort regions": "no", "proc number": 20, "bin avg type": "mean", "missing data as zero": False}
oname = "/tmp/sorted.mat.gz"
args = "sort -m {} -o {} -R {}".format(self.matrix, oname, self.bed)
args = args.split()
cmo.main(args)
f = gzip.GzipFile(oname)
d = getHeader(f) # Skip the header, which can be in a different order
h = hashlib.md5(f.read()).hexdigest()
f.close()
assert(d == dCorrect)
assert(h == "10ea07d1aa58f44625abe2142ef76094")
os.remove(oname)
|
