def test_create_default(self):
ms = MotifSet()
self.assertEqual(
len(ms.motifs_map),
0,
msg="motif dictionary must be empty by default (no preload)")
def test_match_multiple(self):
ms = MotifSet(preload_motifs="default")
ms = ms.filter({'database': ["jaspar_vertebrates"], 'name': ["MA0139.1.CTCF"]}, search="inexact")
self.assertEqual(len(ms), 1)
motif = ms.get_motif_list(1, 0.0001)[0]
scanner = scan.Scanner(7)
pssm_list, thresholds = [], []
thresholds.append(motif.threshold)
thresholds.append(motif.threshold)
pssm_list.append(motif.pssm)
pssm_list.append(motif.pssm_rc)
bg = tools.flat_bg(4)
scanner.set_motifs(pssm_list, bg, thresholds)
genomic_region = GenomicRegion("chr1", 0, 5022)
# Reading sequence associated to genomic_region
sequence = str(self.genome_file.fetch(genomic_region.chrom, genomic_region.initial, genomic_region.final))
grs = match_multiple(scanner, [motif], sequence, genomic_region)
self.assertSequenceEqual(grs.sequences,
[GenomicRegion("chr1", 4270, 4289, name="MA0139.1.CTCF", orientation="+"),
GenomicRegion("chr1", 4180, 4199, name="MA0139.1.CTCF", orientation="-")])
def setUp(self):
dirname = os.path.dirname(__file__)
mtf_file = os.path.join(dirname, "../data/motifs/hocomoco.mtf")
# we must enforce the use hocomoco as database
self.motif_set = MotifSet(preload_motifs=False)
self.motif_set.read_mtf(mtf_file)
def test_built_in_functions(self):
ms = MotifSet(preload_motifs="hocomoco")
self.assertTrue(str(ms).startswith("MotifSet:{"),
msg="str(ms): wrong format")
self.assertTrue(repr(ms) == str(ms),
msg="MotifSet: repr does not equal str")
ms2 = ms.filter(
{
'name': ["ALX1_HUMAN.H11MO.0.B"],
'species': ["H**o sapiens"]
},
search="exact")
self.assertTrue("'name': 'ALX1_HUMAN.H11MO.0.B'" in str(ms2),
msg="str(ms2): wrong MotifMap")
self.assertTrue(str(ms2).startswith("MotifSet:{"),
msg="str(ms2): wrong format")
ma = ms2.__getitem__("ALX1_HUMAN.H11MO.0.B")
self.assertTrue(
"'thresholds': {0.005: 3.1595, 0.001: 6.52, 0.0005: 7.778, 0.0001: 10.3565, "
"5e-05: 11.318, 1e-05: 13.4015}" in str(ma),
msg="str(ma): threshold missing")
self.assertTrue("'name': 'ALX1_HUMAN.H11MO.0.B'" in str(ma),
msg="str(ma): wrong Motif")
self.assertTrue(repr(ma) == str(ma),
msg="MotifAnnotation: repr does not equal str")
def test_create_multiple(self):
ms = MotifSet(preload_motifs=["hocomoco", "jaspar_vertebrates"])
self.assertEqual(
len(ms),
2042,
msg=
"motif dictionary must contain sum of motifs in files from jaspar"
"_vertebrates and hocomoco")
def test_create_default(self):
ms = MotifSet()
self.assertEqual(
len(ms),
0,
msg="motif dictionary must be empty by default (no preload)")
motif_list = ms.get_motif_list(1.0, 0.0001)
self.assertEqual(len(motif_list), 0)
search_mode = sys.argv[3]
# pvalue cuttoff for definition of active factors
pvalue = float(sys.argv[4])
# output file
out = sys.argv[5]
# genes to be used as potential targets
filter_targets = []
targets = None
if len(sys.argv) > 6:
targets_file = sys.argv[6]
# reading targets
targets = GeneSet("genes")
targets.read(targets_file)
# starting motif databases
motif_set = MotifSet()
if len(sys.argv) > 7:
motif_set.read_file([sys.argv[7]])
else:
motif_set.read_file([jaspar, uniprobe, internal])
# reading genes
factors = GeneSet("genes")
factors.read(factor_file)
# reading networks
#for f in glob.glob(enrichment_files):
# # use last dir name as name for condition
# condition=os.path.dirname(f)
# condition=condition.split("/")[-1]
motif_set.read_motif_targets_enrichment(enrichment_files, pvalue)
def test_create_non_empty(self):
ms = MotifSet(preload_motifs=True)
self.assertGreater(len(ms.motifs_map),
0,
msg="motif dictionary must be non empty")
def test_create_empty(self):
ms = MotifSet(preload_motifs=False)
self.assertEqual(len(ms.motifs_map),
0,
msg="motif dictionary must be empty")
def test_get_mappings_wrong_key_type(self):
ms = MotifSet()
with self.assertRaises(ValueError):
ms.get_mappings("test")
def test_create_non_empty(self):
ms = MotifSet(preload_motifs="hocomoco")
self.assertGreater(len(ms), 0, msg="motif dictionary must be non empty")
def test_create_empty(self):
ms = MotifSet(preload_motifs=None)
self.assertEqual(len(ms), 0, msg="motif dictionary must be empty")
motif_list = ms.get_motif_list(1.0, 0.0001)
self.assertEqual(len(motif_list), 0)
def setUp(self):
# use CustomDB
self.motif_set = MotifSet(preload_motifs=[os.path.join(os.path.dirname(__file__), "TestCustomDB")],
motif_dbs=True)
def setUp(self):
# we must enforce the use hocomoco as database
self.motif_set = MotifSet(preload_motifs="hocomoco")
import sys
from rgt.GeneSet import GeneSet
from rgt.MotifSet import MotifSet
motifs = [(l.strip("\n")).split("\t")[0] for l in open(sys.argv[1])]
geneset_file = sys.argv[2]
search_mode = sys.argv[3]
# preload all available motifs from the repositories
motif_set = MotifSet(preload_motifs=True)
genes = GeneSet("DC Genes")
genes.read_expression(geneset_file)
# take only a subset of the motifs (using their exact names)
motif_set, _, _ = motif_set.filter(motifs, key_type="name")
# of these new motif set, take the subset of those matching these gene names
# (we only care about the motif2gene mapping)
_, m_g, _ = motif_set.filter(genes.genes,
key_type="gene_names",
search=search_mode)
genes_found = []
not_found = []
print("\t\t" + ("\t".join(genes.cond)))
for m in motifs:
try:
sel_genes = m_g[m]
for g in sel_genes: