def test_auto_distancing_scrambled(self):
distance_matrix = genome_tools.RegionSet(self.regions1A, self.scrambled_genome)\
.map_intersects(genome_tools.RegionSet(self.regions1B, self.scrambled_genome),
lambda x,y : x.get_genomic_distance(y), slop_distance=75)
self.assertTrue(
np.all(np.array(distance_matrix.todense()).astype(int) == self.auto_distancing_truth)
)
def test_genome_bin_mapping(self):
m2m_map = genome_tools.RegionSet(self.regions1A, self.genome)\
.map_genomic_windows(min_window_overlap_proportion=0.0, regions_to_bins=False)
self.assertTrue(
np.all(m2m_map == self.m2m_map_truth)
)
def load_genes(self):
self.log.append('Loading gene info ...')
self.genes = gene_selection.GeneSet.from_refseq(self._config.get('genome','genes')\
.format(package_path = PACKAGE_PATH, species = self.species), self.genome)
self.gene_loc_set = genome_tools.RegionSet(
[gene.get_tss_region() for gene in self.genes], self.genome)
self.rp_map_locs = np.array(
[r.annotation.get_location() for r in self.gene_loc_set.regions])
def build_binned_rp_map(self, style, rp_decay):
region_set = genome_tools.RegionSet(list(self.genome.list_windows()),
self.genome)
if style == 'basic':
return self._make_basic_rp_map(self.gene_loc_set, region_set,
rp_decay)
elif style == 'enhanced':
return self._make_enhanced_rp_map(self.gene_loc_set, region_set,
rp_decay)
else:
NotImplementedError()
def _make_enhanced_rp_map(self, gene_loc_set, region_set, decay):
#make regions x exons map and exons x genes map
try:
indptr, indices, exons = [0], [], []
for locus in gene_loc_set.regions:
new_exons = locus.annotation.get_exon_regions()
exons.extend(new_exons)
indices.extend(range(indptr[-1], indptr[-1] + len(new_exons)))
indptr.append(indptr[-1] + len(new_exons))
exon_gene_map = sparse.csc_matrix(
(np.ones(len(exons)), indices, indptr),
shape=(len(exons), len(gene_loc_set.regions)))
exons = genome_tools.RegionSet(exons, self.genome)
region_exon_map = region_set.map_intersects(
exons,
distance_function=lambda x, y: x.overlaps(
y, min_overlap_proportion=0.4),
slop_distance=0) #REGIONS X EXONS
region_exon_map = region_exon_map.dot(exon_gene_map).astype(
np.bool)
not_exon_promoter = 1 - region_exon_map.sum(axis=1).astype(np.bool)
basic_rp_map = self._make_basic_rp_map(gene_loc_set, region_set,
decay)
enhanced_rp_map = basic_rp_map.transpose().multiply(
not_exon_promoter) + region_exon_map
return enhanced_rp_map.transpose()
except Exception as err:
print(repr(err))
return region_exon_map, exon_gene_map
def __init__(self,
species,
regions,
rp_map='enhanced',
rp_decay=10000,
isd_method='chipseq',
verbose=4,
log=None):
'''
*class*
**lisa.FromRegions** (species, regions, rp_map = 'enhanced', rp_decay = 10000, isd_method = 'chipseq', verbose = 4, log = None)**
Initialize the LISA test using user-defined regions.
Parameters:
species: {'hg38', 'mm10'}
regions (list of lists/tuples with format [('chr', start, end), ... ]):
User-defined regions.
rp_map ({"basic", "enhanced"}, scipy.sparse_matrix):
RP map type, currently supports "basic" and "enhanced". User may also pass their own RP map as scipy.sparse_matrix in the shape (genes x regions)
rp_decay (float, int):
Decay rate of region influence on gene based on distance from TSS. Increase to prioritize distal regions, decrease to prioritize promoters. Default of 10000 bp is balanced.
isd_method {"chipseq", "motifs"}:
Use ChIP-seq data or motifs to mark TF binding locations.
verbose (int):
Number of levels of log messages to print to stderr
Returns:
lisa object
'''
super().__init__(species,
_config,
100,
isd_method=isd_method,
verbose=verbose,
log=log)
if isinstance(rp_map, str):
rp_map_styles = self._config.get('lisa_params',
'rp_map_styles').split(',')
assert (
rp_map in rp_map_styles
), 'RP map must be numpy/scipy.sparse array, or be one of provided maps: {}'.format(
','.join(rp_map_styles))
else:
assert (
isinstance(rp_map, np.ndarry)
or isinstance(rp_map, scipy.sparse)
), 'RP map must be either numpy ndarry or scipy.sparse matrix'
self.rp_map = rp_map
#self.genome = genome_tools.Genome.from_file(self._config.get('paths','genomes').format(package_path = PACKAGE_PATH, species = self.species), window_size=100)
assert (
isinstance(regions, (list, tuple))
), '"regions" parameter must be list of region tuples in format [ (chr,start,end [,score]), (chr,start,end [,score]) ... ] or name of bed file.'
self.log.append('Validation user-provided regions ...')
self.num_regions_supplied = len(regions)
regions = self._check_region_specification(regions)
self.region_set = genome_tools.RegionSet(regions,
self.data_interface.genome)
self.region_score_map = np.array(
[r.annotation for r in self.region_set.regions])
assert (isinstance(rp_decay, (int, float)) and
rp_decay > 0), 'RP decay parameter must be positive int/float'
self.rp_decay = rp_decay
assert (
len(regions) >= 1000 and len(regions) < 1000000
), 'User must provide atleast 1000 reigons, and less than 1 million.'
