def test_clusterfinder_include_duplicates(datadir_copy): # noqa: D103
input_path = str(datadir_copy[INPUT])
cf = ClusterFinder(input_path=input_path,
include_duplicates=True,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
assert len(cf.clusters) == 1
assert cf.clusters[0].nalt == 26
def test_clusterfinder_multiple_cluster(datadir_copy, tmpdir): # noqa: D103
input_path = str(datadir_copy[EXTENDED])
output_bam = tmpdir.join('tagged_clusters.bam')
cf = ClusterFinder(input_path=input_path,
output_bam=output_bam.strpath,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
assert len(cf.clusters) == 3
def test_clusterfinder_single_cluster(datadir_copy): # noqa: D103
input_path = str(datadir_copy[INPUT])
cf = ClusterFinder(input_path=input_path,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
assert len(cf.clusters) == 1
assert cf.clusters[0].nalt == 19
assert cf.clusters[0].reference_name == '3R'
def test_cornercase(datadir_copy, tmpdir): # noqa: D103
input_path = str(datadir_copy[CORNERCASE])
output_gff = tmpdir.join('output.gff').strpath
cf = ClusterFinder(input_path=input_path,
output_gff=output_gff,
min_mapq=-1,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
assert len(cf.clusters) == 1
input_path = str(datadir_copy[CORNERCASE2])
cf = ClusterFinder(input_path=input_path,
output_gff=output_gff,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
assert len(cf.clusters) == 0
input_path = str(datadir_copy[CORNERCASE3])
cf = ClusterFinder(input_path=input_path,
output_gff=output_gff,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
def test_nonevidence(datadir_copy): # noqa: D103
input_path = str(datadir_copy[NON_SUPPORT])
result = ClusterFinder(input_path=input_path).clusters[:4]
assert len(result) == 4
assert result[0].nref == 12
assert result[1].nref == 39
assert result[2].nref == 32
assert result[3].nref == 30
def test_clusterfinder_decoy_chromosome(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[DECOY])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
assert len(clusters.clusters) == 84
def test_clusterfinder_start_end_problem(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[START_END_PROBLEM])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649,
skip_decoy=False)
assert len(clusters.clusters) == 0
def test_clusterfinder_multisample(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[MULTI_H6])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
assert len(clusters.softclip_finder.clusters) == 8
assert clusters.clusters[0].nalt == 1
assert clusters.clusters[0].valid_tsd is False
def test_clusterfinder_split_cluster(datadir_copy, tmpdir): # noqa: D103
input_path = str(datadir_copy[SPLIT_CLUSTER])
cf = ClusterFinder(input_path=input_path,
output_bam=tmpdir.join('output.bam').strpath,
include_duplicates=False,
remove_supplementary_without_primary=False,
output_gff=tmpdir.join('out.gff').strpath,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
assert len(cf.clusters) == 3
assert len(cf.clusters[1]) == 39
assert len(cf.clusters[2]) == 27
assert cf.clusters[1] != cf.clusters[2]
def test_clusterfinder_skip_abnormal(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[ARTEFACT_ACCUMULATION])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649,
skip_decoy=False)
assert len(clusters.clusters) == 26
assert clusters.clusters[2].abnormal
def test_clusterfinder_reorganize_cluster(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[REORGANIZE_CLUSTER])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster = clusters.clusters[-1]
genotype = cluster.genotype_likelihoods
assert genotype.genotype == 'homozygous'
def test_clusterfinder_refine_split(datadir_copy, tmpdir): # noqa: D103
input_path = str(datadir_copy[SPLIT_CLUSTER_OPT])
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=tmpdir.join('output.gff').strpath,
transposon_reference_fasta=None,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster = clusters.clusters[0]
genotype = cluster.genotype_likelihoods
assert genotype.nref == 73
assert genotype.nalt == 117
assert genotype.genotype == 'heterozygous'
def test_clusterfinder_reassemble(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[REASSEMBLE])
genome_reference_fasta = str(datadir_copy[GENOME_FRAGMENT])
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=tmpdir.join('output.gff').strpath,
genome_reference_fasta=genome_reference_fasta,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=480)
assert len(clusters.clusters) == 1
assert clusters.clusters[0].valid_tsd
def test_clusterfinder_refine_coord(datadir_copy, tmpdir): # noqa: D103
input_path = str(datadir_copy[REFINE_COORD])
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=tmpdir.join('output.gff').strpath,
transposon_reference_fasta=None,
max_proper_pair_size=480)
cluster = clusters.clusters[-1]
genotype = cluster.genotype_likelihoods
assert genotype.nref == 0
assert genotype.nalt == 3
assert genotype.genotype == 'homozygous'
def test_clusterfinder_refine_tsd(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
# This cluster should not be split, since there is a small deletion
# associated with a TE insertion.
input_path = str(datadir_copy[REFINE_TSD])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
cluster = clusters.clusters[0]
assert cluster.valid_tsd
def test_clusterfinder_predicted_insertion_rover(
datadir_copy, tmpdir, reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[PREDICTED_INSERTION])
output_gff = tmpdir.join('output.gff').strpath
output_fasta = tmpdir.join('output.fa').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_fasta=output_fasta,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
assert len(clusters.softclip_finder.clusters) == 2
assert len(clusters.clusters[0].feature_args) == 1
def test_clusterfinder_nonsupport(datadir_copy, tmpdir): # noqa: D103
input_path = str(datadir_copy[NON_SUPPORT])
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=None,
transposon_reference_fasta=None,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster = clusters.clusters[-1]
assert cluster.nref == 25 # Could also be 26 -- need to figure that out.
genotype = cluster.genotype_likelihoods
assert genotype.nref == 25
assert genotype.nalt == 1
assert genotype.genotype == 'reference'
def test_clusterfinder_join_cluster_test(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy['join_cluster_test.bam'])
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=tmpdir.join('output.gff').strpath,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster_gate, cluster_rover = clusters.clusters
assert len(cluster_gate) == 1
assert len(cluster_rover) == 21
assert not cluster_gate.valid_tsd
assert cluster_rover.valid_tsd
def test_clusterfinder_skip_abnormal(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[ARTEFACT_ACCUMULATION])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649,
skip_decoy=False)
assert len(clusters.clusters) in (
21, 22
) # TODO: this should really be deterministic, what's going on here?
assert clusters.clusters[2].abnormal
def test_clusterfinder_jockey_not_found(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[JOCKEY_NOT_FOUND])
output_gff = tmpdir.join('output.gff').strpath
output_fasta = tmpdir.join('output.fa').strpath
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_fasta=output_fasta,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
rover, jockey = clusters.clusters
assert rover.insert_reference_name == 'rover'
assert jockey.insert_reference_name == 'transposable_element_Ivk'
def test_clusterfinder_dont_split(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
# This cluster should not be split, since there is a small deletion
# associated with a TE insertion.
input_path = str(datadir_copy[DONT_SPLIT])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
assert len(clusters.clusters) == 1
cluster = clusters.clusters[0]
assert cluster.nref == 18
assert cluster.nalt == 37
def test_clusterfinder_nonsupport_reference_genotype(datadir_copy,
tmpdir): # noqa: D103
input_path = str(datadir_copy[MATE_SUPPORT_REFERENCE_GENOTYPE])
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=None,
transposon_reference_fasta=None,
max_proper_pair_size=578)
cluster = clusters.clusters[-1]
assert cluster.nref == 50 # Could also be 26 -- need to figure that out.
genotype = cluster.genotype_likelihoods
assert genotype.nref == 50
assert genotype.nalt == 2
assert genotype.genotype == 'reference'
def test_clusterfinder_estimate_coverage(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[DONT_MERGE_5])
output_gff = tmpdir.join('output.gff').strpath
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=1500)
assert len(clusters.clusters) == 2
cluster_one = clusters.clusters[0]
assert cluster_one.genotype == 'reference'
assert cluster_one.nref == 66
assert cluster_one.nalt == 4
def test_clusterfinder_homozygous_copia(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[HOMOZYGOUS_COPIA])
output_bam = tmpdir.join('output.bam').strpath
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster = clusters.clusters[0]
assert cluster.nalt == 57
genotype = cluster.genotype_likelihoods
assert genotype.genotype == 'homozygous'
assert genotype.nref == 0
assert genotype.nalt == 57
def test_clusterfinder_clip_assigned_to_insertion(
datadir_copy, tmpdir, reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[CLIP_TO_INSERTION])
output_gff = tmpdir.join('output.gff').strpath
output_vcf = tmpdir.join('output.vcf').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
output_vcf=output_vcf,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
assert len(clusters.softclip_finder.clusters) == 16
assert len(clusters.clusters) == 3
assert clusters.clusters[1].nalt == 66
assert clusters.clusters[1].valid_tsd
assert len(clusters.clusters[1].feature_args) == 2
def test_clusterfinder_nanopore(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[NANOPORE_ROVER])
output_bam = tmpdir.join('output.bam').strpath
output_gff = tmpdir.join('output.gff').strpath
output_fasta = tmpdir.join('output.fasta').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
output_fasta=output_fasta,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster = clusters.clusters[0]
assert cluster.nalt == 6
assert cluster.total_left_count == 1
assert cluster.total_right_count == 5
def test_clusterfinder_check_consistency(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[DONT_MERGE_6])
output_gff = tmpdir.join('output.gff').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=None,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
cluster_one = clusters.clusters[0]
assert cluster_one.genotype == 'reference'
assert cluster_one.nref == 69
assert cluster_one.nalt == 3
cluster_two = clusters.clusters[1]
assert cluster_two.genotype == 'reference'
assert cluster_two.nref == 64
assert cluster_two.nalt == 1
def test_clusterfinder_do_not_merge7(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[DONT_MERGE_7])
output_gff = tmpdir.join('output.gff').strpath
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=900)
assert len(clusters.clusters) == 2
cluster_one, cluster_two = clusters.clusters
assert cluster_one.genotype == 'reference'
assert cluster_one.nref == 31
assert cluster_one.nalt == 2
assert cluster_two.genotype == 'heterozygous'
assert cluster_two.nref == 45
assert cluster_two.nalt == 71
def test_clusterfinder_do_not_merge5(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[DONT_MERGE_5])
output_gff = tmpdir.join('output.gff').strpath
output_bam = tmpdir.join('output.bam').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
max_proper_pair_size=649)
cluster_one = clusters.clusters[0]
assert cluster_one.genotype == 'reference'
assert cluster_one.nref == 108
assert cluster_one.nalt == 4
cluster_two = clusters.clusters[1]
assert cluster_two.genotype == 'reference'
assert cluster_two.nref == 66
assert cluster_two.nalt == 4
def test_clusterfinder_complex_genotype(datadir_copy, tmpdir,
reference_fasta): # noqa: D103, F811
input_path = str(datadir_copy[COMPLEX])
output_bam = tmpdir.join('output.bam').strpath
output_gff = tmpdir.join('output.gff').strpath
output_fasta = tmpdir.join('output.fasta').strpath
clusters = ClusterFinder(input_path=input_path,
output_bam=output_bam,
output_gff=output_gff,
transposon_reference_fasta=reference_fasta,
output_fasta=output_fasta,
max_proper_pair_size=DEFAULT_MAX_PROPER_PAIR_SIZE)
cluster = clusters.clusters[0]
assert cluster.nalt == 28
genotype = cluster.genotype_likelihoods
assert genotype.nref == 17
assert genotype.nalt == 28
assert genotype.genotype == 'heterozygous'
assert len(open(output_fasta).readlines()) == 4