def test_get_weight(db, bam_file, splice_file):
db.get_read_statistics("scaffold_1", bam_file, "H3K4me3")
db.get_splice_statistics("scaffold_1", splice_file, "RNAseq")
from pita.dbcollection import DbCollection
c = DbCollection(db)
model = list(c.get_connected_models())[0][0]
w = c.get_weight(model, "H3K4me3", "all")
assert 365 == w
w = c.get_weight(model, None, "length")
assert 60100 == w
w = c.get_weight(model, "H3K4me3", "rpkm")
assert abs(1163.9 - w) < 0.1
w = c.get_weight(model, "H3K4me3", "weighted")
assert abs(0.01821963394342762 - w) < 0.0001
w = c.get_weight(model, "H3K4me3", "total_rpkm")
assert abs(4292.832 - w) < 0.1
w = c.get_weight(model, "H3K4me3", "mean_exon")
assert abs(1430.944 - w) < 0.1
w = c.get_weight(model, "RNAseq", "splice")
assert 24 == w
w = c.get_weight(model, "H3K4me3", "first")
assert 64 == w
w = c.get_weight(model, None, "evidence")
assert 1 == w
def test_variants(db, variant_track):
from pita.dbcollection import DbCollection
from pita.io import read_bed_transcripts
from pita.util import model_to_bed
for tname, source, exons in read_bed_transcripts(open(variant_track)):
db.add_transcript("{0}{1}{2}".format("t1", "|", tname), source, exons)
c = DbCollection(db)
best_model = [m for m in c.get_connected_models()][0][0]
cuts = [str(e) for e in c.get_node_cuts(best_model)]
assert ["chr1:800+900", "chr1:1400+1500"] == cuts
best_variant = c.get_best_variant(best_model, [{"weight":1,"type":"length","name":"length"}])
s = [str(s) for s in best_variant]
assert ["chr1:100+200", "chr1:400+700", "chr1:800+900", "chr1:1000+1300", "chr1:1400+1500", "chr1:1600+1900", "chr1:2000+2100"] == s
def test_long_exon_filter(db, t1, t2):
from pita.dbcollection import DbCollection
from pita.io import read_bed_transcripts
for tname, source, exons in read_bed_transcripts(open(t1)):
db.add_transcript("{0}{1}{2}".format("t1", "|", tname), source, exons)
for tname, source, exons in read_bed_transcripts(open(t2)):
db.add_transcript("{0}{1}{2}".format("t2", "|", tname), source, exons)
c = DbCollection(db, chrom="chr1")
c.filter_long(evidence=1)
models = []
for cluster in c.get_connected_models():
for m in cluster:
models.append(m)
assert [1,3,5] == sorted([len(m) for m in models])
def test_db_collection(db):
from pita.dbcollection import DbCollection
c = DbCollection(db)
for model in c.get_connected_models():
print model
