def test_parse_tag_attributes_with_usecols():
parsed = parse_gtf_and_expand_attributes(
StringIO(GTF_TEXT), restrict_attribute_columns=["tag"])
tag_column = parsed["tag"]
eq_(len(tag_column), 1)
tags = tag_column[0]
eq_(tags, 'cds_end_NF,mRNA_end_NF')
def test_parse_tag_attributes_with_usecols_other_column():
parsed = parse_gtf_and_expand_attributes(
StringIO(GTF_TEXT), restrict_attribute_columns=["exon_id"])
tag_column = parsed.get("tag")
assert tag_column is None, "Expected 'tag' to get dropped but got %s" % (
parsed, )
def test_parse_gtf_lines_with_expand_attributes():
parsed_dict = parse_gtf_and_expand_attributes(StringIO(gtf_text))
# excluding 'attribute' column from required names
expected_columns = REQUIRED_COLUMNS[:8] + [
"gene_id",
"gene_name",
"gene_source",
"gene_biotype",
"transcript_id",
"transcript_name",
"transcript_source",
]
# convert to list since Py3's dictionary keys are a distinct collection type
eq_(list(parsed_dict.keys()), expected_columns)
eq_(list(parsed_dict["seqname"]), ["1", "1"])
# convert to list for comparison since numerical columns may be NumPy arrays
eq_(list(parsed_dict["start"]), [11869, 11869])
eq_(list(parsed_dict["end"]), [14409, 14409])
# can't compare NaN with equality
scores = list(parsed_dict["score"])
assert np.isnan(scores).all(), "Unexpected scores: %s" % scores
eq_(list(parsed_dict["gene_id"]), ["ENSG00000223972", "ENSG00000223972"])
eq_(list(parsed_dict["transcript_id"]), ["", "ENST00000456328"])
# inferred
GTF_TEXT = "\n".join([
"# seqname biotype feature start end score strand frame attribute",
"".join([
"""18\tprotein_coding\tstop_codon\t32630766\t32630768\t.\t-\t0\t""",
"""gene_id "ENSG00000134779"; transcript_id "ENST00000334295"; exon_number "7";"""
""" gene_name "C18orf10";""", """ transcript_name "C18orf10-201";"""
]),
"".join([
"""18\tprotein_coding\texon\t32663078\t32663157\t.\t+\t.\tgene_id "ENSG00000150477"; """,
"""transcript_id "ENST00000383055"; exon_number "1"; gene_name "KIAA1328"; """,
"""transcript_name "KIAA1328-202";"""
]),
])
GTF_DATAFRAME = parse_gtf_and_expand_attributes(StringIO(GTF_TEXT))
def test_create_missing_features_identity():
df_should_be_same = create_missing_features(GTF_DATAFRAME, {})
assert len(GTF_DATAFRAME) == len(df_should_be_same), \
"GTF DataFrames should be same size"
def _check_expanded_dataframe(df):
assert "gene" in set(df["feature"]), \
"Extended GTF should contain gene feature"
assert "transcript" in set(df["feature"]), \
"Extended GTF should contain transcript feature"
C18orf10_201_transcript_mask = ((df["feature"] == "transcript") &
def test_parse_tag_attributes():
parsed = parse_gtf_and_expand_attributes(StringIO(GTF_TEXT))
tag_column = parsed["tag"]
eq_(len(tag_column), 1)
tags = tag_column[0]
eq_(tags, 'cds_end_NF,mRNA_end_NF')