def get_human_22_fake_genome():
from mbf_genomics.testing import MockGenome
import gzip
genes = pd.read_msgpack(
gzip.GzipFile(get_sample_data(Path("mbf_align/hs_22_genes.msgpack.gz")))
).reset_index()
tr = pd.read_msgpack(
gzip.GzipFile(get_sample_data(Path("mbf_align/hs_22_transcripts.msgpack.gz")))
).reset_index()
return MockGenome(df_genes=genes, df_transcripts=tr, chr_lengths={"22": 50_818_468})
def get_human_22_fake_genome():
import gzip
genes = pd.read_msgpack(
gzip.GzipFile(
mbf_sampledata.get_sample_path("mbf_align/hs_22_genes.msgpack.gz")
)
).reset_index()
tr = pd.read_msgpack(
gzip.GzipFile(
mbf_sampledata.get_sample_path("mbf_align/hs_22_transcripts.msgpack.gz")
)
).reset_index()
genes["chr"] = "chr22"
tr["chr"] = "chr22"
return MockGenome(
df_genes=genes, df_transcripts=tr, chr_lengths={"chr22": 50_818_468}
)
def test_simple(self):
genome = MockGenome(
pd.DataFrame({
"stable_id": ["a", "b", "c"],
"chr": "1",
"tss": [0, 100, 1000],
"tes": [10, 101, 1010],
}),
df_genes_meta=pd.DataFrame({
"gene_stable_id": ["a", "b", "c"],
"description": ["hello", "world", "!"],
}).set_index("gene_stable_id"),
)
g = genes.Genes(genome)
anno = genes.annotators.Description()
g += anno
force_load(g.annotate())
ppg.run_pipegraph()
assert "description" in g.df.columns
assert (g.df.sort_values("gene_stable_id")["description"] == [
"hello", "world", "!"
]).all()
def test_simple(self, tmpdir):
genome = MockGenome(
pd.DataFrame({
"stable_id": ["a", "b", "c"],
"chr": "1",
"tss": [0, 100, 1000],
"tes": [10, 101, 1010],
}),
df_genes_meta=pd.DataFrame({
"gene_stable_id": ["a", "b", "c"],
"description": ["hello", "world", "!"],
}).set_index("gene_stable_id"),
)
g = genes.Genes(genome)
df_to_add = pd.DataFrame(
{
"testcol": [1, 2, 3],
"index_vals": ["a", "b", "d"]
},
index=["a", "b", "d"])
tmp_path = Path(tmpdir) / "dump.tsv"
df_to_add.to_csv(tmp_path, sep="\t", index=False)
anno = genes.annotators.FromFile(
tmp_path,
columns_to_add=["testcol"],
index_column_table="index_vals",
index_column_genes="gene_stable_id",
fill_value=-1,
)
g += anno
force_load(g.annotate())
ppg.run_pipegraph()
print(g.df.index)
print(g.df)
assert "testcol" in g.df.columns
assert g.df.loc[0]["testcol"] == 1
assert g.df.loc[1]["testcol"] == 2
assert g.df.loc[2]["testcol"] == -1
assert len(g.df) == 3