def test_record_guess_refseq():
ref_seq_nuc = [
"NM_123456789", "NR_123456789", "XM_123456789", "XR_123456789"
]
for accn in ref_seq_nuc:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_nuc"
assert rec.type == "nucleotide"
ref_seq_chrom = ["NC_123456789", "XC_123456789"]
for accn in ref_seq_chrom:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_nuc"
assert rec.type == "nucleotide"
ref_seq_prot = [
"NM_123456789", "NR_123456789", "XM_123456789", "XR_123456789"
]
for accn in ref_seq_prot:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_nuc"
assert rec.type == "nucleotide"
def test_record_update():
rec = Db.Record("K9WMR5XBZ1")
summary = OrderedDict([("ACCN", "F6SBJ1"), ("DB", "uniprot"),
("entry_name", "F6SBJ1_HORSE"), ("length", "451"),
("organism-id", "9796"),
("organism", "Equus caballus (Horse)"),
("protein_names", "Caspase"),
("comments",
"Caution (1); Sequence similarities (1)"),
("record", "summary")])
new_rec = Db.Record("F6SBJ1",
gi=None,
_version=None,
_record=None,
summary=summary,
_size=451,
_database="uniprot",
_type="protein",
_search_term="casp9")
rec.update(new_rec)
assert rec.accession == "F6SBJ1"
assert not rec.gi
assert not rec.version
assert not rec.record
assert list(rec.summary) == [
"ACCN", "DB", "entry_name", "length", "organism-id", "organism",
"protein_names", "comments", "record"
]
assert rec.size == 451
assert rec.database == "uniprot"
assert rec.type == "protein"
assert rec.search_term == "casp9"
assert str(
rec
) == "Accession:\tF6SBJ1\nDatabase:\tuniprot\nRecord:\tNone\nType:\tprotein\n"
def test_record_instantiation():
rec = Db.Record("Foo")
assert rec.accession == "Foo"
assert not rec.version
assert not rec.record
assert not rec.summary
assert type(rec.summary) == OrderedDict
assert not rec.size
assert not rec.database
assert not rec.type
assert not rec.search_term
assert str(rec) == "Accession:\tFoo\nDatabase:\tNone\nRecord:\tNone\nType:\tNone\n"
rec = Db.Record("Foo", _size='5746')
assert rec.size == 5746
def test_ensembl_fetch_nucleotide(monkeypatch, capsys, hf):
def patch_ensembl_perform_rest_action(*args, **kwargs):
print("patch_ensembl_perform_rest_action\nargs: %s\nkwargs: %s" %
(args, kwargs))
if "info/species" in args:
with open("%s/ensembl_species.json" % test_files, "r") as ifile:
return json.load(ifile)
elif "sequence/id" in args:
with open("%s/ensembl_sequence.seqxml" % test_files, "r") as ifile:
tmp_file = br.TempFile(byte_mode=True)
tmp_file.write(ifile.read().encode())
return Db.SeqIO.parse(tmp_file.get_handle("r"), "seqxml")
test_files = "%s/mock_resources/test_databasebuddy_clients/" % hf.resource_path
monkeypatch.setattr(Db.EnsemblRestClient, "perform_rest_action",
patch_ensembl_perform_rest_action)
dbbuddy = Db.DbBuddy(", ".join(ACCNS[7:]))
dbbuddy.records['ENSAMEG00000011912'] = Db.Record('ENSAMEG00000011912')
summary = OrderedDict([('organism', 'macropus_eugenii'),
('comments', 'Blahh blahh blahh'),
('name', 'Foo1')])
dbbuddy.records['ENSCJAG00000008732'].summary = summary
client = Db.EnsemblRestClient(dbbuddy)
client.fetch_nucleotide()
capsys.readouterr()
client.dbbuddy.print()
out, err = capsys.readouterr()
assert hf.string2hash(out + err) == "bc7610d5373db0b0fd9835410a182f10"
def test_record_guess_genbank_pdb():
randomly_generated_from_regex = ["2OOX", "4M7U", "700Y", "6TNH_2", "5CTC_C", "52O0", "3QNM"]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_prot"
assert rec.type == "protein"
def test_record_guess_genbank_prot():
randomly_generated_from_regex = ["TXB10644", "DII59567", "FTJ23865", "SRR43454", "OIJ24077", "HNP42487", "TJS12387"]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_prot"
assert rec.type == "protein"
def test_record_guess_genbank_nuc():
randomly_generated_from_regex = ["PU844519", "I96398", "V72255", "M06308", "KP485089", "T79891", "R36898"]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_nuc"
assert rec.type == "nucleotide"
def test_search_ensembl(monkeypatch, capsys, hf):
def patch_ensembl_perform_rest_action(*args, **kwargs):
print("patch_ensembl_perform_rest_action\nargs: %s\nkwargs: %s" % (args, kwargs))
with open("%s/ensembl_species.json" % test_files, "r") as ifile:
return json.load(ifile)
def patch_search_ensembl_empty(*args, **kwargs):
print("patch_search_ensembl_empty\nargs: %s\nkwargs: %s" % (args, kwargs))
return
def patch_search_ensembl_results(*args, **kwargs):
print("patch_search_ensembl_empty\nargs: %s\nkwargs: %s" % (args, kwargs))
with open("%s/ensembl_search_results.txt" % test_files, "r") as ifile:
client.results_file.write(ifile.read())
return
test_files = "%s/mock_resources/test_databasebuddy_clients/" % hf.resource_path
monkeypatch.setattr(Db.EnsemblRestClient, "perform_rest_action", patch_ensembl_perform_rest_action)
monkeypatch.setattr(br, "run_multicore_function", patch_search_ensembl_empty)
dbbuddy = Db.DbBuddy(", ".join(ACCNS[7:]))
client = Db.EnsemblRestClient(dbbuddy)
client.dbbuddy.search_terms = ["Panx3"]
client.dbbuddy.records["ENSLAFG00000006034"] = Db.Record("ENSLAFG00000006034")
client.search_ensembl()
out, err = capsys.readouterr()
assert err == "Searching Ensembl for Panx3...\nEnsembl returned no results\n"
assert not client.dbbuddy.records["ENSLAFG00000006034"].record
monkeypatch.setattr(br, "run_multicore_function", patch_search_ensembl_results)
client.search_ensembl()
assert hf.string2hash(str(client.dbbuddy)) == "95dc1ecce077bef84cdf2d85ce154eef"
assert len(client.dbbuddy.records) == 44
assert client.dbbuddy.records["ENSLAFG00000006034"].database == "ensembl"
def test_liveshell_do_write(monkeypatch, capsys, hf):
monkeypatch.setattr(Db.LiveShell, "cmdloop", mock_cmdloop)
monkeypatch.setattr(Db.LiveShell, "dump_session", lambda _: True)
dbbuddy = Db.DbBuddy()
crash_file = br.TempFile(byte_mode=True)
liveshell = Db.LiveShell(dbbuddy, crash_file)
load_file = "%s/mock_resources/test_databasebuddy_clients/dbbuddy_save.db" % hf.resource_path
liveshell.do_load(load_file)
capsys.readouterr()
tmp_dir = br.TempDir()
# write a summary
monkeypatch.setattr("builtins.input", lambda _: "%s/save1" % tmp_dir.path)
liveshell.do_write(None)
assert os.path.isfile("%s/save1" % tmp_dir.path)
with open("%s/save1" % tmp_dir.path, "r") as ifile:
assert len(ifile.read()) == 249980
out, err = capsys.readouterr()
assert re.search("1407 summary records.*written to.*save1", out)
# write ids/accns
dbbuddy.out_format = "ids"
monkeypatch.setattr(br, "ask", lambda _: True)
dbbuddy.records['O14727'].record = Db.Record('O14727', _record=True)
liveshell.do_write("%s/save2" % tmp_dir.path)
assert os.path.isfile("%s/save2" % tmp_dir.path)
with open("%s/save2" % tmp_dir.path, "r") as ifile:
assert len(ifile.read()) == 18661
out, err = capsys.readouterr()
assert re.search("1407 accessions.*written to.*save2", out)
# Abort summary
monkeypatch.setattr(br, "ask", lambda _: False)
liveshell.do_write("%s/save3" % tmp_dir.path)
assert not os.path.isfile("%s/save3" % tmp_dir.path)
out, err = capsys.readouterr()
assert "Abort..." in out
# Permission error
dbbuddy.out_format = "fasta"
monkeypatch.setattr("builtins.open", OpenPermissionError)
liveshell.do_write("%s/save4" % tmp_dir.path)
assert not os.path.isfile("%s/save4" % tmp_dir.path)
out, err = capsys.readouterr()
assert "Error: You do not have write privileges in the specified directory.\n\n" in out
# File exists
monkeypatch.setattr(br, "ask", lambda _: False)
liveshell.do_write("%s/save2" % tmp_dir.path)
out, err = capsys.readouterr()
assert "Abort..." in out
assert "written" not in out
# Not a directory
liveshell.do_write("%s/ghostdir/save5" % tmp_dir.path)
out, err = capsys.readouterr()
assert "The specified directory does not exist. Please create it before continuing" in out
assert "written" not in out
def test_record_guess_genbank_mga():
randomly_generated_from_regex = ["BJCKQ0111866", "YXRUT6401652", "PVAGD7038775", "OGSVS5937667",
"LPMXX1503516", "NTEWQ3440974", "CTDME6774392"]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_prot"
assert rec.type == "protein"
def test_record_guess_uniprot():
randomly_generated_from_regex = ["K2O417", "I0DZU1", "A8GFV0", "J3K7W6", "O3U582", "C3YWY7GUS7", "Q0L5K7",
"Q5FO16", "K9WMR5XBZ1"]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "uniprot"
assert rec.type == "protein"
def test_record_guess_genbank_genome():
randomly_generated_from_regex = ["LJIJ8045260586", "MRMV14919426", "WBGU8744627061", "WYNM11788712",
"SQVS3339736221", "LVGB461502017", "FAWG101678469"]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_nuc"
assert rec.type == "nucleotide"
def test_record_guess_ensembl():
accns = ["ENSRNOG00000018630", "ENSMUSG00000057666", "ENSPTRG00000004577",
"ENSCAFG00000015077", "ENSPPYG00000004189", "ENSPCAG00000006928",
"ENSOPRG00000012514", "ENSECAG00000022051", "ENSTSYG00000002171",
"FBgn0001987", "FBtr0330306", "FBcl0254909"]
for accn in accns:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ensembl"
assert rec.type == "nucleotide"
def test_record_guess_genbank_gi():
randomly_generated_from_regex = [
"13545654", "1445", "9876513546531", "154351", "135464316", "4684315",
"21240"
]
for accn in randomly_generated_from_regex:
rec = Db.Record(accn)
rec.guess_database()
assert rec.database == "ncbi_nuc"
assert rec.type == "gi_num"
assert str(rec.gi) == accn
assert rec.accession == accn
def mock_big_record_no_dl(_dbbuddy):
_dbbuddy.records["NP_001287575.1"] = Db.Record("NP_001287575.1",
_size=5000001)
def test_record_search(sb_resources):
summary = {
"ACCN": "F6SBJ1",
"DB": "uniprot",
"entry_name": "F6SBJ1_HORSE",
"length": "451",
"organism-id": "9796",
"organism": "Equus caballus (Horse)",
"protein_names": "Caspase",
"comments": "Caution (1); Sequence similarities (1)",
"record": "summary"
}
rec = Db.Record("F6SBJ1", summary=summary, _type="protein")
assert rec.search("*")
assert not rec.search("Foo")
# Length operator True
assert rec.search("(length=451)")
assert rec.search("(length >=451)")
assert rec.search("(length<= 451)")
assert rec.search("(length > 200)")
assert rec.search("(length<500)")
# Length operator False
assert not rec.search("(length=452)")
assert not rec.search("(length>=452)")
assert not rec.search("(length<=450)")
assert not rec.search("(length>500)")
assert not rec.search("(length<200)")
# Length operator errors
with pytest.raises(ValueError) as err:
rec.search("(length!<200)")
assert "Invalid syntax for seaching 'length': length!<200" in str(err)
with pytest.raises(ValueError) as err:
rec.search("(length<>200)")
assert "Invalid operator: <>" in str(err)
del rec.summary['length']
assert not rec.search("(length>200)")
# Other columns
assert rec.search("(ACCN) [A-Z0-9]{6}")
assert not rec.search("(ACCN) [A-Z0-9]{7}")
print(rec.type)
assert rec.search("(Type) prot")
assert not rec.search("(Type) nucl")
assert rec.search("(DB) uniprot")
assert not rec.search("(DB) ncbi")
assert rec.search("(comments)(Caution|Blahh)")
assert not rec.search("(organism)Sheep")
assert rec.search("(entry_name)")
assert rec.search("(entry_name) ")
assert not rec.search("(foo_name)")
# No columns -> params
assert rec.search("F6SBJ1")
assert rec.search("uniprot")
assert rec.search("protein")
# No columns -> summary
assert rec.search("Equus")
assert not rec.search("equus")
assert rec.search("i?equus")
assert rec.search("?iEqUuS")
# Genbank record
sb_obj = sb_resources.get_one("p g")
rec = Db.Record("Mle-Panxα8", _record=sb_obj.records[4])
assert rec.search("Innexin")
assert not rec.search("ML07312abcd")
def test_uniprotrestclient_fetch_proteins(monkeypatch, capsys, hf):
def patch_query_uniprot_search(*args, **kwargs):
print("patch_query_uniprot_search\nargs: %s\nkwargs: %s" %
(args, kwargs))
client.results_file.write(
'''# Search: inx15
A8XEF9 A8XEF9_CAEBR 381 6238 Caenorhabditis briggsae Innexin Function (1); Sequence similarities (1); \
Subcellular location (2)
O61786 O61786_CAEEL 382 6239 Caenorhabditis elegans Innexin Function (1); Sequence similarities (1); \
Subcellular location (2)
A0A0H5SBJ0 A0A0H5SBJ0_BRUMA 129 6279 Brugia malayi (Filarial nematode worm) Innexin Function (1); Sequence \
similarities (1); Subcellular location (1)
E3MGD6 E3MGD6_CAERE 384 31234 Caenorhabditis remanei (Caenorhabditis vulgaris) Innexin Function (1); \
Sequence similarities (1); Subcellular location (2)
//
# Search: inx16
O61787 INX16_CAEEL 372 6239 Caenorhabditis elegans Innexin-16 (Protein opu-16) Function (1); Sequence \
similarities (1); Subcellular location (1)
A0A0V1AZ11 A0A0V1AZ11_TRISP 406 6334 Trichinella spiralis (Trichina worm) Innexin Caution (1); Function (1); \
Sequence similarities (1); Subcellular location (2)
A8XEF8 A8XEF8_CAEBR 374 6238 Caenorhabditis briggsae Innexin Function (1); Sequence similarities (1); \
Subcellular location (2)
A0A0B2VB60 A0A0B2VB60_TOXCA 366 6265 Toxocara canis (Canine roundworm) Innexin Caution (2); Function (1); \
Sequence similarities (1); Subcellular location (1)
A0A0V0W5E2 A0A0V0W5E2_9BILA 410 92179 Trichinella sp. T6 Innexin Caution (2); Function (1); Sequence \
similarities (1); Subcellular location (1)
//''', "w")
return
def patch_query_uniprot_fetch(*args, **kwargs):
print("patch_query_uniprot_fetch\nargs: %s\nkwargs: %s" %
(args, kwargs))
with open("%s/mock_resources/test_databasebuddy_clients/uniprot_fetch.txt" % hf.resource_path, "r") \
as ifile:
client.results_file.write(ifile.read(), "w")
return
def patch_query_uniprot_fetch_nothing(*args, **kwargs):
print("patch_query_uniprot_fetch_nothing\nargs: %s\nkwargs: %s" %
(args, kwargs))
client.results_file.write(
"# Search: A8XEF9,O61786,A0A0H5SBJ0,E3MGD6,O61787,A0A0V1AZ11,A8XEF8,A0A0B2VB60,"
"A0A0V0W5E2\n//\n//", "w")
return
monkeypatch.setattr(Db.UniProtRestClient, "query_uniprot", lambda _: True)
dbbuddy = Db.DbBuddy("inx15,inx16")
client = Db.UniProtRestClient(dbbuddy)
client.fetch_proteins()
out, err = capsys.readouterr()
assert client.results_file.read() == ""
assert "full records from UniProt..." not in err
# Test a single call to query_uniprot
monkeypatch.setattr(Db.UniProtRestClient, "query_uniprot",
patch_query_uniprot_search)
client.search_proteins()
monkeypatch.setattr(Db.UniProtRestClient, "query_uniprot",
patch_query_uniprot_fetch)
client.fetch_proteins()
out, err = capsys.readouterr()
assert "Requesting 9 full records from UniProt..." in err
# Test multicore call to query_uniprot
monkeypatch.setattr(br, "run_multicore_function",
patch_query_uniprot_fetch)
for accn, rec in client.dbbuddy.records.items():
rec.record = None
client.dbbuddy.records["a" * 999] = Db.Record("a" * 999,
_database="uniprot")
client.fetch_proteins()
out, err = capsys.readouterr()
assert "Requesting 10 full records from UniProt..." in err
seq = str(client.dbbuddy.records["A8XEF9"].record.seq)
assert hf.string2hash(seq) == "04f13629336cf6cdd5859c8913b742a5"
# Some edge cases
monkeypatch.setattr(Db.UniProtRestClient, "query_uniprot",
patch_query_uniprot_fetch_nothing)
client.http_errors_file.write("inx15\n%s\n//\n" %
URLError("Fake URLError from Mock"))
client.dbbuddy.records = OrderedDict([("a" * 999,
Db.Record("a" * 999,
_database="uniprot"))])
client.fetch_proteins()
out, err = capsys.readouterr()
assert "Requesting 1 full records from UniProt..." in err
assert "No sequences returned\n\n" in err
assert "The following errors were encountered while querying UniProt with fetch_proteins():" in err
assert hf.string2hash(str(
client.dbbuddy.records["a" *
999])) == "670bf9c6ae5832b42841798d882a7276"
with pytest.raises(ValueError) as err:
client.dbbuddy.records["a" * 1001] = Db.Record("a" * 1001,
_database="uniprot")
client.fetch_proteins()
assert "The provided accession or search term is too long (>1000)." in str(
err)
