def test_num_groups_vs_endpoints(here, paths, query, span_cost):
primers = make_linear(load_fasta_glob(paths["primers"]))
templates = load_genbank_glob(paths["templates"])
query_path = join(here, "data/test_data/genbank/designs", query)
queries = make_circular(load_genbank_glob(query_path))
design = Design(span_cost)
design.add_materials(primers=primers, templates=templates, queries=queries)
design._blast()
containers = design.container_list
assert len(containers) == 1
container = containers[0]
container.expand()
groups = container.groups()
print(len(groups)**2)
a_arr = set()
b_arr = set()
for g in groups:
a_arr.add(g.query_region.a)
b_arr.add(g.query_region.b)
print(len(a_arr) * len(b_arr))
def test_not_raise_pyblast_when_unique(here):
subjects = load_genbank_glob(
join(here, "data/test_data/genbank/templates/*.gb"))
queries = load_genbank_glob(
join(here, "data/test_data/genbank/designs/*.gb"))
force_unique_record_ids(subjects + queries)
print("n_queres: {}".format(len(queries)))
BioBlast(subjects, queries)
def test_raises_pyblast_when_not_unique(here):
subjects = load_genbank_glob(
join(here, "data/test_data/genbank/templates/*.gb"))
queries = load_genbank_glob(
join(here, "data/test_data/genbank/designs/*.gb"))
print("n_queres: {}".format(len(queries)))
print("n_subjects: {}".format(len(subjects)))
with pytest.raises(PyBlastException):
BioBlast(subjects, queries)
def blast_factory(paths) -> BioBlastFactory:
factory = BioBlastFactory()
primers = make_linear(load_fasta_glob(paths[PRIMERS]))
templates = load_genbank_glob(paths[REGISTRY])
queries = make_circular(load_genbank_glob(paths[QUERIES]))
factory.add_records(primers, PRIMERS)
factory.add_records(templates, TEMPLATES)
factory.add_records(queries, QUERIES)
return factory
def test_benchmark_blast(benchmark, here, paths, query):
primers = make_linear(load_fasta_glob(paths["primers"]))
templates = load_genbank_glob(paths["templates"])
query_path = join(here, "data/test_data/genbank/designs", query)
queries = make_circular(load_genbank_glob(query_path))
design = Design()
design.add_materials(primers=primers, templates=templates, queries=queries)
design._blast()
benchmark(design._blast)
def make_blast():
subjects = load_genbank_glob(join(
here, "data/test_data/genbank/templates/*.gb"),
force_unique_ids=True)
queries = load_genbank_glob(
join(
here,
"data/test_data/genbank/designs/pmodkan-ho-pact1-z4-er-vpr.gb"
),
force_unique_ids=True,
)
queries = make_circular(queries)
assert is_circular(queries[0])
return BioBlast(subjects, queries)
def run(self, n_jobs: int = 10):
"""Run a design job.
:param n_jobs: number of parrallel jobs to run. (default: 10)
:return:
"""
import warnings
warnings.simplefilter(action="ignore", category=RuntimeWarning)
warnings.simplefilter(action="ignore", category=BiopythonParserWarning)
self._logger.info("Loading sequence files")
primers = make_linear(load_fasta_glob(self._primers))
templates = make_circular(load_genbank_glob(self._templates))
fragments = make_linear(load_genbank_glob(self._fragments))
goals = make_circular(load_genbank_glob(self._goals))
design = Design()
design.n_jobs = n_jobs
design.add_materials(primers=primers,
templates=templates,
fragments=fragments,
queries=goals)
self._logger.info("Getting span cost model")
span_cost = self._get_span_cost()
design.span_cost = span_cost
self._logger.info("Compiling possible molecular assemblies")
design.compile()
self._logger.info("Optimizing molecular assemblies")
design.optimize()
self._logger.info("Designing assembly primers and fragments")
df, adf, design_json = design.to_df()
adf.to_csv("summary.csv")
df.to_csv("sequence_design.csv")
records = []
for result in design.results.values():
if result.assemblies:
a = result.assemblies[0]
for i, role, m in a.molecules:
records.append(m.sequence)
SeqIO.write(records, os.path.join(self._directory, "sequences.gb"),
"genbank")
def test_multiquery_blast(here):
subjects = load_genbank_glob(join(here,
"data/test_data/genbank/templates/*.gb"),
force_unique_ids=True)
queries = load_genbank_glob(join(here,
"data/test_data/genbank/designs/*.gb"),
force_unique_ids=True)
print("n_queres: {}".format(len(queries)))
print("n_subjects: {}".format(len(subjects)))
bioblast = BioBlast(subjects, queries)
results = bioblast.blastn()
recids = set()
for res in results:
recid = res["query"]["origin_record_id"]
recids.add(recid)
print("n_records: {}".format(len(results)))
assert len(recids) == len(queries)
def _get_results_func(n_jobs):
if True:
print("PROCESSING!")
primers = make_linear(load_fasta_glob(paths["primers"]))
templates = load_genbank_glob(paths["templates"])
query_path = join(here, "data/test_data/genbank/designs/*.gb")
queries = make_circular(
load_genbank_glob(query_path))[:LIM_NUM_DESIGNS]
design = Design(span_cost=cached_span_cost)
design.add_materials(primers=primers,
templates=templates,
queries=queries)
if n_jobs > 1:
design._run_with_pool(n_jobs, 1)
else:
design.run()
return design, design.results
def test_self_blast(here):
subjects = load_genbank_glob(join(here,
"data/test_data/genbank/templates/*.gb"),
force_unique_ids=True)
queries = [
SeqRecord(Seq(str(subjects[0][:1000].seq))),
# SeqRecord(Seq(str(subjects[1][:1000]))),
]
force_unique_record_ids(make_linear(queries))
bioblast = BioBlast(queries, queries)
results = bioblast.blastn()
assert not results
def test_library_design_to_df_2(paths, here, span_cost):
primers_path = join(here, "data/test_data_sd2", "primers.fasta")
fragments_path = join(here, "data/test_data_sd2", "fragments", "*.gb")
plasmids_path = join(here, "data/test_data_sd2", "plasmids", "*.gb")
designs_path = join(here, "data/test_data_sd2", "designs", "*.gb")
primers = make_linear(load_fasta_glob(primers_path))
templates = load_genbank_glob(plasmids_path)
fragments = load_genbank_glob(fragments_path)
print(fragments_path)
queries = make_circular(load_genbank_glob(designs_path))
design = LibraryDesign(span_cost=span_cost)
design.n_jobs = 1
design.add_materials(
primers=primers,
templates=make_circular(templates),
queries=queries,
fragments=make_linear(fragments),
)
design.logger.set_level("DEBUG")
design.compile()
results = design.optimize()
for result in results.values():
assembly = result.assemblies[0]
print(assembly.to_df())
#
a, b, c = design.to_df()
a.to_csv("library_design.csv")
b.to_csv("library_summary.csv")
with open("designs.json", "w") as f:
json.dump(c, f)
print(a)
print(b)
print(c)
def test_bioblast_factory_init(here):
subjects = load_genbank_glob(join(here,
"data/test_data/genbank/templates/*.gb"),
force_unique_ids=True)
queries = load_genbank_glob(join(here,
"data/test_data/genbank/designs/*.gb"),
force_unique_ids=True)
primers = load_fasta_glob(join(here, "data/test_data/primers/*.fasta"))
factory = BioBlastFactory()
factory.add_records(make_linear(primers), "primers")
factory.add_records(queries, "queries")
factory.add_records(subjects, "subjects")
primer_blaster = factory("primers", "queries")
template_blaster = factory("subjects", "queries")
primer_results = primer_blaster.blastn_short()
template_results = template_blaster.blastn()
print(len(primer_results))
print(len(template_results))
def make_blast():
subjects = load_fasta_glob(join(
here, "data/test_data/primers/primers.fasta"),
force_unique_ids=True)
subjects = make_linear(subjects)
queries = load_genbank_glob(
join(
here,
"data/test_data/genbank/designs/pmodkan-ho-pact1-z4-er-vpr.gb"
),
force_unique_ids=True,
)
return BioBlast(subjects, queries)
def test_library_design_to_df(paths, here, span_cost):
primers = make_linear(load_fasta_glob(paths["primers"]))
templates = load_genbank_glob(paths["templates"])
query_path = join(here, "data/test_data/genbank/library_designs/*.gb")
queries = make_circular(load_genbank_glob(query_path))
queries = queries
design = LibraryDesign(span_cost=span_cost)
design.n_jobs = 1
design.add_materials(primers=primers, templates=templates, queries=queries)
design.logger.set_level("DEBUG")
design.compile()
results = design.optimize()
print(results)
a, b, c = design.to_df()
a.to_csv("library_design.csv")
b.to_csv("library_summary.csv")
with open("designs.json", "w") as f:
json.dump(c, f)
print(a)
print(b)
print(c)
def test_unnamed_queries_raises_duplicate_error(here):
subjects = load_genbank_glob(join(here,
"data/test_data/genbank/templates/*.gb"),
force_unique_ids=True)
seqstr1 = str(subjects[0].seq)[:1000]
seqstr2 = str(subjects[1].seq)[:1000]
queries = [
SeqRecord(Seq(seqstr1)),
SeqRecord(Seq(seqstr2))
# SeqRecord(Seq(str(subjects[1][:1000]))),
]
make_linear(queries)
with pytest.raises(PyBlastException):
BioBlast(subjects, queries)
def test(paths):
factory = BioBlastFactory()
templates = load_genbank_glob(paths[TEMPLATES])
subject = templates[0]
query = subject.reverse_complement()
templates = make_linear([subject])
queries = make_linear([query])
factory.add_records(templates, TEMPLATES)
factory.add_records(queries, QUERIES)
blast = factory(TEMPLATES, QUERIES)
results = blast.blastn()
assert results[0]["subject"]["strand"] == -1
assert results[0]["subject"]["start"] == len(templates[0])
def test_validate_rc(here):
queries = load_genbank_glob(join(here,
"data/test_data/genbank/designs/*.gb"),
force_unique_ids=True)
templates = make_linear(queries[:1])
queries = make_linear([templates[0].reverse_complement()])
factory = BioBlastFactory()
factory.add_records(queries, "queries")
factory.add_records(templates, "templates")
blaster = factory("templates", "queries")
results = blaster.blastn()
assert results[0]["subject"]["strand"] == -1
assert results[0]["query"]["strand"] == 1
assert results[0]["subject"]["start"] == len(queries[0])
def test_unnamed_queries(here):
subjects = load_genbank_glob(join(here,
"data/test_data/genbank/templates/*.gb"),
force_unique_ids=True)
seqstr1 = str(subjects[0].seq)[:1000]
seqstr2 = str(subjects[1].seq)[:1000]
queries = [
SeqRecord(Seq(seqstr1)),
SeqRecord(Seq(seqstr2))
# SeqRecord(Seq(str(subjects[1][:1000]))),
]
force_unique_record_ids(make_linear(queries))
bioblast = BioBlast(subjects, queries)
results = bioblast.blastn()
recids = set()
for res in results:
recid = res["query"]["origin_record_id"]
recids.add(recid)
print("n_records: {}".format(len(results)))
assert len(recids) == len(queries)
