def test_raw_assay_type_equivelence(self):
rdata = os.path.join(base_dir, "tests/example_sce.RData")
sce_from_rdata = SingleCellExperiment.fromRData(rdata)
tenx = DropletUtils()
rs4_results = tenx.read10xCounts("/home/ceglian/data/raw_gene_bc_matrices/hg19/")
sce_from_rs4 = SingleCellExperiment(rs4_results)
self.assertEqual(type(sce_from_rdata.assays["counts"]),type(sce_from_rdata.assays["counts"]))
def read10xCountsRaw(tenx_analysis, output):
tenx_analysis.load()
utils = DropletUtils()
counts = utils.read10xCounts(tenx_analysis.raw_matrices())
sce = SingleCellExperiment.fromRS4(counts)
sce.save(output)
return sce
def test_save_and_load_rdata(self):
print("Reading")
tenx = DropletUtils()
rs4_result = tenx.read10xCounts("/home/ceglian/data/raw_gene_bc_matrices/hg19/")
sce = SingleCellExperiment.fromRS4(rs4_result)
print("Writing")
sce.save("tests/sce_1.rdata")
print("Loading...")
sce_saved = SingleCellExperiment.fromRData("tests/sce_1.rdata")
print(sce_saved.assays["counts"].shape)
def Run(sampleid, before, finished, use_corrected=False):
if use_corrected and os.path.exists(".cache/corrected/"):
sce = ".cache/corrected/corrected_sce.rdata"
if not os.path.exists(sce):
utils = DropletUtils()
utils.read10xCounts(".cache/corrected/",
".cache/corrected/corrected_sce.rdata")
else:
tenx = TenxDataStorage(sampleid, version="v3")
tenx.download()
analysis_path = tenx.tenx_path
tenx_analysis = TenxAnalysis(analysis_path)
tenx_analysis.load()
tenx_analysis.extract()
qc = QualityControl(tenx_analysis, sampleid)
sce = qc.sce
if not os.path.exists(".cache/{}/celltypes.rdata".format(sampleid)):
CellAssign.run(sce, config.rho_matrix,
".cache/{}/celltypes.rdata".format(sampleid))
open(finished, "w").write("Completed")
def Analysis(sampleid, before, finished, use_corrected=False):
if use_corrected and os.path.exists(".cache/corrected"):
sce = ".cache/corrected/corrected_sce.rdata"
if not os.path.exists(sce):
utils = DropletUtils()
utils.read10xCounts(".cache/corrected/",
".cache/corrected/corrected_sce.rdata")
filtered_sce = sce
else:
tenx = TenxDataStorage(sampleid, version="v3")
tenx.download()
analysis_path = tenx.tenx_path
tenx_analysis = TenxAnalysis(analysis_path)
tenx_analysis.load()
tenx_analysis.extract()
qc = QualityControl(tenx_analysis, sampleid)
filtered_sce = os.path.join(os.path.split(qc.sce)[0], "sce_cas.rdata")
cellassign_analysis = ".cache/{}/cellassignanalysis/".format(sampleid)
if not os.path.exists(cellassign_analysis):
os.makedirs(cellassign_analysis)
pyfit = os.path.join(".cache/{}/cell_types.pkl".format(sampleid))
assert os.path.exists(pyfit), "No Pyfit Found."
pyfit = pickle.load(open(pyfit, "rb"))
marker_list = GeneMarkerMatrix.read_yaml(config.rho_matrix)
cell_types = marker_list.celltypes()
if "B cell" not in cell_types: cell_types.append("B cell")
celltypes(pyfit, sampleid, cellassign_analysis, known_types=cell_types)
tsne_by_cell_type(filtered_sce,
pyfit,
sampleid,
cellassign_analysis,
known_types=cell_types)
umap_by_cell_type(filtered_sce,
pyfit,
sampleid,
cellassign_analysis,
known_types=cell_types)
open(finished, "w").write("Completed")
def test_symbol_retrieve(self):
tenx = TenxAnalysis("tests/pre_igo")
sce = TenX.read10xCounts(tenx)
print(sce.rowData.keys())
example_rda = os.path.join(base_dir, "tests/example_sce.rda")
sce = SingleCellExperiment.fromRData(example_rda)
print(sce.rowData.keys())
tenx = DropletUtils()
rs4_result = tenx.read10xCounts("tests/hg19/")
sce = SingleCellExperiment.fromRS4(rs4_result)
print(sce.rowData.keys())
example_rda = os.path.join(base_dir, "tests/example_copy_number.rda")
sce = SingleCellExperiment.fromRData(example_rda)
print(sce.rowData.keys())
print(sce.rownames)
print(sce.colnames)
def test_get_assay_with_row_col_data_rs4(self):
tenx = DropletUtils()
rs4_results = tenx.read10xCounts(
"/home/ceglian/data/raw_gene_bc_matrices/hg19/")
sce_from_rs4 = SingleCellExperiment.fromRS4(rs4_results)
def test_read10x_counts_load_rs4(self):
tenx = DropletUtils()
rs4_result = tenx.read10xCounts(
"/home/ceglian/data/raw_gene_bc_matrices/hg19/")
sce_from_rs4 = SingleCellExperiment.fromRS4(rs4_result)
def test_call_empty_drops(self):
rdata = os.path.join(base_dir, "tests/example_sce.RData")
sce_from_rdata = SingleCellExperiment.fromRData(rdata)
tenx = DropletUtils()
assay = sce_from_rdata.assays["counts"]
values = tenx.emptyDrops(assay)
def test_barcode_ranks(self):
rdata = os.path.join(base_dir, "tests/example_sce.RData")
sce_from_rdata = SingleCellExperiment.fromRData(rdata)
tenx = DropletUtils()
assay = sce_from_rdata.assays["counts"]
values = tenx.barcodeRanks(assay)
def emptyDrops(counts):
utils = DropletUtils()
cells = utils.emptyDrops(counts)
cells = cells.slots["listData"]
return dict(zip(cells.names, map(list,list(cells))))
def barcodeRanks(sce):
utils = DropletUtils()
ranks = utils.barcodeRanks(sce.assays["counts"])
return dict(zip(ranks.names, map(list,list(ranks))))
def read10xCountsFiltered(tenx_analysis, output):
utils = DropletUtils()
counts = utils.read10xCounts(tenx_analysis.filtered_matrices())
sce = SingleCellExperiment.fromRS4(counts)
sce.save(output)
return sce
def emptyDrops(tenx_analysis):
utils = DropletUtils()
def barcodeRanks(tenx_analysis):
utils = DropletUtils()
def read10xCounts(tenx_analysis):
utils = DropletUtils()
counts = utils.read10xCounts(tenx_analysis.raw_matrices(config.build))
sce = SingleCellExperiment.fromRS4(counts)
return sce