def cell_type_by_cluster(rdata, cell_assign_fit, tenx_analysis, prefix):
tenx = TenxAnalysis(tenx_analysis)
tenx.load()
fit = pickle.load(open(cell_assign_fit, "rb"))
cell_types = dict(zip(fit["Barcode"], fit["cell_type"]))
sce = SingleCellExperiment.fromRData(rdata)
cluster_labels = tenx.clusters(sce)
clusters = dict(zip(sce.colData["Barcode"], cluster_labels))
data_by_cluster = collections.defaultdict(list)
data_by_celltype = collections.defaultdict(list)
cluster = []
cell_type = []
for barcode, cell in cell_types.items():
try:
cluster.append(str(clusters[barcode]))
cell_type.append(cell)
data_by_celltype[cell] = str(clusters[barcode])
data_by_cluster[str(clusters[barcode])] = cell
except Exception as e:
continue
f, ax = plt.subplots(figsize=(16, 8))
counts = collections.defaultdict(lambda: collections.defaultdict(int))
for cluster, ctype in zip(cluster, cell_type):
counts[cluster][ctype] += 1
fclusters = []
fcelltypes = []
fpercentages = []
for cluster, ctype in counts.items():
total = float(sum(ctype.values()))
for cell in cell_type:
fcelltypes.append(cell)
fclusters.append(cluster)
if cell in ctype:
fpercentages.append(float(ctype[cell]) / total)
else:
fpercentages.append(0.0)
df = pandas.DataFrame({
"Cluster": fclusters,
"Cell Type": fcelltypes,
"Percentage": fpercentages
})
ax = sns.barplot(x="Cluster",
y="Percentage",
hue="Cell Type",
data=df,
palette="tab10")
ax.set_title("Cell Type by Cluster - {}".format(prefix))
plt.tight_layout()
plt.savefig("figures/cell_type_by_cluster.png")
def Run(sampleid, before, finished):
clustering = ".cache/{}/clustering/".format(sampleid)
if not os.path.exists(clustering):
os.makedirs(clustering)
cluster_results = os.path.join(clustering,
"{}_clusters.pkl".format(sampleid))
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)
if not os.path.exists(cluster_results):
clusters = tenx_analysis.clusters(qc.sce)
pickle.dump(clusters, open(cluster_results, "wb"))
else:
clusters = pickle.load(open(cluster_results, "rb"))
tsne_by_cluster(qc.sce, clusters, sampleid, clustering)
umap_by_cluster(qc.sce, clusters, sampleid, clustering)
open(finished, "w").write("Completed")
