latent = pd.read_table(latent_file, index_col=0)
# Have to do this because data_slideseq makes it a numpy array
gene_info = pd.DataFrame(gene_info, columns=['EnsID',
'Symbol']).set_index('EnsID')
counts = pd.DataFrame(counts, index=gene_info.index, columns=barcodes)
num_umi = pd.Series(num_umi, index=barcodes)
# Align to latent space
counts = counts.loc[:, latent.index]
num_umi = num_umi[latent.index]
proj = proj.loc[latent.index]
# need counts, latent, and num_umi
hs = hotspot.Hotspot(counts, latent, num_umi)
hs.create_knn_graph(weighted_graph=False,
n_neighbors=n_neighbors,
neighborhood_factor=3)
# %%
module = 5
module_genes = out_clusters.index[out_clusters == module]
scores = hotspot.modules.compute_scores(counts.loc[module_genes].values, model,
num_umi.values, hs.neighbors.values,
hs.weights.values)
# %% Plot scores
return tot / recovered
dist_mat = np.zeros((cm.shape[0], cm.shape[0]))
cm_np = cm.values
for i in tqdm(range(cm.shape[0])):
for j in range(cm.shape[0]):
dd = dist_fun(cm_np[i, :], cm_np[j, :])
dist_mat[i, j] = dd
dist_mat = pd.DataFrame(dist_mat, index=cm.index, columns=cm.index)
hs = hotspot.Hotspot(counts,
model=model,
distances=dist_mat,
umi_counts=num_umi)
hs.create_knn_graph(weighted_graph=weighted_graph,
n_neighbors=n_neighbors,
neighborhood_factor=3)
results = hs.compute_hotspot(jobs=5)
results = gene_info.join(results, how='right')
results.to_csv(out_file, sep="\t")
# Have to do this because data_slideseq makes it a numpy array
gene_info = pd.DataFrame(gene_info, columns=['EnsID',
'Symbol']).set_index('EnsID')
counts = pd.DataFrame(counts, index=gene_info.index, columns=barcodes)
num_umi = pd.Series(num_umi, index=barcodes)
# Align to latent space
counts = counts.loc[:, latent.index]
num_umi = num_umi[latent.index]
# need counts, latent, and num_umi
valid_genes = (counts > 0).sum(axis=1) >= n_cells_min
counts = counts.loc[valid_genes]
hs = hotspot.Hotspot(counts, model='danb', latent=latent, umi_counts=num_umi)
hs.create_knn_graph(weighted_graph=weighted_graph,
n_neighbors=n_neighbors,
neighborhood_factor=3)
neighbors = hs.neighbors.values
weights = hs.weights.values
norm_counts = counts.values / num_umi.values.reshape((1, -1)) * 10000
norm_counts = np.log(norm_counts + 1)
from hotspot.local_stats_pairs import create_centered_counts
norm_counts = create_centered_counts(counts.values, hs.model, num_umi.values)
num_umi = pd.Series(num_umi, index=barcodes)
valid_cells = set()
for x in t:
if x.is_leaf():
valid_cells.add(x.name)
valid_cells = pd.Index(valid_cells)
# Align to latent space
counts = counts.loc[:, valid_cells]
num_umi = num_umi[valid_cells]
# need counts, latent, and num_umi
latent = pd.DataFrame(0, index=counts.columns, columns=range(10))
hs = hotspot.Hotspot(counts, latent=latent, umi_counts=num_umi)
neighbors, weights = hotspot.knn.tree_neighbors_and_weights(
t, n_neighbors, counts)
weights = hotspot.knn.make_weights_non_redundant(neighbors.values,
weights.values)
weights = pd.DataFrame(weights,
index=neighbors.index,
columns=neighbors.columns)
hs.weights = weights
hs.neighbors = neighbors
if highXMeanCutoff is not None:
