Extract dataframe used for pl.heatmap

[akramdi]

Hello,

I was wondering if it was possible to export the dataframe behind the time series heatmap produced with:

top_genes = adata.var['fit_likelihood'].sort_values(ascending=False).index[:300]
scv.pl.heatmap(adata, var_names=top_genes, sortby='latent_time', col_color='clusters', n_convolve=100)

Here's my attempt (fully inspired by the code in plotting/heatmap.py ):

top_genes=var_names
tkey="latent_time"
xkey="Ms"
n_convolve=100
sort=True

time = adata.obs[tkey].values
time = time[np.isfinite(time)]
X = (adata[:, var_names].layers[xkey]
if xkey in adata.layers.keys()
else adata[:, var_names].X
)

if issparse(X): X = X.A

df = pd.DataFrame(X[np.argsort(time)], columns=var_names)
if n_convolve is not None:
	weights = np.ones(n_convolve) / n_convolve
	for gene in var_names:
		try:
			df[gene] = np.convolve(df[gene].values, weights, mode="same")
		except:
			pass  # e.g. all-zero counts or nans cannot be convolved
if sort:
	max_sort = np.argsort(np.argmax(df.values, axis=0))
	df = pd.DataFrame(df.values[:, max_sort], columns=df.columns[max_sort])


outFILE="df.timeSeries.heatmap.sorted.csv"
df.to_csv(outFILE, header=True,index=False)

I can't seem to reproduce the heatmap using this dataframe.. Could someone help me extract it correctly?

Many thanks for the help,
Amira

[WeilerP]

Looks good to me (only skimmed through it). Are you using the same keyword arguments for the plotting as scv.pl.heatmap and plotting df.T?