Tutorial 4: Visualization¶

Plotting helpers work with tensors, network arrays, manifold outputs, and differential-regulation tables produced by the workflows.

In [1]:

%matplotlib inline
from scTenifold import compare_networks, scTenifoldNet
from scTenifold.data import get_test_df
from scTenifold.plotting import plot_hist, plot_network_heatmap, plot_qqplot

x = get_test_df(n_cells=80, n_genes=40, random_state=0)
y = get_test_df(n_cells=80, n_genes=40, random_state=1)

%matplotlib inline from scTenifold import compare_networks, scTenifoldNet from scTenifold.data import get_test_df from scTenifold.plotting import plot_hist, plot_network_heatmap, plot_qqplot x = get_test_df(n_cells=80, n_genes=40, random_state=0) y = get_test_df(n_cells=80, n_genes=40, random_state=1)

Build a small result¶

For plotting intermediate tensors, use the class API.

In [2]:

model = scTenifoldNet(
    x,
    y,
    "control",
    "condition",
    qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0},
    nc_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0, "backend": "serial"},
    td_kws={"K": 2, "max_iter": 20, "init": "random"},
    ma_kws={"d": 2},
)
model.build()

model = scTenifoldNet( x, y, "control", "condition", qc_kws={"min_lib_size": 1, "plot": False, "max_mito_ratio": 1.0, "min_percent": 0}, nc_kws={"n_nets": 2, "n_samp_cells": 25, "q": 0, "backend": "serial"}, td_kws={"K": 2, "max_iter": 20, "init": "random"}, ma_kws={"d": 2}, ) model.build()

Removed 0 cells with lib size < 1
Removed 0 outlier cells from original data
Found mitochondrial genes: ['MT-1', 'MT-10', 'MT-2', 'MT-3', 'MT-4', 'MT-5', 'MT-6', 'MT-7', 'MT-8', 'MT-9']
Removed 0 samples from original data (mt genes ratio > 1.0)
Removed 0 genes expressed in less than 0 of data
Removed 0 genes with expression values: average < 0 or sum < 0
finish QC: control
Removed 0 cells with lib size < 1
Removed 0 outlier cells from original data
Found mitochondrial genes: ['MT-1', 'MT-10', 'MT-2', 'MT-3', 'MT-4', 'MT-5', 'MT-6', 'MT-7', 'MT-8', 'MT-9']
Removed 0 samples from original data (mt genes ratio > 1.0)
Removed 0 genes expressed in less than 0 of data
Removed 0 genes with expression values: average < 0 or sum < 0
finish QC: condition
process qc finished in 0.010431443000015861 secs.
make_networks  processing time:  0.11921537599937437

make_networks  processing time:  0.11902902600013476
process nc finished in 0.2391113330004373 secs.
Using tensorly
(40, 40, 2)
tensor_decomp  processing time:  0.00449678600034531
Using tensorly
(40, 40, 2)
tensor_decomp  processing time:  0.004096064999430382
process td finished in 0.009546962000058556 secs.
manifold_alignment  processing time:  0.0024742929999774788
process ma finished in 0.002513353000722418 secs.
d_regulation  processing time:  0.011251283999627049
process dr finished in 0.011294083999928262 secs.

Out[2]:

	Gene	Distance	boxcox-transformed distance	Z	FC	p-value	adjusted p-value
34	NG-4	0.029244	-1.382743	2.033638	3.698975	0.054446	0.669520
31	NG-29	0.027043	-1.390411	1.787239	3.163037	0.075323	0.669520
10	NG-1	0.024698	-1.398821	1.516972	2.638354	0.104312	0.669520
37	NG-7	0.023560	-1.403003	1.382574	2.400828	0.121271	0.669520
21	NG-2	0.021716	-1.409936	1.159797	2.039616	0.153248	0.669520
13	NG-12	0.021076	-1.412387	1.081014	1.921230	0.165721	0.669520
7	MT-7	0.019370	-1.419056	0.866696	1.622804	0.202701	0.669520
11	NG-10	0.018749	-1.421535	0.787053	1.520416	0.217557	0.669520
5	MT-5	0.018358	-1.423109	0.736469	1.457703	0.227296	0.669520
36	NG-6	0.018210	-1.423707	0.717235	1.434323	0.231060	0.669520
3	MT-3	0.017761	-1.425537	0.658447	1.364433	0.242771	0.669520
28	NG-26	0.017729	-1.425669	0.654208	1.359484	0.243627	0.669520
29	NG-27	0.017520	-1.426525	0.626701	1.327665	0.249221	0.669520
8	MT-8	0.017387	-1.427074	0.609063	1.307530	0.252842	0.669520
38	NG-8	0.016313	-1.431550	0.465213	1.150939	0.283353	0.669520
23	NG-21	0.016251	-1.431809	0.456883	1.142281	0.285171	0.669520
16	NG-15	0.015174	-1.436408	0.309103	0.995890	0.318307	0.669520
4	MT-4	0.015082	-1.436804	0.296370	0.983904	0.321237	0.669520
22	NG-20	0.015065	-1.436878	0.293984	0.981669	0.321787	0.669520
30	NG-28	0.014473	-1.439462	0.210957	0.906010	0.341175	0.669520
35	NG-5	0.014167	-1.440814	0.167518	0.868042	0.351498	0.669520
17	NG-16	0.012110	-1.450164	-0.132955	0.634331	0.425771	0.729819
9	MT-9	0.011887	-1.451212	-0.166622	0.611152	0.434354	0.729819
32	NG-3	0.011696	-1.452113	-0.195592	0.591670	0.441774	0.729819
15	NG-14	0.011331	-1.453849	-0.251357	0.555357	0.456137	0.729819
24	NG-22	0.010439	-1.458181	-0.390582	0.471319	0.492381	0.743579
0	MT-1	0.010106	-1.459827	-0.443484	0.441784	0.506263	0.743579
26	NG-24	0.009347	-1.463660	-0.566651	0.377909	0.538724	0.743579
14	NG-13	0.009333	-1.463732	-0.568981	0.376765	0.539339	0.743579
33	NG-30	0.008915	-1.465893	-0.638424	0.343729	0.557685	0.743579
12	NG-11	0.008206	-1.469633	-0.758585	0.291282	0.589400	0.753433
1	MT-10	0.007914	-1.471211	-0.809295	0.270874	0.602746	0.753433
39	NG-9	0.006644	-1.478307	-1.037349	0.190936	0.662139	0.802592
6	MT-6	0.006147	-1.481211	-1.130661	0.163454	0.685996	0.807055
18	NG-17	0.004996	-1.488279	-1.357776	0.107964	0.742475	0.836668
20	NG-19	0.004785	-1.489635	-1.401360	0.099026	0.753001	0.836668
25	NG-23	0.003878	-1.495714	-1.596716	0.065047	0.798689	0.854055
2	MT-2	0.003336	-1.499585	-1.721123	0.048137	0.826337	0.854055
27	NG-25	0.003212	-1.500503	-1.750598	0.044620	0.832704	0.854055
19	NG-18	0.002612	-1.505121	-1.899023	0.029513	0.863601	0.863601

QC histogram¶

In [3]:

plot_hist(x, "control")

plot_hist(x, "control")

Tensor heatmap¶

In [4]:

plot_network_heatmap(model.tensor_dict["control"].to_numpy())

plot_network_heatmap(model.tensor_dict["control"].to_numpy())

Differential regulation QQ plot¶

In [5]:

plot_qqplot(model.d_regulation)

plot_qqplot(model.d_regulation)

The documentation build executes this notebook with the inline Matplotlib backend, so figures are rendered into the generated page.