SBMLDataModule Dataloader¶

To load and simulate data from the SBML model, follow the steps below:

Step 1: 📦 Import the module

In [1]:

Copied!

import sys
import os

# Go up to the root where `vpeleaderboard/` is located
sys.path.append(os.path.abspath("../../"))
import sys
import os

# Go up to the root where `vpeleaderboard/` is located
sys.path.append(os.path.abspath("../../"))

In [2]:

Copied!

from vpeleaderboard.data.src.sbml_dataloader import SBMLDataModule
from vpeleaderboard.data.src.sbml_dataloader import SBMLDataModule

c:\Users\hsrak\Documents\VPELeaderboard\myenv\Lib\site-packages\tqdm\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

Step 2: ⚙️ Initialize the SBMLDataModule

Initialize the module by specifying the model base name (without the .xml extension).

In [3]:

Copied!

# Initialize with model base name (without `.xml`)
module = SBMLDataModule(file_name="BIOMD0000000537_url")
# Initialize with model base name (without `.xml`)
module = SBMLDataModule(file_name="BIOMD0000000537_url")

Step 3: 🧹 Prepare the model and config

Prepare the model by loading the configuration YAML and locating the SBML file.

In [4]:

Copied!

module.prepare_data()  # Loads config YAML and locates SBML file
module.prepare_data()  # Loads config YAML and locates SBML file

Step 4: 🧠 Setup the SBML model

Set up the model using the basico method.

In [5]:

Copied!

module.setup()  # Loads the model using basico
module.setup()  # Loads the model using basico

Step 5: 📈 Run simulation and access train DataFrame

Run the simulation and extract the data into a Pandas DataFrame.

In [6]:

Copied!





# Load the dataloader
train_loader = module.train_dataloader()

# Extract the DataFrame directly from the dataset
train_df = train_loader.dataset.data

# Show simulation preview
train_df
# Load the dataloader
train_loader = module.train_dataloader()

# Extract the DataFrame directly from the dataset
train_df = train_loader.dataset.data

# Show simulation preview
train_df

Out[6]:

	sR{serum}	sgp130{serum}	R_IL6_gp130{liver}	IL6{serum}	Ab{serum}	R	sR_IL6{gut}	sR_IL6{liver}	R_IL6_gp130{gut}	Ab_sR{serum}	...	sgp130{liver}	sR_IL6_sgp130{gut}	Ab{peripheral}	sR_IL6_sgp130{liver}	pSTAT3{gut}	STAT3{liver}	CRP Suppression (%)	CRP (% of baseline)	CRP{liver}	geneProduct
Time
0.0	4.253507	3.900000	0.000066	0.000436	2.381820e-29	0.438236	0.001307	0.000976	0.000084	6.104391e-26	...	5.589699	0.136304	1.679209e-29	0.116344	9.389364	0.777537	-0.000000	100.000000	158.325847	159.803597
1.0	0.000031	3.901765	0.000064	0.000638	6.753452e+02	0.000178	0.001055	0.000951	0.000072	7.791481e+00	...	5.591034	0.127067	2.144021e-01	0.114914	9.389266	0.777559	0.000001	99.999999	158.325653	159.802738
2.0	0.000037	3.905215	0.000062	0.000739	6.522828e+02	0.000070	0.000959	0.000916	0.000068	9.015753e+00	...	5.594230	0.115733	4.442855e-01	0.110774	9.388692	0.777686	0.000029	99.999971	158.324515	159.797695
3.0	0.000043	3.907882	0.000060	0.000756	6.303828e+02	0.000049	0.000887	0.000868	0.000065	1.019966e+01	...	5.597806	0.107157	6.659729e-01	0.105075	9.387640	0.777986	0.000156	99.999844	158.321844	159.788467
4.0	0.000049	3.909825	0.000058	0.000755	6.095828e+02	0.000039	0.000826	0.000817	0.000062	1.134655e+01	...	5.600867	0.099879	8.798707e-01	0.098958	9.386196	0.778528	0.000495	99.999505	158.317000	159.775787
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
96.0	0.000960	3.900048	0.000008	0.000643	1.690247e+02	0.000086	0.000002	0.000002	0.000009	6.443776e+01	...	5.581057	0.000269	8.875419e+00	0.000263	8.689731	1.591484	4.118263	95.881737	150.735143	153.432452
97.0	0.000972	3.900045	0.000007	0.000643	1.680433e+02	0.000087	0.000002	0.000002	0.000009	6.483892e+01	...	5.581051	0.000258	8.918491e+00	0.000252	8.677568	1.605962	4.200370	95.799630	150.594039	153.317467
98.0	0.000984	3.900042	0.000007	0.000643	1.670710e+02	0.000088	0.000002	0.000002	0.000009	6.523864e+01	...	5.581045	0.000247	8.961150e+00	0.000241	8.665300	1.620560	4.283303	95.716697	150.451544	153.201341
99.0	0.000995	3.900039	0.000007	0.000643	1.661073e+02	0.000089	0.000002	0.000002	0.000009	6.563691e+01	...	5.581040	0.000237	9.003399e+00	0.000232	8.652927	1.635279	4.367068	95.632932	150.307646	153.084063
100.0	0.001007	3.900036	0.000007	0.000643	1.651518e+02	0.000090	0.000002	0.000002	0.000009	6.603375e+01	...	5.581035	0.000228	9.045242e+00	0.000222	8.640447	1.650118	4.451671	95.548329	150.162334	152.965623

101 rows × 44 columns

In [7]:

Copied!





# Load the dataloader
train_loader = module.val_dataloader()

# Extract the DataFrame directly from the dataset
train_df = train_loader.dataset.data

# Show simulation preview
train_df
# Load the dataloader
train_loader = module.val_dataloader()

# Extract the DataFrame directly from the dataset
train_df = train_loader.dataset.data

# Show simulation preview
train_df

Out[7]:

	sR{serum}	sgp130{serum}	R_IL6_gp130{liver}	IL6{serum}	Ab{serum}	R	sR_IL6{gut}	sR_IL6{liver}	R_IL6_gp130{gut}	Ab_sR{serum}	...	sgp130{liver}	sR_IL6_sgp130{gut}	Ab{peripheral}	sR_IL6_sgp130{liver}	pSTAT3{gut}	STAT3{liver}	CRP Suppression (%)	CRP (% of baseline)	CRP{liver}	geneProduct
Time
100.0	0.001007	3.900036	0.000007	0.000643	165.151830	0.000090	0.000002	1.885293e-06	0.000009	66.033750	...	5.581035	0.000228	9.045242	0.000222	8.640447	1.650118	4.451671	95.548329	150.162334	152.965623
100.3	0.001011	3.900036	0.000007	0.000643	164.866762	0.000090	0.000002	1.863234e-06	0.000009	66.152523	...	5.581034	0.000225	9.057716	0.000220	8.636683	1.654593	4.477216	95.522784	150.118463	152.929863
100.6	0.001014	3.900035	0.000007	0.000643	164.582401	0.000091	0.000002	1.841614e-06	0.000009	66.271167	...	5.581032	0.000223	9.070154	0.000217	8.632909	1.659079	4.502837	95.497163	150.074463	152.893997
100.9	0.001018	3.900034	0.000007	0.000643	164.298740	0.000091	0.000002	1.820424e-06	0.000009	66.389683	...	5.581031	0.000220	9.082556	0.000214	8.629125	1.663576	4.528535	95.471465	150.030335	152.858025
101.2	0.001021	3.900034	0.000007	0.000643	164.015772	0.000091	0.000002	1.799658e-06	0.000009	66.508072	...	5.581030	0.000218	9.094922	0.000212	8.625332	1.668085	4.554309	95.445691	149.986077	152.821947
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
128.8	0.001380	3.900005	0.000005	0.000643	140.176195	0.000128	0.000001	9.195297e-07	0.000007	76.867934	...	5.580976	0.000113	10.088813	0.000106	8.232916	2.131595	7.278681	92.721319	145.316474	149.008650
129.1	0.001384	3.900005	0.000005	0.000643	139.935180	0.000128	0.000001	9.159466e-07	0.000007	76.974824	...	5.580976	0.000113	10.098145	0.000106	8.228154	2.137183	7.312435	92.687565	145.258702	148.961374
129.4	0.001388	3.900005	0.000005	0.000643	139.694472	0.000129	0.000001	9.124256e-07	0.000007	77.081590	...	5.580976	0.000113	10.107447	0.000106	8.223382	2.142783	7.346285	92.653715	145.200767	148.913962
129.7	0.001392	3.900005	0.000005	0.000643	139.454070	0.000129	0.000001	9.089656e-07	0.000007	77.188233	...	5.580976	0.000112	10.116719	0.000105	8.218598	2.148395	7.380231	92.619769	145.142669	148.866414
130.0	0.001397	3.900005	0.000005	0.000643	139.213971	0.000129	0.000001	9.055653e-07	0.000007	77.294752	...	5.580975	0.000112	10.125962	0.000105	8.213803	2.154020	7.414273	92.585727	145.084408	148.818730

101 rows × 44 columns

In [8]:

Copied!





# Load the dataloader
train_loader = module.test_dataloader()

# Extract the DataFrame directly from the dataset
train_df = train_loader.dataset.data

# Show simulation preview
train_df
# Load the dataloader
train_loader = module.test_dataloader()

# Extract the DataFrame directly from the dataset
train_df = train_loader.dataset.data

# Show simulation preview
train_df

Out[8]:

	sR{serum}	sgp130{serum}	R_IL6_gp130{liver}	IL6{serum}	Ab{serum}	R	sR_IL6{gut}	sR_IL6{liver}	R_IL6_gp130{gut}	Ab_sR{serum}	...	sgp130{liver}	sR_IL6_sgp130{gut}	Ab{peripheral}	sR_IL6_sgp130{liver}	pSTAT3{gut}	STAT3{liver}	CRP Suppression (%)	CRP (% of baseline)	CRP{liver}	geneProduct
Time
130.0	0.001397	3.900005	0.000005	0.000643	139.213971	0.000129	1.021915e-06	9.055653e-07	0.000007	77.294752	...	5.580975	0.000112	10.125962	0.000105	8.213803	2.154020	7.414273	92.585727	145.084408	148.818730
130.5	0.001404	3.900005	0.000005	0.000643	138.814482	0.000130	1.016836e-06	9.000287e-07	0.000007	77.472009	...	5.580975	0.000111	10.141299	0.000104	8.205787	2.163421	7.471227	92.528773	144.986941	148.738951
131.0	0.001411	3.900005	0.000005	0.000643	138.415819	0.000131	1.011916e-06	8.946486e-07	0.000007	77.648924	...	5.580975	0.000111	10.156554	0.000103	8.197739	2.172857	7.528449	92.471551	144.889019	148.658791
131.5	0.001418	3.900005	0.000005	0.000643	138.017981	0.000132	1.007151e-06	8.894215e-07	0.000007	77.825496	...	5.580975	0.000110	10.171727	0.000103	8.189660	2.182326	7.585942	92.414058	144.790638	148.578249
132.0	0.001426	3.900004	0.000005	0.000643	137.620962	0.000132	1.002538e-06	8.843432e-07	0.000006	78.001725	...	5.580974	0.000109	10.186818	0.000102	8.181550	2.191830	7.643706	92.356294	144.691798	148.497322
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
178.0	0.002237	3.900000	0.000003	0.000643	104.073070	0.000217	8.993366e-07	7.262020e-07	0.000004	92.687652	...	5.580967	0.000095	11.249528	0.000085	7.293227	3.216138	14.272712	85.727288	133.382560	139.173850
178.5	0.002248	3.900000	0.000003	0.000643	103.737957	0.000218	9.000409e-07	7.261637e-07	0.000004	92.829869	...	5.580967	0.000095	11.257798	0.000085	7.281962	3.228905	14.360736	85.639264	133.232879	139.049463
179.0	0.002259	3.900000	0.000003	0.000643	103.403456	0.000219	9.007694e-07	7.261462e-07	0.000004	92.971691	...	5.580967	0.000095	11.266003	0.000085	7.270662	3.241707	14.449138	85.550862	133.082567	138.924522
179.5	0.002269	3.900000	0.000003	0.000643	103.069566	0.000220	9.015220e-07	7.261493e-07	0.000004	93.113118	...	5.580967	0.000095	11.274143	0.000085	7.259326	3.254543	14.537921	85.462079	132.931624	138.799027
180.0	0.002280	3.900000	0.000003	0.000643	102.736288	0.000221	9.022986e-07	7.261728e-07	0.000004	93.254148	...	5.580967	0.000095	11.282218	0.000085	7.247955	3.267413	14.627084	85.372916	132.780047	138.672974

101 rows × 44 columns