This database contains all training datasets for the Gaussian processes emulators (GPEs) trained in the study entitled "Cell to Whole Organ Global Sensitivity Analysis on a Four-chamber Electromechanics Model Using Gaussian Processes Emulators", submitted to PLOS Computational Biology. Every folder contains two csv files: - parameters.csv: the rows are the samples and the columns represent the parameters that were varied in the analysis - outputs.csv: the rows are the samples and the columns represent the values for the output features simulated for each sample In ventricular_cell_model, there are four folders: - ionic: ToR-ORd model samples used to train GPEs to predict the ventricular calcium transient features - contraction_isometric_stretch1.0: ToR-ORd model coupled with the Land contraction model samples used to train GPEs to predict the ventricular active tension transient features. The simulations were isometric contractions with no strain (or stretch 1.0). - contraction_isometric_stretch1.1: ToR-ORd model coupled with the Land contraction model samples used to train GPEs to predict the ventricular active tension transient features. The simulations were isometric contractions with 0.1 strain (or stretch 1.1). - contraction_isotonic: ToR-ORd model coupled with the Land contraction model samples used to train GPEs to predict the ventricular active tension transient features. The simulations were isotonic. The folder atrial_contraction_model follows the same structure, but the ionic model was Courtemanche, used to represent an atrial rather than ventricular calcium transient. The folder tissue_electrophysiology contains the training dataset for the GPEs to predict total atrial and ventricular activation times with an Eikonal model. The folder passive_mechanics contains the training dataset for the GPEs to predict inflated volumes and mean atrial and ventricular fiber strains for a passive inflation. The folder CircAdapt contains the training dataset for the GPEs to predict four-chamber pressure and volume features with the CircAdapt ODE model. Finally, the folder fourchamber contains the samples generated with a 3D-0D four-chamber electromechanics model to predict pressure and volume biomarkers for cardiac function. The details about the model can be found in the original publication.

This work was supported by the Wellcome/EPSRC Centre for Medical Engineering (WT 203148/Z/16/Z). SAN is supported by NIH R01-HL152256, ERC PREDICT-HF 453 (864055), BHF (RG/20/4/34803), EPSRC (EP/P01268X/1). This work was supported by the Technology Missions Fund under the EPSRC Grant EP/X03870X/1 & The Alan Turing Institute. This study received financial support from the French Government as part of the "Investments of the Future" program managed by the National Research Agency (ANR) (ANR-10-IAHU-04). This research has received funding from the European Union's Horizon 2020 research and innovation programme under the ERA-NET co-fund action No. 680969 (ERA-CVD SICVALVES) funded by the Austrian Science Fund (FWF), Grant I 4652-B to CMA. Dr Petras A. was partially supported by the State of Upper Austria. This work used the ARCHER2 UK National Supercomputing Service (https://www.archer2.ac.uk). Dr Neic A. is employed by NumeriCor GmbH, Graz, Austria.