The human heart is enclosed in the pericardial cavity. The pericardium consists of a layered thin sac and is separated from the myocardium by a thin film of fluid. It provides a fixture in space and frictionless sliding of the myocardium. The influence of the pericardium is essential for predictive mechanical simulations of the heart. However, there is no consensus on physiologically correct and computationally tractable pericardial boundary conditions. Here we propose to model the pericardial influence as a parallel spring and dashpot acting in normal direction to the epicardium. Using a four-chamber geometry, we compare a model with pericardial boundary conditions to a model with fixated apex. The influence of pericardial stiffness is demonstrated in a parametric study. Comparing simulation results to measurements from cine magnetic resonance imaging reveals that adding pericardial boundary conditions yields a better approximation with respect to atrioventricular plane displacement, atrial filling, and overall spatial approximation error. We demonstrate that this simple model of pericardial-myocardial inter-M. R. Pfaller * joint last authors action can correctly predict the pumping mechanisms of the heart as previously assessed in clinical studies. Utilizing a pericardial model can not only provide much more realistic cardiac mechanics simulations but also allows new insights into pericardial-myocardial interaction which cannot be assessed in clinical measurements yet.

Background This study is motivated by the following three considerations: a) the physico-chemical properties of transmembrane (TM) proteins are distinctly different from those of globular proteins, necessitating the development of specialized structure prediction techniques, b) for many structural features no specialized predictors for TM proteins are available at all, and c) deep learning algorithms allow to automate the feature engineering process and thus facilitate the development of multi-target methods for predicting several protein properties at once. Results We present AllesTM, an integrated tool to predict almost all structural features of transmembrane proteins that can be extracted from atomic coordinate data. It blends several machine learning algorithms: random forests and gradient boosting machines, convolutional neural networks in their original form as well as those enhanced by dilated convolutions and residual connections, and, finally, long short-term memory architectures. AllesTM outperforms other available methods in predicting residue depth in the membrane, flexibility, topology, relative solvent accessibility in its bound state, while in torsion angles, secondary structure and monomer relative solvent accessibility prediction it lags only slightly behind the currently leading technique SPOT-1D. High accuracy on a multitude of prediction targets and easy installation make AllesTM a one-stop shop for many typical problems in the structural bioinformatics of transmembrane proteins. Conclusions In addition to presenting a highly accurate prediction method and eliminating the need to install and maintain many different software tools, we also provide a comprehensive overview of the impact of different machine learning algorithms and parameter choices on the prediction performance. AllesTM is freely available at https://github.com/phngs/allestm.