Search for: All records

Cardiomyocytes (CMs), the contractile heart cells that can be derived from human induced pluripotent stem cells (hiPSCs). These hiPSC derived CMs can be used for cardiovascular disease drug testing and regeneration therapies, and they have therapeutic potential. Currently, hiPSC-CM differentiation cannot yet be controlled to yield specific heart cell subtypes consistently. Designing differentiation processes to consistently direct differentiation to specific heart cells is important to realize the full therapeutic potential of hiPSC-CMs. A model that accurately represents the dynamic changes in cell populations from hiPSCs to CMs over the differentiation timeline is a first step towards designing processes for directing differentiation. This paper introduces a microsimulation model for studying temporal changes in the hiPSC-to-early CM differentiation. The differentiation process for each cell in the microsimulation model is represented by a Markov chain model (MCM). The MCM includes cell subtypes representing key developmental stages in hiPSC differentiation to early CMs. These stages include pluripotent stem cells, early primitive streak, late primitive streak, mesodermal progenitors, early cardiac progenitors, late cardiac progenitors, and early CMs. The time taken by a cell to transit from one state to the next state is assumed to be exponentially distributed. The transition probabilities of the Markov chain process and the mean duration parameter of the exponential distribution were estimated using Bayesian optimization. The results predicted by the MCM agree with the data. 

Cardiomyocytes (CMs) are heart cells responsible for heart contraction and relaxation. CMs can be derived from human induced pluripotent stem cells (hiPSCs) with high yield and purity. Mature CMs can potentially replace dead and dysfunctional cardiac tissue and be used for screening cardiac drugs and toxins. However, hiPSCs-derived CMs (hiPSC-CMs) are immature, which limits their utilization. Therefore, it is crucial to understand how experimental variables, especially tunable ones, of hiPSC expansion and differentiation phases affect the hiPSC-CM maturity stage. This study applied clustering algorithms to day 30 cardiac differentiation data to investigate if any maturity-related cell features could be related to the experimental variables. The best models were obtained using k-means and Gaussian mixture model clustering algorithms based on the evaluation metrics. They grouped the cells based on eccentricity and elongation. The cosine similarity between the clustering results and the experimental parameters revealed that the Gaussian mixture model results have strong similarities of 0.88, 0.94, and 0.93 with axial ratio, diameter, and cell concentration. 

Cardiovascular diseases (CVD) are the leading cause of death worldwide. Engineered heart tissue produced by differentiation of human induced pluripotent stem cells may provide an encompassing treatment for heart failure due to CVD. However, considerable difficulties exist in producing the large number of cardiomyocytes needed for therapeutic purposes through differentiation protocols. Data-driven modeling with machine learning techniques has the potential to identify factors that significantly affect the outcomes of these differentiation experiments. Using data from previous cardiac differentiation experiments, we have developed data-driven modeling methods for determining which experimental conditions are most influential on the final cardiomyocyte content of a differentiation experiment. With those identified conditions, we were able to build classification models that can predict whether an experiment will have a sufficient cardiomyocyte content to continue with the experiment on the seventh (out of 10) day of the differentiation with a 90% accuracy. This early failure prediction will provide cost and time savings, as each day the differentiation continues requires significant resources. 

Surrogate models are used to map input data to output data when the actual relationship between the two is unknown or computationally expensive to evaluate. We have constructed a tool to recommend the appropriate surrogate modelling technique for a given dataset using attributes calculated from the input and output values. The tool identifies the appropriate surrogate modeling techniques with an accuracy of 98% and a precision of 91%. 

Uncertainty propagation methods are used to estimate the distribution of model outputs resulting from a set of uncertain model outputs. There are a number of uncertainty propagation methods available in literature. This paper compares six non-intrusive uncertainty propagation methods, Latin Hypercube Sampling, Full Factorial Integration, Univariate Dimension Reduction, Halton series, Sobol series, and Polynomial Chaos Expansion, in terms of their efficiency for estimating the first four moments of the output distribution using computational experiments. The results suggest employing FFNI if there are few uncertain inputs, up to three. Uncertainty propagation methods that utilize Halton and Sobol series are found to be robust for estimating output moments as the number of uncertain inputs increased. In general, higher order polynomial chaos expansion approximations (3rd-5th order) obtained accurate estimates of model outputs with fewer model evaluations.