Ranjbarvaziri, S. | bioRxiv Science

bioRxiv2021

Deep Learning Predicts Patterns of Cardiotoxicity in a High-Content Screen Using Induced Pluripotent Stem Cell-Derived Cardiomyocytes

Drug-induced cardiotoxicity and hepatotoxicity are major causes of drug attrition. To decrease late-stage drug attrition, pharmaceutical and biotechnology industries need to establish biologically relevant models that use phenotypic screening to predict drug-induced toxicity. In this study, we sought to rapidly detect patterns of cardiotoxicity using high-content image analysis with deep learning and induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs). We screened a library of 1280 bioactive compounds and identified those predicted to have cardiotoxic liabilities using a single-parameter score based on deep learning. Compounds with major predicted cardiotoxicity included DNA intercalators, ion channel blockers, epidermal growth factor receptor, cyclin-dependent kinase, and multi-kinase inhibitors. We also screened a diverse library of molecules with unknown targets and identified chemical frameworks with predicted cardiotoxic liabilities. By using this screening approach during target discovery and lead optimization, we can de-risk early-stage drug discovery. We show that the broad applicability of combining deep learning with iPSC technology is an effective way to interrogate cellular phenotypes and identify drugs that protect against diseased phenotypes and deleterious mutations. GRAPHICAL ABSTRACT O_FIG O_LINKSMALLFIG WIDTH=161 HEIGHT=200 SRC="FIGDIR/small/436666v1_ufig1.gif" ALT="Figure 1"> View larger version (42K): org.highwire.dtl.DTLVardef@695707org.highwire.dtl.DTLVardef@1d0980forg.highwire.dtl.DTLVardef@1af30e7org.highwire.dtl.DTLVardef@b3a312_HPS_FORMAT_FIGEXP M_FIG C_FIG CONTRIBUTION TO THE FIELDIn this article, Grafton and colleagues use induced pluripotent stem cell technology and deep learning to train a neural network capable of detecting patterns of cardiotoxicity. To identify bioactive and chemical classes that lead to cardiotoxicity, they combine the neural network with high-content screening of 2560 compounds. The methods described in this study can be used to de-risk early-stage drug development, triage hits, and identify drugs that protect against disease. This screening paradigm will serve as a useful resource for drug discovery and phenotypic interrogation of stem cells and stem cell-derived cell types.

cell biology↗

bioRxiv2020

Hypertrophic cardiomyopathy β-cardiac myosin mutation (P710R) leads to hypercontractility by disrupting super-relaxed state: multiscale measurements and computational modeling

Hypertrophic cardiomyopathy (HCM) is the most common inherited form of heart disease, associated with over 1000 mutations, many in {beta}-cardiac myosin (MYH7). Molecular studies of myosin with different HCM mutations have revealed a diversity of effects on ATPase and load-sensitive rate of detachment from actin. It has been difficult to predict how such diverse molecular effects combine to influence forces at the cellular level and further influence cellular phenotypes. This study focused on the P710R mutation that dramatically decreased in vitro motility velocity and actin-activated ATPase, in contrast to other MYH7 mutations. Optical trap measurements of single myosin molecules revealed that this mutation reduced the step size of the myosin motor and the load sensitivity of the actin detachment rate. Conversely, this mutation destabilized the super-relaxed state in longer, two-headed myosin constructs, freeing more heads to generate force. Micropatterned hiPSC-cardiomyocytes CRISPR-edited with the P710R mutation produced significantly increased force (measured by traction force microscopy) compared with isogenic control cells. The P710R mutation also caused cardiomyocyte hypertrophy and cytoskeletal remodeling as measured by immunostaining and electron microscopy. Cellular hypertrophy was prevented in the P710R cells by inhibition of ERK or Akt. Finally, we used a computational model that integrated the measured molecular changes to predict the measured traction forces. These results confirm a key role for regulation of the super-relaxed state in driving hypercontractility in HCM with the P710R mutation and demonstrate the value of a multiscale approach in revealing key mechanisms of disease. Significance StatementHeart disease is the leading cause of death worldwide, and hypertrophic cardiomyopathy (HCM) is the most common inherited form of heart disease, affecting over 1 in 200 people. Mutations in myosin, the motor protein responsible for contraction of the heart, are a common cause of HCM but have diverse effects on the biomechanics of the myosin protein. We demonstrate that complex biomechanical effects of mutations associated with heart disease can be effectively studied and understood using a multi-scale experimental and computational modeling approach. This work confirmed an important role for disruption of the super-relaxed state for one particular HCM mutation, and our approach can be extended to aid in the development of new targeted therapies for patients with different mutations.

biophysics↗