Phenotypic screening with deep learning identifies HDAC6 inhibitors as cardioprotective in a BAG3 mouse model of dilated cardiomyopathy.

Dilated cardiomyopathy (DCM) is characterized by reduced cardiac output, as well as thinning and enlargement of left ventricular chambers. These characteristics eventually lead to heart failure. Current standards of care do not target the underlying molecular mechanisms associated with genetic forms of heart failure, driving a need to develop novel therapeutics for DCM. To identify candidate therapeutics, we developed an in vitro DCM model using induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) deficient in B-cell lymphoma 2 (BCL2)-associated athanogene 3 (BAG3). With these BAG3-deficient iPSC-CMs, we identified cardioprotective drugs using a phenotypic screen and deep learning. From a library of 5500 bioactive compounds and siRNA validation, we found that inhibiting histone deacetylase 6 (HDAC6) was cardioprotective at the sarcomere level. We translated this finding to a BAG3 cardiomyocyte-knockout (BAG3cKO) mouse model of DCM, showing that inhibiting HDAC6 with two isoform-selective inhibitors (tubastatin A and a novel inhibitor TYA-018) protected heart function. In BAG3cKO and BAG3E455K mice, HDAC6 inhibitors improved left ventricular ejection fraction and reduced left ventricular diameter at diastole and systole. In BAG3cKO mice, TYA-018 protected against sarcomere damage and reduced Nppb expression. Based on integrated transcriptomics and proteomics and mitochondrial function analysis, TYA-018 also enhanced energetics in these mice by increasing expression of targets associated with fatty acid metabolism, protein metabolism, and oxidative phosphorylation. Our results demonstrate the power of combining iPSC-CMs with phenotypic screening and deep learning to accelerate drug discovery, and they support developing novel therapies that address underlying mechanisms associated with heart disease.

Deep learning detects cardiotoxicity in a high-content screen with 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 detect drug-induced toxicity in vitro. 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 with potential cardiotoxic liabilities in iPSC-CMs using a single-parameter score based on deep learning. Compounds demonstrating cardiotoxicity in iPSC-CMs 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 that show cardiotoxic signal in iPSC-CMs. 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 may protect against diseased phenotypes and deleterious mutations.

Colorectal cancer stem cells are enriched in xenogeneic tumors following chemotherapy.

BACKGROUND: Patients generally die of cancer after the failure of current therapies to eliminate residual disease. A subpopulation of tumor cells, termed cancer stem cells (CSC), appears uniquely able to fuel the growth of phenotypically and histologically diverse tumors. It has been proposed, therefore, that failure to effectively treat cancer may in part be due to preferential resistance of these CSC to chemotherapeutic agents. The subpopulation of human colorectal tumor cells with an ESA(+)CD44(+) phenotype are uniquely responsible for tumorigenesis and have the capacity to generate heterogeneous tumors in a xenograft setting (i.e. CoCSC). We hypothesized that if non-tumorigenic cells are more susceptible to chemotherapeutic agents, then residual tumors might be expected to contain a higher frequency of CoCSC. METHODS AND FINDINGS: Xenogeneic tumors initiated with CoCSC were allowed to reach approximately 400 mm(3), at which point mice were randomized and chemotherapeutic regimens involving cyclophosphamide or Irinotecan were initiated. Data from individual tumor phenotypic analysis and serial transplants performed in limiting dilution show that residual tumors are enriched for cells with the CoCSC phenotype and have increased tumorigenic cell frequency. Moreover, the inherent ability of residual CoCSC to generate tumors appears preserved. Aldehyde dehydrogenase 1 gene expression and enzymatic activity are elevated in CoCSC and using an in vitro culture system that maintains CoCSC as demonstrated by serial transplants and lentiviral marking of single cell-derived clones, we further show that ALDH1 enzymatic activity is a major mediator of resistance to cyclophosphamide: a classical chemotherapeutic agent. CONCLUSIONS: CoCSC are enriched in colon tumors following chemotherapy and remain capable of rapidly regenerating tumors from which they originated. By focusing on the biology of CoCSC, major resistance mechanisms to specific chemotherapeutic agents can be attributed to specific genes, thereby suggesting avenues for improving cancer therapy.

Multiclass cancer classification and biomarker discovery using GA-based algorithms.

MOTIVATION: The development of microarray-based high-throughput gene profiling has led to the hope that this technology could provide an efficient and accurate means of diagnosing and classifying tumors, as well as predicting prognoses and effective treatments. However, the large amount of data generated by microarrays requires effective reduction of discriminant gene features into reliable sets of tumor biomarkers for such multiclass tumor discrimination. The availability of reliable sets of biomarkers, especially serum biomarkers, should have a major impact on our understanding and treatment of cancer. RESULTS: We have combined genetic algorithm (GA) and all paired (AP) support vector machine (SVM) methods for multiclass cancer categorization. Predictive features can be automatically determined through iterative GA/SVM, leading to very compact sets of non-redundant cancer-relevant genes with the best classification performance reported to date. Interestingly, these different classifier sets harbor only modest overlapping gene features but have similar levels of accuracy in leave-one-out cross-validations (LOOCV). Further characterization of these optimal tumor discriminant features, including the use of nearest shrunken centroids (NSC), analysis of annotations and literature text mining, reveals previously unappreciated tumor subclasses and a series of genes that could be used as cancer biomarkers. With this approach, we believe that microarray-based multiclass molecular analysis can be an effective tool for cancer biomarker discovery and subsequent molecular cancer diagnosis.

G protein-coupled receptors GPR4 and TDAG8 are oncogenic and overexpressed in human cancers.

The GPR4 subfamily consists of four G protein-coupled receptors that share significant sequence homology. In addition to GPR4, this subfamily includes OGR1, TDAG8 and G2A. G2A has previously been shown to be a potent transforming oncogene for murine 3T3 cells. Here we show that GPR4 also malignantly transforms NIH3T3 cells and that TDAG8 malignantly transforms the normal mammary epithelial cell line NMuMG. Overexpression of GPR4 or TDAG8 in HEK293 cells led to transcriptional activation from SRE- and CRE-driven promoters, independent of exogenously added ligand. TDAG8 and GPR4 are also overexpressed in a range of human cancer tissues. Our results suggest that GPR4 and TDAG8 overexpression in human tumors plays a role in driving or maintaining tumor formation.