Integration of deep learning-based histopathology and transcriptomics reveals key genes associated with fibrogenesis in patients with advanced NASH

Conway, Jake R.; Pouryahya, Maryam; Gindin, Yevgeniy; Pan, David Z.; Carrasco-Zevallos, Oscar; Mountain, Vicki; Subramanian, G. Mani; Montalto, Michael; Resnick, Murray B.; Beck, Andrew H.; Huss, Ryan; Myers, Robert P.; Taylor-Weiner, Amaro; Wapinski, Ilan; Chung, Chuhan

doi:10.1016/j.xcrm.2023.101016

Cited by 9 publications

(4 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, the data here show that in mice with mostly human hepatocytes, GalNAc-siTAZ blocks fibrotic NASH progression. One mechanism for the GalNAc-siTAZ-induced decreases in fibrosis, inflammation, and liver injury suggested by our previous studies is lowering of the HSC activator IHH (5), and new data here suggest that suppression of the hepatocyte Notch pathway by GalNAc-siTAZ in NASH may be another human-relevant mechanism (20,21). Previous work has shown that hepatocyte Notch signaling contributes to NASH fibrosis by promoting Ephb2 expression (24), as knockdown of Ephb2 in hepatocytes ameliorated inflammation and fibrosis in a mouse model of NASH.…”

Section: Discussionsupporting

confidence: 56%

“…While the reduction in IHH by GalNAc-siTAZ is a likely mechanism for the decrease in liver fibrosis in GalNAc-siTAZ-treated hu-liver NASH mice (5), we considered another possible mechanism. Both pre-clinical and human data suggest an important role for hepatocyte Notch activation in NASH fibrosis (20,21), and work in other settings has shown that YAP/TAZ can induce NOTCH and its ligands (22). We therefore examined the livers for NOTCH1 and HES1, a gene marker of Notch activation.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Hepatocyte-Targeted siTAZ Therapy Lowers Liver Fibrosis in NASH Diet-Fed Chimeric Mice with Hepatocyte-Humanized Livers

Wang,

Moore,

Shi

et al. 2023

Preprint

View full text Add to dashboard Cite

Nonalcoholic steatohepatitis (NASH) is emerging as the most common cause of liver disease. Although many studies in mouse NASH models have suggested therapies, translation to humans is poor, with no approved drugs for NASH. One explanation may lie in inherent differences between mouse and human hepatocytes. We used NASH diet-fed chimeric mice reconstituted with human hepatocytes (hu-liver mice) to test a mechanism-based hepatocyte-targeted siRNA, GalNAc-siTaz, shown previously to block the progression to fibrotic NASH in mice. Mice were reconstituted with human hepatocytes following ablation of endogenous hepatocytes, resulting in ~95% human hepatocyte reconstitution. The mice were then fed a high-fat choline-deficient Lamino acid-defined diet for 6 weeks to induce NASH, followed by six weekly injections of GalNAc-siTAZ to silence hepatocyte-TAZ or control GalNAc-siRNA (GalNAc-control) while still on the NASH diet. The results revealed that GalNAc-siTAZ lowered human hepatic TAZ and IHH, the major TAZ target that promotes liver fibrosis in NASH. Most importantly, GalNAc-siTAZ decreased liver inflammation, hepatocellular injury, hepatic fibrosis, and profibrogenic mediator expression, and profibroticNOTCHvs. GalNAc-control, indicating that GalNAc-siTAZ decreased the progression of NASH in mice reconstituted with human hepatocytes. In conclusion, silencing TAZ in human hepatocytes suppresses liver fibrosis in a hu-liver model of NASH.Impact and ImplicationsNo drugs have yet been approved for NASH, which is a leading cause of liver disease worldwide. The findings here provide support for this therapeutic strategy of using hepatocyte-targeted siTAZ to decrease NASH progression. More generally, the study illustrates how hu-liver NASH mice can be used to evaluate therapeutic hepatocyte-targeted siRNAs to help prioritize future testing in human NASH.

show abstract

Section: Discussionsupporting

confidence: 56%

Section: Resultsmentioning

confidence: 99%

Hepatocyte-Targeted siTAZ Therapy Lowers Liver Fibrosis in NASH Diet-Fed Chimeric Mice with Hepatocyte-Humanized Livers

Wang,

Moore,

Shi

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Conway et al . [33] utilized ML on clinical trial data (STELLAR 3 and 4) to establish a prognostic five-gene signature predicting progression to cirrhosis and liver-related events in MASH patients, correlating with histological features. Deep learning (DL) was also investigated, outperforming other algorithms with an AUROC >0.80 in identifying genes associated with MASL to MASH progression [34] .…”

Section: Big Data Classes and Their Utility In Masld Researchmentioning

confidence: 99%

A data-driven approach to decode metabolic dysfunction-associated steatotic liver disease

Jimenez Ramos,

Kendall,

Drozdov

et al. 2024

Annals of Hepatology

View full text Add to dashboard Cite

“…DenseNet [3]- [5], Visual Geometry Group Network (VGGNet) [6], GoogleNet [7], and AlexNet [8]. Deep learning is also widely used for several medical datasets such as Magnetic Resonance Imaging (MRI) in [9]- [12], Histopathology in [13]- [18], Computerized Tomography (CT), and Radiology [19]- [22]. In this work, a simple but effective design of CNN architecture was carried out to identify the CT images of COVID-19 patients.…”

Section: Introductionmentioning

confidence: 99%

SCOV-CNN: A Simple CNN Architecture for COVID-19 Identification Based on the CT Images

Haryanto,

Suhartanto,

Murni

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Since the coronavirus was first discovered in Wuhan, it has widely spread and was finally declared a global pandemic by the WHO. Image processing plays an essential role in examining the lungs of affected patients. Computed Tomography (CT) and X-ray images have been popularly used to examine the lungs of COVID-19 patients. This research aims to design a simple Convolution Neural Network (CNN) architecture called SCOV-CNN for the classification of the virus based on CT images and implementation on the web-based application. The data used in this work were CT images of 120 patients from hospitals in Brazil. SCOV-CNN was inspired by the LeNet architecture, but it has a deeper convolution and pooling layer structure. Combining seven and five kernel sizes for convolution and padding schemes can preserve the feature information from the images. Furthermore, it has three fully connected (FC) layers with a dropout of 0.3 on each. In addition, the model was evaluated using the sensitivity, specificity, precision, F1 score, and ROC curve values. The results showed that the architecture we proposed was comparable to some prominent deep learning techniques in terms of accuracy (0.96), precision (0.98), and F1 score (0.95). The best model was integrated into a website-based system to help and facilitate the users' activities. We use Python Flask Pam tools as a web server on the server side and JavaScript for the User Interface (UI) Design

show abstract

Integration of deep learning-based histopathology and transcriptomics reveals key genes associated with fibrogenesis in patients with advanced NASH

Cited by 9 publications

References 54 publications

Hepatocyte-Targeted siTAZ Therapy Lowers Liver Fibrosis in NASH Diet-Fed Chimeric Mice with Hepatocyte-Humanized Livers

Hepatocyte-Targeted siTAZ Therapy Lowers Liver Fibrosis in NASH Diet-Fed Chimeric Mice with Hepatocyte-Humanized Livers

A data-driven approach to decode metabolic dysfunction-associated steatotic liver disease

SCOV-CNN: A Simple CNN Architecture for COVID-19 Identification Based on the CT Images

Contact Info

Product

Resources

About