# Machine learning analysis of ARVC informed by sodium channel protein-based interactome networks

## TL;DR

This study uses machine learning and cardiac organoids to identify Kaempferol as a potential treatment for arrhythmogenic right ventricular cardiomyopathy (ARVC).

## Contribution

A novel approach combining ML modeling with organoid validation to identify ARVC treatment compounds.

## Key findings

- SCN5A is the most significantly affected sodium channel protein in ARVC.
- Kaempferol was predicted to bind to SCN5A with high affinity and showed therapeutic effects in vitro.
- The ML model and experimental validation platform offers broad application for ARVC drug development.

## Abstract

Arrhythmogenic right ventricular cardiomyopathy (ARVC) is an inherited cardiac disorder characterized by sodium channel dysfunction. However, the clinical management of ARVC remains challenging. Identifying novel compounds for the treatment of ARVC is crucial for advancing drug development.

In this study, we aim to identify novel compounds for treating ARVC.

Machine learning (ML) models were constructed using proteins analyzed from the scRNA-seq data of ARVC rats and their corresponding protein-protein interaction (PPI) network to predict binding affinity (BA). To validate these predictions, a series of experiments in cardiac organoids were conducted, including Western blotting, ELISA, MEA, and Masson staining to assess the effects of these compounds.

We first discovered and identified SCN5A as the most significantly affected sodium channel protein in ARVC. ML models predicted that Kaempferol binds to SCN5A with high affinity. In vitro experiments further confirmed that Kaempferol exerted therapeutic effects in ARVC.

This study presents a novel approach for identifying potential compounds to treat ARVC. By integrating ML modeling with organoid validation, our platform provides valuable support in addressing the public health challenges posed by ARVC, with broad application prospects. Kaempferol shows promise as a lead compound for ARVC treatment.

Detection and verification processes for ARVC target proteins are shown. The left panel includes a rat and heart diagram for ARVC, followed by ScRNA-seq data and a PPI network. The right panel describes experiments with cardiac organoids, focusing on cell viability, protein expression, heart failure markers, myocardial fibrosis, and electrophysiologic function. The bottom includes ML model construction, a heatmap for BA prediction, molecular docking, and dynamic simulation.