In Silico Tools and Web Resources for Cardiotoxicity Screening ​

Shiuli Roy

Co-Presenters: Individual Presentation

College: Hennings College of Science Mathematics and Technology

Major: BS.BIO/CELL/MOLEC

Faculty Research Mentor: Kar, Supratik  

Abstract:

Cardiotoxicity is a frequent cause of late-stage drug attrition and post-market withdrawal, motivating early computational safety screening. This work compiles and explains practical in silico tools and web resources that enable cardiotoxicity prediction, with emphasis on what a scientist can use immediately rather than developing new models. We surveyed peer-reviewed literature from 2015-2025 to identify software platforms, online predictors, and publicly available resources that support cardiotoxicity-relevant endpoints. Although hERG channel blockade remains the most common screening endpoint, many usable tools also address broader liabilities, including multi–ion-channel risk, QT prolongation surrogates, contractility-related signals, mitochondrial/oxidative stress indicators, and integrated cardiotoxicity classification. A structured search was conducted in Scopus and Google Scholar using cardiotoxicity terms (e.g., “cardiotoxicity,” “hERG,” “QT,” “heart failure”) combined with tool- and computation-related terms (e.g., “webserver,” “software,” “QSAR,” “machine learning,” “AI,” “deep learning”). Inclusion criteria were English-language, peer-reviewed sources published between 2015 and 2025 that described an accessible tool or resource with sufficient methodological detail for use; sources primarily intended for marketing or lacking reproducible information were excluded. The retrieved papers were used to curate a toolkit-style list of resources, documenting for each tool the endpoint(s) supported, required inputs, output interpretation, and practical limitations. The resulting compilation provides an actionable, tool-centered roadmap for early cardiotoxicity triage and prioritization. These resources are positioned as a decision-support layer to augment experimental testing and expert review, enabling faster elimination of high-risk candidates and more focused downstream validation.