FEAOF: A transferable framework applied to prediction of hERG-related cardiotoxicity.

Comput Biol Chem

Department of Pharmacy, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou 450003, China; Henan Province Engineering Research Center for Clinical Application, Evaluation and Transformation of Traditional Chinese Medicine; Henan Provincial Key Laboratory for Clinical Pha

Published: August 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Inhibition of the hERG (human ether-a-go-go-related gene) channel by drug molecules can lead to severe cardiac toxicity, resulting in the withdrawal of many approved drugs from the market or halting their development in later stages. These findings highlight the pressing need to evaluate hERG blockade during drug development. We propose a novel framework for feature extraction and aggregation optimization (FEAOF), which primarily consists of a feature extraction module and an aggregation optimization module. The model integrates diverse ligand representations, including molecular fingerprints, descriptors, and graphs, as well as ligand-receptor interaction features. Based on this integration, we further optimize the algorithmic framework to achieve precise predictions of compounds cardiac toxicity. Two independent test sets exhibiting pronounced structural dissimilarity from the training data were constructed to rigorously assess the model's generalization ability. The results demonstrate that the FEAOF model exhibits strong robustness compared to seven baseline models, achieving F1 score of 66.1 % and 68.1 %. Notably, when benchmarked against five existing models on two external test sets, FEAOF also achieved the highest or near-highest scores across all key evaluation metrics. Importantly, this model can be easily adapted for other drug-target interaction prediction tasks. It is made available as open source under the permissive MIT license at https://github.com/ConfusedAnt/FEAOF.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiolchem.2025.108622DOI Listing

Publication Analysis

Top Keywords

cardiac toxicity
8
feature extraction
8
aggregation optimization
8
test sets
8
feaof
4
feaof transferable
4
transferable framework
4
framework applied
4
applied prediction
4
prediction herg-related
4

Similar Publications

Morning administration of anthracyclines is associated with a lower risk of cancer therapy-related cardiac dysfunction.

Eur Heart J Open

September 2025

Department of Cardiology, Division of Heart and Lungs, University Medical Centre Utrecht, Utrecht University, Heidelberglaan 100, 3584 CX Utrecht, The Netherlands.

Aims: Pre-clinical studies point towards an administration time-dependency of anthracycline-induced cancer therapy-related cardiac dysfunction (CTRCD). This retrospective study aimed to investigate the association between time-of-day of AC administration and CTRCD.

Methods And Results: Patients from two cardio-oncology outpatient clinics, treated with ACs for any malignancy, were included.

View Article and Find Full Text PDF

Technological advances and the desire to reduce dependence on animal models have brought human-relevant models to the forefront of drug development. This paradigm shift is leveraging the advances in systems and new approach methodologies (NAMs), which was the focus of a workshop convened by the Health and Environmental Sciences Institute (HESI) in May 2024. Highlights included discussions on predicting cardiac failure modes and the utility of human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs), microfluidic systems like BioFlux™, and engineered heart tissues in enhancing early-stage drug safety assessments.

View Article and Find Full Text PDF

Heart failure (HF) and lung cancer (LC) often coexist, yet their shared molecular mechanisms are unclear. We analyzed transcriptome data from the NCBI Gene Expression Omnibus (GEO) database (GSE141910, GSE57338) to identify 346 HF‑related differentially expressed genes (DEGs), then combined weighted gene co-expression network analysis (WGCNA) pinpointed 70 hub candidates. Further screening of these 70 hub candidates in TCGA lung cancer cohorts via LASSO, Random Forest, and multivariate Cox regression suggested CYP4B1 as the only independent prognostic marker.

View Article and Find Full Text PDF

Evolving Cardioprotective Strategies in Cardio-Oncology: A Narrative Review.

Curr Cardiol Rep

September 2025

Division of Cardiology, Health Sciences Building, University of Washington Medical Center, 1959 NE Pacific StreetSuite #A506D Box 356422, Seattle, WA, 98195, USA.

Purpose Of Review: Patients living with cancer are at risk for significant potential cardiovascular complications as a direct result of cancer treatment or due to underlying comorbid cardiovascular disease. This article reviews the methods of risk stratification as well as pharmacologic and nonpharmacologic approaches to cardioprotection in cardio-oncology.

Recent Findings: Several cancer-specific risk stratification tools have incorporated variables such as age, sex, cancer subtype, traditional cardiovascular risk factors and cancer treatment-related parameters to assess cardiovascular specific risk prior to cancer therapy.

View Article and Find Full Text PDF

Heart failure (HF) is a complex clinical syndrome marked by impaired contractility, adverse remodeling, and dysregulated intracellular signaling. Protein kinases are central regulators of cardiac function, modulating calcium handling, gene transcription, hypertrophy, and apoptosis through phosphorylation of target proteins. In HF, chronic activation of kinases such as protein kinase A, protein kinase C, calcium/calmodulin-dependent kinase II, mitogen-activated protein kinases, protein kinase B, and Rho-associated protein kinase contributes to progressive cardiac dysfunction.

View Article and Find Full Text PDF