Herrman, Joerg

Abstract Anthracycline-induced cardiotoxicity (AIC) remains a dose-limiting complication of cancer treatment, often leading to irreversible heart failure, yet effective cardioprotective therapies remain limited. Graph-driven drug repurposing offers a rapid pathway to identify cardioprotective therapies, but different computational models often generate divergent candidate lists that exceed experimental validation capacity. We applied a novel "Union-then-Filter" framework to prioritize therapeutics for AIC using AI-based approaches and evaluated candidates in zebrafish models. Three state-of-the-art graph learning models (TxGNN, CompGCN, and RLR) were trained on the PrimeKG to generate an initial candidate pool. A Large Language Model (LLM) agent automated evidence synthesis across 4,286 PubMed abstracts for the top 50 drugs from each model. Candidates were stratified using dual decision criteria and filtered against existing clinical trials. The pipeline narrowed 150 initial candidates to four novel candidates: Cysteine, Dasatinib, Tranilast, and Tretinoin. Prospective in vivo validation was subsequently conducted using an adult AIC (aAIC) zebrafish model. Phenotypic screening via echocardiography revealed that Cysteine, Tranilast, and Tretinoin significantly restored ejection fraction (EF) (overall one-way ANOVA: \(\:F\left(\text{4,95}\right)=47.66,\:\:p<0.0001\); Tukey's post hoc: \(\:\:\:p<0.01\) for all three treatments vs. DOX+ control) and normalized cardiac remodeling markers in doxorubicin-treated subjects (Kruskal-Wallis: \(\:{\chi\:}^{2}\left(4\right)=17.21,\:\:p=0.0018\); Dunn’s post hoc: \(\:\:\:p<0.01\) for all three comparisons vs. DOX control). This study demonstrates the translational utility of an LLM-integrated AI pipeline for drug repurposing and highlights zebrafish AIC as an efficient bridge between in silico prediction and in vivo phenotypic validation in cardio-oncology.

Hypertension increases oxidative stress, which can impair myocardial microvascular function and integrity. However, it is yet unclear whether long-term antioxidant intervention in early hypertension would preserve myocardial perfusion and vascular permeability responses to challenge. Pigs were studied after 12 weeks of renovascular hypertension without (n=8) or with daily supplementation of antioxidants (100 IU/kg vitamin E and 1 g vitamin C, n=6), and compared with normal controls (n=7). Myocardial perfusion and microvascular permeability were measured in vivo by electron beam computed tomography before and after 2 cardiac challenges (intravenous adenosine and dobutamine). Basal left ventricular muscle mass was also obtained. Mean arterial pressure was significantly increased in both groups of hypertensive animals (without and with antioxidants, 123±9 and 126±4 mm Hg, respectively, versus normal, 101±4 mm Hg; both P <0.05), but muscle mass was not different among the groups. The impaired myocardial perfusion response to adenosine observed in hypertensives (normal, +51±14%; P <0.05 versus baseline; hypertension, +14±15%; P =0.3 versus baseline) was preserved in hypertensive pigs that received antioxidants (+44±15%; P =0.01 compared with baseline). Long-term antioxidant intervention also preserved subendocardial microvascular permeability responses in hypertension. On the other hand, antioxidant intervention had little effect on the hypertension-induced myocardial vascular dysfunction observed in response to dobutamine. This study demonstrates that the impaired myocardial perfusion and permeability responses to increased cardiac demand in early hypertension are significantly improved by long-term antioxidant intervention. These results support the involvement of oxidative stress in myocardial vascular dysfunction in hypertension and suggest a role for antioxidant strategies to preserve the myocardial microvasculature.