Determining the ototoxic potential of COVID-19 therapeutics using machine learning and in vivo approaches

项目摘要/摘要 目前有900多种药物和药物组合正在进行新冠肺炎的临床试验。虽然这一速度 药物开发是必要的，它也伴随着产生具有显著副作用的疗法的风险增加- 效果。一些新冠肺炎药物的一个可能的副作用是听力损失。药物对听力的潜在影响 在药物开发或临床测试期间，损失通常是未经评估的。我们的研究将迅速评估 新冠肺炎药物的潜在耳毒性，按照NOT-DC-20-008中的《潜在耳毒性》进行测定 与新冠肺炎相关的治疗学或疫苗接种。我们的目标是推动平安新冠肺炎的发展 副作用最小的药物。新冠肺炎的一些临床试验药物与听力损失有关，但 这些药物的耳毒性潜力是基于个别病例报告或体外实验，因此真实的 耳毒性负担在很大程度上是未知的。我们不应该把病人作为改变生活的消极方面的试验床- 当有快速、低成本的替代方案可供选择时，就会产生效果。这项提议的目标是迅速确定 新冠肺炎疗法在硅胶和活体两种方法中的耳毒性潜力。我们将实现 这个目标有三个具体的目的：1)用机器预测新冠肺炎疗法的耳毒性 学习(ML)，2)确定新冠肺炎疗法在斑马鱼侧线的相对毛细胞毒性， 以及3)确定预测的耳毒素导致大鼠听力损失的程度。我们创新的ML模式 正确地将耳毒素和非耳毒素分类，准确率为87%。在这个项目中，我们将利用我们目前的 模型用于即时耳毒性检测，并进一步优化模型以获得更好的预测准确性。在……里面 与ML模型平行，我们将在斑马鱼幼体侧线筛选新冠肺炎疗法，这是一种 快速耳毒性筛查的极佳模型。我们小组和其他人之前的工作证明了 侧线作为有效发现耳毒素的平台。最后，我们将验证预测的耳毒素来自 AIMS 1和AIMS 2在大鼠的生理和形态分析中的应用。我们的研究意义重大，因为 我们将确定新的或重新调整用途的疗法对新冠肺炎的耳毒性潜力，这可以为 努力1)推出无耳毒性的有效候选者，2)修改成功但耳毒性的新冠肺炎 药物和/或开发耳保护性共疗法，以保持治疗效果，同时最大限度地减少耳毒性副作用- 效果，以及3)确定哪些患者因他们接受的药物而需要听力监测。我们的 团队包括耳毒性、药物化学、生物统计学、机器学习和临床专业知识方面的专家 在新冠肺炎疗法的大规模人体试验中。我们的研究极有可能发现耳毒性新冠肺炎 药物，促进开发更安全的药物疗法来抗击这一致命的流行病。此外，还有许多 新冠肺炎临床试验中的药物已经被批准用于其他适应症。因此，我们的研究将 提供有关非冠状病毒相关疾病的临床用药的重要数据，增加额外价值。

Project Summary/Abstract There are over 900 drugs and drug combinations currently in clinical trials for COVID-19. While this pace of drug development is necessary, it also comes with increased risk of producing therapies with significant side- effects. One likely side-effect of some COVID-19 drugs is hearing loss. The potential of drugs to cause hearing loss is typically unassessed during drug development or clinical testing. Our research will rapidly assess COVID-19 drugs for ototoxic potential, as per NOT-DC-20-008 to determine the “Potential ototoxicity from therapeutics or vaccination related to COVID-19.” Our goal is to promote the development of safe COVID-19 drugs with minimal side effects. Some drugs in clinical trials for COVID-19 are associated with hearing loss but the ototoxic potential for these drugs is based on individual case reports or in vitro experiments so the true ototoxic burden is largely unknown. We should not use patients as a testbed for a life-altering negative side- effect when there are rapid low-cost alternatives available. The objective of this proposal is to rapidly identify the ototoxic potential of COVID-19 therapeutics using both in silico and in vivo approaches. We will achieve this objective with three Specific Aims: 1) Predict ototoxic potential of COVID-19 therapies with Machine Learning (ML), 2) Determine the relative hair cell toxicity of COVID-19 therapies in the zebrafish lateral line, and 3) Determine the degree to which predicted ototoxins cause hearing loss in rats. Our innovative ML model correctly categorizes ototoxins vs. non-ototoxins with 87% accuracy. In this project we will employ our current model for immediate ototoxicity detection and further optimize the model for better predictive accuracy. In parallel with the ML model, we will screen COVID-19 therapeutics in the larval zebrafish lateral line, which is an excellent model for rapid ototoxicity screening. Prior work by our group and others demonstrates the validity of the lateral line as a platform for effective ototoxin discovery. Finally, we will validate predicted ototoxins from Aims 1 and 2 in rats using both physiological and morphological assays. Our research is significant because we will determine the ototoxic potential of new or repurposed therapeutics for COVID-19, which can inform efforts to 1) advance effective candidates that are not ototoxic, 2) modify successful yet ototoxic COVID-19 drugs and/or develop otoprotective co-therapies to preserve therapeutic efficacy while minimizing ototoxic side- effects, and 3) determine which patients require audiometric monitoring due to the drugs they receive. Our team includes experts in ototoxicity, medicinal chemistry, biostatistics, machine learning, and clinical expertise in large-scale human trials for COVID-19 therapies. Our research is highly likely to identify ototoxic COVID-19 drugs, facilitating development of safer pharmacotherapies to combat this deadly pandemic. Further, many drugs in clinical trials for COVID-19 are already approved for other indications. Our research will therefore provide important data about drugs in clinical use for non-COVID-related disease, adding additional value.