WILMINGTON, Del.

威尔明顿，特拉华州

and COPENHAGEN, Denmark

和丹麦哥本哈根

,

，

April 9, 2026

2026年4月9日

/PRNewswire/ --

/PRNewswire/ --

DeepCyte

深细胞

, a techbio company building AI toxicology tools for drug development, launched today with $1.5 million in seed funding. The company is introducing two solutions to help biopharma teams detect, predict and explain drug toxicity – in human cells, at single-cell resolution.

一家致力于为药物开发打造人工智能毒理学工具的技术生物公司，今天宣布获得150万美元的种子资金。该公司推出了两款解决方案，帮助生物医药团队在人体细胞中检测、预测和解释药物毒性，且达到单细胞分辨率。

Drug toxicity remains a leading cause of clinical trial failure and drug withdrawal, costing the industry billions annually. Conventional methods – animal models, high-throughput screening and bulk assays – often fail to predict human responses and cannot resolve the heterogeneous cellular effects that drive adverse outcomes.

药物毒性仍然是临床试验失败和药物撤回的主要原因，每年给行业造成数十亿美元的损失。传统方法——动物模型、高通量筛选和批量分析——常常无法预测人类反应，也无法解决导致不良结果的异质性细胞效应。

Regulators including the FDA and EMA are accelerating the shift toward human-relevant, evidence-based, mechanism-aware testing, creating demand for new predictive technologies..

包括FDA和EMA在内的监管机构正在加速转向与人类相关、基于证据、机制明确的测试，从而创造了对新型预测技术的需求。

'DeepCyte's mission is to reveal and prevent toxicity in every cell, at scale, before drugs reach patients,' said Theodore Alexandrov, Ph.D., CEO and co-founder. 'By combining advances in AI and single-cell biology, we predict not only whether a drug is toxic, but also why.'

“DeepCyte的使命是在药物到达患者之前，大规模地揭示并预防每个细胞中的毒性，”Theodore Alexandrov博士，首席执行官兼联合创始人表示。“通过结合人工智能和单细胞生物学的进步，我们不仅可以预测药物是否有毒，还能预测其原因。”

MetaCore is DeepCyte's high-throughput single-cell metabolomics platform built on award-winning laser-based sampling and mass spectrometry technology. MetaCore delivers molecular profiles providing insights on what is happening inside cells and captures the heterogeneous responses that bulk assays obscure.

MetaCore 是 DeepCyte 基于获奖的激光采样和质谱技术开发的高通量单细胞代谢组学平台。MetaCore 提供分子谱，揭示细胞内部发生的情况，并捕获批量分析所掩盖的异质性反应。

Critically, it generates atlas-scale AI-ready datasets with minimal sample preparation and at enabling cost..

关键的是，它能够以最少的样本准备和可接受的成本生成图集规模的AI就绪数据集。

DeeImmuno is DeepCyte's first AI solution using MetaCore data and purpose-built ML to exploit single-cell biology, trained on proprietary single-cell metabolomics atlases. DeeImmuno predicts toxicity class, identifies biomarkers, and infers molecular mechanisms of toxicity. Evaluated on 100 held-out drugs, DeeImmuno predicted 17 detailed toxicity mechanisms with 94% accuracy – a breakthrough result for such mechanistic resolution unachievable with conventional methods..

DeeImmuno 是 DeepCyte 首个利用 MetaCore 数据并专门构建机器学习模型以挖掘单细胞生物学的 AI 解决方案，其训练基于专有的单细胞代谢组图谱。DeeImmuno 能够预测毒性类别、识别生物标志物，并推断毒性的分子机制。在对 100 种保留药物进行评估时，DeeImmuno 以 94% 的准确率预测了 17 种详细的毒性机制——这一突破性成果是传统方法无法达到的机制分辨率。

DeepCyte's leadership combines expertise in pharmacology, AI, and life sciences commercialization. CEO Theodore Alexandrov previously developed METASPACE, a cloud software used by thousands of researchers globally, and co-founded SCiLS GmbH, later acquired by Bruker. The seed round was supported by Carl J.

DeepCyte的领导层融合了药理学、人工智能和生命科学商业化的专业知识。首席执行官Theodore Alexandrov曾开发了METASPACE——一款被全球数千名研究人员使用的云软件，并共同创立了SCiLS GmbH，该公司后来被Bruker收购。种子轮融资得到了Carl J的支持。

G. Evertsz, a medtech executive, former CEO and investor who will serve as Board Chair..

G. Evertsz，一位医疗科技高管、前首席执行官和投资者，将担任董事会主席。

About DeepCyte

关于DeepCyte

DeepCyte is headquartered in Delaware and Copenhagen, with the mission to transform toxicology. DeepCyte combines MetaCore, a category-defining high-throughput single-cell metabolomics platform, with DeeImmuno, an AI toxicology solution enabling biopharma teams to predict toxicity earlier, infer mechanisms, and move beyond animal models and bulk assays toward human-centric drug safety testing..

DeepCyte 总部位于特拉华州和哥本哈根，致力于变革毒理学。DeepCyte 将 MetaCore（一个定义类别的高通量单细胞代谢组学平台）与 DeeImmuno（一种 AI 毒理学解决方案）相结合，使生物制药团队能够更早预测毒性、推断机制，并超越动物模型和批量分析，迈向以人为中心的药物安全性测试。

Media Contact

媒体联系人

Vikki Herrera

维基·赫雷拉

Oak Street Communications

橡树街通讯

[email protected]

电子邮件地址

21

21

%

%

more press release views with

更多新闻发布视图与

Request a Demo

请求演示