NEW YORK – Tempus AI on Wednesday said it signed multiyear, strategic collaboration agreements with AstraZeneca and Pathos AI to develop a multimodal foundation model for oncology.

纽约——Tempus AI 周三表示，已与阿斯利康和 Pathos AI 签订了多年的战略合作协议，以开发用于肿瘤学的多模态基础模型。

The firms hope to gain biological and clinical insights, discover novel drug targets, and accelerate development of therapeutics. Researchers will build the model using Tempus' AI-driven platform and repository of de-identified patient data.

这些公司希望获得生物学和临床方面的见解，发现新的药物靶点，并加速治疗方法的开发。研究人员将使用Tempus的AI驱动平台和去标识化的患者数据存储库来构建模型。

Under the terms of the agreement, Chicago-based Tempus will receive $200 million in data licensing and model development fees. All three partners will have access to the model to support their individual programs.

根据协议条款，总部位于芝加哥的Tempus公司将获得2亿美元的数据许可和模型开发费用。所有三位合作伙伴都可以访问该模型，以支持各自的项目。

The new agreement expands an existing partnership between AstraZeneca and Tempus, originally signed in 2021. Under that older agreement, Tempus and AstraZeneca have been collaborating on a prospective clinical study to identify biomarkers of response in

新协议扩大了阿斯利康与Tempus之间自2021年签署的现有合作关系。根据之前的协议，Tempus与阿斯利康一直在合作开展一项前瞻性临床研究，以识别响应生物标志物。

small cell lung cancer (SCLC) patients

小细胞肺癌（SCLC）患者

and a study in non-small cell lung cancer to create a multiomics dataset for discovering biomarkers and developing precision treatments and diagnostics.

并在非小细胞肺癌中进行研究，以创建一个多组学数据集，用于发现生物标志物并开发精准治疗和诊断方法。

'Generative AI and the emergence of large multimodal models is the final catalyst needed to usher in precision medicine in oncology at scale,' Tempus Founder and CEO Eric Lefkofsky said in a statement. 'Tempus has spent the last decade investing billions of dollars into collecting the necessary data needed for a foundation model of this kind to take shape.'.

“生成式人工智能和大型多模态模型的出现是推动肿瘤学领域精准医疗大规模发展的最后一剂催化剂，”Tempus创始人兼首席执行官埃里克·莱夫科夫斯基在一份声明中表示。“过去十年中，Tempus已经投入了数十亿美元来收集构建此类基础模型所需的数据。”

According to Tempus, its data repository is larger than the Cancer Genome Atlas (TCGA), with more than 8 million de-identified patient records. These include 2 million records with imaging data, 1.5 million records with matched clinical data and genomic information, and over 250,000 records with transcriptome profiles..

据 Tempus 称，其数据存储库比癌症基因组图谱（TCGA）更大，包含超过 800 万份去标识化的患者记录。这些记录中包括 200 万份带有影像数据的记录、150 万份匹配了临床数据和基因组信息的记录，以及超过 25 万份带有转录组谱的记录。