2. Academic Validation
  3. Deep Learning-Powered Scalable Cancer Organ Chip for Cancer Precision Medicine

Deep Learning-Powered Scalable Cancer Organ Chip for Cancer Precision Medicine

  • Adv Sci (Weinh). 2026 May;13(26):e16660. doi: 10.1002/advs.202516660.
Yu-Chieh Yuan 1,  Beibei Xu 2,  Jenna McCormack 1,  XuHai Huang 1,  Jingzhe Ma 1,  Thomas Marshall 1,  Yacong Sun 2,  Hardeep Singh 1,  Alyssa Fanelli 1,  Gauri Kulkarni 1,  Ji Hye Seo 1,  Paige Gilbride 1,  Bing Wei 3 4,  Bo Wang 3 4,  Yanyan Liu 5,  Fei Ma 6,  Lin Zhou 1 7,  Shuyang Wang 8,  Xiaohua Qian 1 7,  Zhiyong Xie 1 7,  Polina Golland 9,  Longlong Si 2 10,  Yu Shrike Zhang 11,  Xin Xie 1 4 7,  Haiqing Bai 1 7
Affiliations

Affiliations

  • 1 Xellar Biosystems, Boston, Massachusetts, USA.
  • 2 CAS Key Laboratory of Quantitative Engineering Biology, Shenzhen Institute of Synthetic Biology, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
  • 3 Department of Molecular Pathology, Henan Cancer Hospital, Zhengzhou, Henan, China.
  • 4 Henan Key Laboratory of Molecular Pathology, Zhengzhou, Henan, China.
  • 5 Department of Internal Medicine, Henan Cancer Hospital, Zhengzhou, Henan, China.
  • 6 Department of General Surgery, Henan Cancer Hospital, Zhengzhou, Henan, China.
  • 7 Henan Academy of Innovations in Medical Science, Zhengzhou, Henan, China.
  • 8 Department of Pathology, School of Basic Medical Sciences, Fudan University, Shanghai, China.
  • 9 Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
  • 10 University of Chinese Academy of Sciences, Beijing, China.
  • 11 Division of Engineering in Medicine, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Cambridge, Massachusetts, USA.
PMID: 41632021 DOI: 10.1002/advs.202516660
Abstract

Functional precision oncology complements genomic approaches by directly testing treatment options on patient-derived models. However, existing platformssuch as patient-derived xenografts (PDXs) and patient-derived organoids (PDOs), face major barriers in clinical use due to technical challenges, including limited standardization, high costs, long assay times, scalability constraints, and incomplete recapitulation of the patient tumor microenvironment (TME). Here, we present a scalable, low-cost Organ Chip (OC) platform fabricated entirely from thermoplastics via injection molding. Leveraging a patented channel geometry and surface treatment, the device achieves barrier-free hydrogel confinement through capillary pinning without porous membranes, micropillars, or Other barrier structures. This automation-compatible platform supports tissue-specific extracellular matrices and co-culture through versatile perfusion modes, with robust imaging compatibility. We demonstrate its feasibility for drug sensitivity testing using multiple cell lines and patient-derived primary cells, with imaging-based phenotypic profiling for accurate quantification of drug responses, closely aligning with clinical outcomes. Additionally, we integrated a deep learning-based image translation model that predicts fluorescence staining from bright-field images. This approach enables longitudinal, label-free phenotypic analysis with higher sensitivity than conventional endpoint staining. Together, this integrated Cancer OC system overcomes key technical challenges and offers a promising framework for functional precision oncology through high-throughput, patient-relevant drug testing.

Keywords

drug screening; in silico staining; organ chip; precision medicine.

Figures
Products