Predicting cell properties with AI from 3D imaging flow cytometer data.

Journal: Scientific reports
PMID: 39962067

Abstract

Predicting the properties of tissues or organisms from the genomics data is widely accepted by the medical community. Here we ask a question: can we predict the properties of each individual cell? Single-cell genomics does not work because the RNA sequencing process destroys the cell, not allowing us to verify our predictions. To test the hypothesis, we investigate the approach of using AI to analyze single-cell images obtained from a 3D imaging flow cytometer. We analyze the cell image at day zero and make the AI-assisted cell property prediction. The prediction is then examined later when the cells continue to live and develop. Our preliminary results are promising, showing 88% accuracy in predicting cells that will have a high protein expression level. The technique can have strong ramifications and impact on preventive medicine, drug development, cell therapy, and fundamental biomedical research.

Authors

  • Zunming Zhang
    Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, 92093, USA.
  • Yuxuan Zhu
    Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, 92093, USA.
  • Zhaoyu Lai
    Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, 92093, USA.
  • Minhong Zhou
    Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, 92093, USA.
  • Xinyu Chen
    State Key Laboratory of ASIC and System, School of Microelectronics, Fudan University, Shanghai 200433, China.
  • Rui Tang
    State Key Laboratory of Earth Surface Processes and Resource Ecology, College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, China.
  • William Alaynick
    NanoCellect Biomedical Inc., San Diego, CA, 92121, USA.
  • Sung Hwan Cho
    Department of Anesthesiology and Pain Medicine, Soonchunhyang University Bucheon Hospital, Soonchunhyang University College of Medicine, Bucheon, Republic of Korea.
  • Yu-Hwa Lo
    Department of Electrical and Computer Engineering, University of California, San Diego, California.

Keywords

External Resources

Popular Topics
Recent Journals