7-UP: Generating in silico CODEX from a small set of immunofluorescence markers

Eric Wu; Alexandro E Trevino; Zhenqin Wu; Kyle Swanson; Honesty J Kim; H Blaize D'Angio; Ryan Preska; Aaron E Chiou; Gregory W Charville; Piero Dalerba; Umamaheswar Duvvuri; Alexander D Colevas; Jelena Levi; Nikita Bedi; Serena Chang; John Sunwoo; Ann Marie Egloff; Ravindra Uppaluri; Aaron T Mayer; James Zou

doi:10.1093/pnasnexus/pgad171

7-UP: Generating in silico CODEX from a small set of immunofluorescence markers

PNAS Nexus. 2023 May 19;2(6):pgad171. doi: 10.1093/pnasnexus/pgad171. eCollection 2023 Jun.

Authors

Eric Wu^{1

2}, Alexandro E Trevino¹, Zhenqin Wu^{1

3}, Kyle Swanson⁴, Honesty J Kim¹, H Blaize D'Angio¹, Ryan Preska¹, Aaron E Chiou¹, Gregory W Charville⁵, Piero Dalerba⁶, Umamaheswar Duvvuri⁷, Alexander D Colevas⁸, Jelena Levi⁸, Nikita Bedi⁹, Serena Chang⁹, John Sunwoo⁹, Ann Marie Egloff¹⁰, Ravindra Uppaluri¹⁰, Aaron T Mayer¹, James Zou^{1

2

4

11}

Affiliations

¹ Enable Medicine, Menlo Park, CA 94025, USA.
² Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USA.
³ Department of Chemistry, Stanford University, Stanford, CA 94305, USA.
⁴ Department of Computer Science, Stanford University, Stanford, CA 94305, USA.
⁵ Department of Pathology, Stanford University, Stanford, CA 94305, USA.
⁶ Department of Pathology and Cell Biology, Columbia University, New York, NY 10027, USA.
⁷ Department of Otolaryngology, University of Pittsburgh, Pittsburgh, PA 15213, USA.
⁸ CellSight Technologies, San Francisco, CA 94107, USA.
⁹ Department of Otolaryngology-Head and Neck Surgery, Stanford University, Stanford, CA 94305, USA.
¹⁰ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA 02215, USA.
¹¹ Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA.

Abstract

Multiplex immunofluorescence (mIF) assays multiple protein biomarkers on a single tissue section. Recently, high-plex CODEX (co-detection by indexing) systems enable simultaneous imaging of 40+ protein biomarkers, unlocking more detailed molecular phenotyping, leading to richer insights into cellular interactions and disease. However, high-plex data can be slower and more costly to collect, limiting its applications, especially in clinical settings. We propose a machine learning framework, 7-UP, that can computationally generate in silico 40-plex CODEX at single-cell resolution from a standard 7-plex mIF panel by leveraging cellular morphology. We demonstrate the usefulness of the imputed biomarkers in accurately classifying cell types and predicting patient survival outcomes. Furthermore, 7-UP's imputations generalize well across samples from different clinical sites and cancer types. 7-UP opens the possibility of in silico CODEX, making insights from high-plex mIF more widely available.