Curriculum vitae

Updated September 2026 · ORCID: 0000-0001-9835-5018

Appointments

2025–present
Associate Research Scientist
Columbia University
Program of Mathematical Genomics, Department of Systems Biology.
2025–present
Irving Cancer Early Scholar
Herbert Irving Comprehensive Cancer Center, Columbia University

Research Funding

2025–2027
Irving Cancer Early Scholar Award
Columbia University
Development of cell-type-specific foundation models for transcription, agentic AI for automated biological discovery, and interpretation of noncoding variants in cancer.

Education

2020–2026
PhD in Biomedical Informatics
Columbia University
Advisor: Raul Rabadan.
Thesis: A foundation model of transcription regulation and application to cancer.
Defense: November 12, 2025; diploma: February 11, 2026.
MPhil (2023) and MA (2022), Biomedical Informatics.
2016–2019
MPhil in Computer Science and Engineering
The Chinese University of Hong Kong
Thesis: Systematic Identification and Prioritization of Noncoding Variants in Hirschsprung’s Disease.
2012–2016
BSc in Cell and Molecular Biology
The Chinese University of Hong Kong

Selected Research Contributions

2022–2024

GET: General Expression Transformer

Initiated the study and brought together collaborators; developed the model and performed regulatory and structural interpretation. GET predicts expression across 213 human cell types and identified a transcription-factor interaction implicated in inherited leukemia risk. Co-first and co-corresponding author, Nature (2025).

2026

p53–ER regulation in breast cancer and chromatin changes in muscle aging

Developed Motiverse for GPU-accelerated motif-spacing analysis. Identified primate-specific Alu-derived p53–ER motif spacing of approximately 73 bp, supporting potential cooperation on the same nucleosome in breast cancer. Identified regulatory elements with age-associated accessibility changes in muscle cell types and tenocytes. Co-first and co-corresponding author; unpublished manuscript (2026).

Chromnitron: protein–DNA interaction modeling

Co-designed the data curation and quality-control pipeline, model architecture, training paradigm, and mechanistic interpretation analyses of the protein encoder. The study identified and experimentally validated regulators of T-cell exhaustion. Co-first author; bioRxiv (2025; revised 2026).

Additional Research Contributions

2021–2023

Structure-informed interpretation of cancer mutations

Used AlphaFold2-based structural modeling, molecular dynamics, and evolutionary features to identify and interpret oncogenic hotspot mutations in tumor suppressors and oncogenes. First author, bioRxiv (2022). Advisor: Raul Rabadan.

2025–present

Eureka: AI-assisted genomic discovery

Developed a platform integrating literature, genetic, regulatory, and structural evidence for variant interpretation and therapeutic target prioritization. Built benchmarks with controls for information leakage to evaluate target prioritization and enrichment for clinical success.

2017–2020

Disease-associated noncoding risk variants

Developed a multiscale framework to prioritize regulatory elements, genes, pathways, and transcription-factor programs from whole-genome sequencing. Applied it to Hirschsprung disease; collaborators experimentally validated candidate mechanisms. The Chinese University of Hong Kong; advisor: Kevin Yip.

2018–2019

Network embedding for gene regulation

Developed and interpreted a semi-supervised framework integrating physical and regulatory interactions in heterogeneous biological networks. The Chinese University of Hong Kong; advisor: Kevin Yip.

2020

Venous thromboembolism GWAS

Performed genome-wide association analyses of susceptibility variants in a Han Chinese population. WeGene, Shenzhen Zaozhidao Company.

Peer-Reviewed Research Articles

Published as Fu, X. and Fu, A. X. *Equal contribution; †corresponding author.

Fu, X.*†, Mo, S.*, Buendia, A.*, et al.
Nature 637, 965–973 (2025)
Su, J., Reynier, J.-B., Fu, X., et al.
Genome Biology 24, 291 (2023)
Hypomorphic and dominant-negative impact of truncated SOX9 dysregulates Hedgehog-Wnt signaling, causing campomelia
Au, T. Y. K., Yip, R. K. H., Wynn, S. L., Tan, T. Y., Fu, A. X., et al.
PNAS 120, e2208623119 (2023)
Genome-wide association analyses identified novel susceptibility loci for pulmonary embolism among Han Chinese population
Zhang, Z., Li, H., …, Fu, X., et al.
BMC Medicine 21, 153 (2023)
A unified framework for integrative study of heterogeneous gene regulatory mechanisms
Cao, Q., Zhang, Z., Fu, A. X., et al.
Nature Machine Intelligence 2, 447–456 (2020)
Identification of genes associated with Hirschsprung disease, based on whole-genome sequence analysis, and potential effects on enteric nervous system development
Tang, C. S.-M., Li, P., Lai, F. P.-L., Fu, A. X., et al.
Gastroenterology 155, 1908–1922.e5 (2018)
Dual roles of an Arabidopsis ESCRT component FREE1 in regulating vacuolar protein transport and autophagic degradation
Gao, C., Zhuang, X., Cui, Y., Fu, X., et al.
PNAS 112, 1886–1891 (2015)

Reviews and Perspectives

Alvarez-Torres, M. d. M., Fu, X., and Rabadan, R.
Cancer Research 85, 2368–2375 (2025)
Fu, X. and Rabadan, R.
The Oncologist 29, 653–657 (2024)

Preprints and Unpublished Manuscripts

Hayward, S. B., Vaitsiankova, A., …, Fu, X., …, and Ciccia, A.
Accepted in principle, Nature Biotechnology. Preprint: bioRxiv (2026)
Tan, J.*, Fu, X.*, Ling, X.*, et al.
bioRxiv (2025; revised January 18, 2026)
Nucleosome-scale p53–hormone receptor grammar links cancer and primate evolution
Fu, X.*†, Cai, Q.*, Satya, P., Rabadan, R.†, and Levine, A. J.†
Unpublished manuscript (2026)

Workshop Contributions

Multi-modal self-supervised pre-training for large-scale genome data
Mo, S., Fu, X., Hong, C., et al.
NeurIPS AI for Science Workshop (2021)

Research Software

  • GET: Released open software for model training, regulatory interpretation, and analysis.
  • Astro (2026–present): Built and launched a browser-based system to coordinate AI research agents across local, cloud, and HPC environments, with reproducible task records.

Invited Talks

Nov 2025 Columbia University: AI at VP&S Workshop - Foundation Models Across Scales
Jul 2025 Google Genomics
Jun 2025 Cancer Convergence Education Network / University of Chicago
Mar 2025 New York University
Feb 2025 Stanford University
Feb 2025 Genentech
Feb 2025 Tsinghua University
Jan 2025 EMBL Heidelberg
Jan 2025 Sanford Burnham Prebys Medical Discovery Institute
Nov 2024 Cancer Convergence Education Network / Spanish National Cancer Research Centre
May 2024 Cancer Convergence Education Network / University of Rome
Dec 2023 Cancer Convergence Education Network / Universitat Politecnica de Catalunya
Oct 2023 Cancer Convergence Education Network / Keio University

Mentoring

  • Mentoring two PhD students on foundation-model training, including extensions of GET.
  • Previously mentored one research assistant; one mentee is now a PhD student at Stanford University.

Teaching

  • Guest lecturer, Introduction to Computational Biomedicine and Health (BINF 4001 / COMS 4560), Columbia University: “Single Cell Foundation Models” (2025); invited to return with “Introduction to Biological Foundation Models” (2026, upcoming).
  • Teaching assistant for a full term of Introduction to Database Systems (undergraduate), The Chinese University of Hong Kong. Responsible for weekly computational labs and grading.
  • Tutored biological and medical collaborators in AI and machine learning, including pretraining and fine-tuning biological foundation models.

Professional Service

  • Reviewer for Nature (2026).
  • Ad hoc / co-reviewer for Science (2025).
  • Reviewer for MLCB (2023, 2024); SPIGM workshop at ICML (2026); AI4Science workshop at ICML (2024); NeurIPS workshops.

Grant Proposal Contributions

Contributed to writing R01, ARPA-H, Evans Foundation, and DoD Idea grant proposals.

Honors & Awards

2021
Champion, DeeCamp Artificial Intelligence Bootcamp
Sinovation Ventures
2017
Certificate of Merit Award for Teaching Assistant
The Chinese University of Hong Kong

Technical Skills

PyTorch Hydra PyTorch Lightning Hugging Face scikit-learn statsmodels seaborn tidyverse ggplot2 Nextflow Bash Linux