Rose Orenbuch
Ph.D. · Systems Biology, Harvard Medical School
Education
Ph.D., Systems Biology
Harvard Medical School · Boston, MA
“Building better models for human disease genetics” · Advisor: Prof. Debora S. Marks
B.A., Information Science
Columbia University · New York, NY
Summa Cum Laude · Jonathan L. Gross Award for Academic Excellence
Research Experience
Postdoctoral Fellow
Department of Systems Biology, Harvard Medical School · Advisor: Prof. Debora S. Marks
- Developing multi-modal generative AI frameworks to integrate germline genetics with longitudinal clinical records for dynamic cancer risk prediction.
- Building unified sequence-to-function foundation models that calibrate coding and non-coding variant effects on a single scale.
- Implementing causal inference strategies to distinguish upstream disease drivers from prodromal symptoms in large-scale biobanks (UK Biobank, All of Us).
Ph.D. Candidate
Marks Lab, Harvard Medical School · Advisor: Prof. Debora S. Marks
- Generative Modeling: Conceptualized and developed popEVE, a deep generative model integrating evolutionary constraints with human population data. Demonstrated unsupervised learning outperforms supervised methods for rare disease causal variants (Nature Genetics, 2025).
- Clinical Discovery: Applied popEVE to a meta-cohort of severe developmental disorders, identifying 123 novel candidate disease genes, with 25 subsequently validated by independent groups.
- Benchmarking: Led the clinical benchmarking arm of ProteinGym, the field-standard suite for evaluating protein fitness predictors (NeurIPS, 2023).
- Community: Co-authored best-practice guidelines for the release and validation of variant effect predictors (Genome Biology, 2025).
Undergraduate Researcher
Rabadan Lab, Columbia University · Advisors: Prof. Raul Rabadan & Prof. Itsik Pe’er
- Algorithm Development: Developed arcasHLA, a high-resolution tool for inferring HLA genotypes from RNA-seq data (Bioinformatics, 2019).
- Cancer Immunogenomics: Applied arcasHLA to TCGA to characterize HLA allele-specific expression loss, identifying a widespread mechanism of immune escape in tumors (Genome Medicine, 2023).
Publications
Peer-Reviewed
Orenbuch, R., Shearer, C., Kollasch, A., et al. (2025). Proteome-wide model for human disease genetics. Nature Genetics. doi:10.1038/s41588-025-02400-1
Livesey, B.J., [including Orenbuch, R.] (2025). Guidelines for releasing a variant effect predictor. Genome Biology, 26, 97.
Dias, M., Orenbuch, R., Marks, D.S., Frazer, J. (2024). Toward trustable use of machine learning models of variant effects in the clinic. The American Journal of Human Genetics, 111(12):2589–2593.
Filip, I.*, Wang, A.*, Kravtes, O.*, Orenbuch, R.*, et al. (2023). Pervasiveness of HLA allele-specific expression loss across tumor types. Genome Medicine, 15, 8. (*Co-first author)
Orenbuch, R., Filip, I., Comito, D., et al. (2020). arcasHLA: high resolution HLA typing from RNA seq. Bioinformatics, 36(1):33–40.
Zhao, J., Chen, A., [including Orenbuch, R.] (2019). Immune and genomic correlates of response to anti-PD-1 immunotherapy in glioblastoma. Nature Medicine, 25, 462–469.
Conference Proceedings
M.C. Angelo*, R. Orenbuch*, D.S. Marks (2025). RNA thermodynamics can be replaced with learnable representations. MLSB at NeurIPS, San Diego, CA.
Notin, P., [including Orenbuch, R.] (2023). ProteinGym: Large-scale benchmarks for protein fitness prediction and design. NeurIPS, 36.
Preprints & Working Papers
Orenbuch, R.*, Khan, A.*, Sander, C., Marks, D.S. Integrating longitudinal clinical trajectories with germline evolutionary risk for dynamic cancer prediction. Manuscript in preparation.
Shearer, C., Orenbuch, R., et al. (2024). A Genomic Language Model for Zero-Shot Prediction of Promoter Variant Effects. bioRxiv.
Software & Resources
popEVE
Deep generative model for proteome-wide variant effect prediction
ProteinGym
Comprehensive benchmark for protein fitness prediction and design
arcasHLA
High-resolution HLA typing from RNA-seq
Honors & Awards
Invited Speaker, Machine Learning in Systems Biology (MLSB)2025
Best Paper Award, GenBioAI2025
Best Paper Award Finalist, ISMB (ProteinGym)2023
NSF Graduate Research Fellowship (GRFP), Honorable Mention2021
Summa Cum Laude, Columbia University2019
Jonathan L. Gross Award for Academic Excellence, Columbia University2019
Teaching & Mentoring
Research Mentor
Marks Lab, Harvard Medical School
- Directed research projects for two Master’s students focused on clinical data integration, EHR analysis, and benchmarking of variant interpretation tools.
- Co-supervised three junior Ph.D. students on generative model development, data pipelines, and manuscript preparation.
Instructor
Harvard University
- Designed and delivered a two-week intensive curriculum on Scientific Figure Design and Illustration.
STEM Tutor
St. Joseph’s University, New York
- General Biology, General Chemistry, and Precalculus for undergraduate students.
Technical Skills
Computational
Bioinformatics
Statistical
Design