Olga Troyanskaya

Professor

Princeton University
Country flagUnited States

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (16)

Year:

2026

Understanding how perturbations influence gene function in a tissue-specific manner is key to uncovering novel drug targets. However, current computational approaches emphasize global network or sequence-derived features over context-driven dependencies. We introduce Mahi, a scalable and interpretable graph neural network framework that learns gene representations by integrating chromatin accessibility, transcription factor binding, histone modifications, and protein structure features in tissue-specific contexts. Through pretraining on tissue-specific network topologies followed by multi-modal feature integration, Mahi learns context-aware gene embeddings across 290 tissues and cell-types. Mahi outperforms sequence-based models in predicting gene essentiality across 1,183 cancer cell lines, demonstrating the advantage of integrating molecular context and functional connectivity. The learned embedding space reveals tissue-specific functional organization, with genes forming distinct clusters reflecting their context-dependent roles. In silico gene knockout perturbations demonstrate Mahi’s ability to model intricate perturbation responses, identifying disease-relevant pathways and therapeutic targets. Together, these results demonstrate Mahi as a foundation for modeling tissue-specific gene function and perturbation responses, enabling applications in precision medicine, therapeutic target discovery, and prediction of context-dependent genetic vulnerabilities. All embeddings and the framework are publicly available to facilitate use by the scientific community.

Year:

2026

New approaches that generate long-lasting therapeutic responses in patients with therapy-resistant metastatic cancer are urgently needed. To address this challenge, we developed Spot Neoantigens in Metastases (SpotNeoMet), a novel data-driven pipeline that systematically identifies recurrently presented neopeptides in treatment-resistant patients. We identified seven therapy resistance mutations predicted to produce neopeptides presented by common HLAs. Using HLA immunopeptidomics, we discovered three novel neopeptides derived from androgen receptor (AR) H875Y, a common metastatic castration-resistant prostate cancer (mCRPC) mutation. We validated these neoantigens as highly immunogenic and then isolated and characterized cognate T-cell receptors (TCR) from healthy donor peripheral blood mononuclear cells. We demonstrated that AR H875Y–specific TCRs are highly specific and kill prostate cancer cells presenting AR neopeptides in vitro and in vivo . Our new pipeline identifies novel immunotherapy targets and potential treatment options for patients with mCRPC. Moreover, SpotNeoMet offers a systematic route to identify “HLA–peptide” pairs and their cognate TCRs across treatment-resistant cancers. Significance: As the emergence of resistance to targeted treatments in patients with metastatic cancer, there is an urgent need for innovative therapeutic approaches for this population. Our study provides a new analytic framework to identify neoantigens from treatment-resistant mutations and a proof-of-concept T cell–based immunotherapy treatment for mCRPC.

Year:

2026

Integrating coding and regulatory variation into unified, interpretable representations remains a challenge in functional genomics. Current approaches either focus on common variants or analyze individual variants in isolation, missing the cumulative, cell-type-specific impact of both coding and noncoding variants on each gene. We present Volaria, a computational framework that integrates coding and regulatory genetic variation into unified, gene-centered representations for disease outcome prediction from whole-genome sequencing. Volaria leverages deep learning models to capture variant effects on cell-type-specific gene expression and integrates them with AI-predicted exonic variant pathogenicity to produce representations that capture the cumulative effect of genome-wide rare and common variation. Applied to whole genomes of individuals with rare glomerular diseases, Volaria predicts individual outcomes directly from germline sequence, demonstrating that structured, cell-type-aware representations capture predictive signals beyond population-based polygenic risk scores and unstructured representations. Importantly, the framework identifies context-specific biological mechanisms, providing interpretability that can be aligned with clinical measurements. By encoding genome-wide variation into compact and biologically grounded representations, Volaria provides a scalable foundation for genome interpretation and individualized outcome modeling from germline sequence, complementing phenotypic and clinical information in the future integrative frameworks.

Year:

2026

Unraveling the phenotypic and genetic complexity of autism is extremely challenging yet critical for understanding the biology, inheritance, trajectory and clinical manifestations of the many forms of the condition. Using a generative mixture modeling approach, we leverage broad phenotypic data from a large cohort with matched genetics to identify robust, clinically relevant classes of autism and their patterns of core, associated and co-occurring traits, which we further validate and replicate in an independent cohort. We demonstrate that phenotypic and clinical outcomes correspond to genetic and molecular programs of common, de novo and inherited variation and further characterize distinct pathways disrupted by the sets of mutations in each class. Remarkably, we discover that class-specific differences in the developmental timing of affected genes align with clinical outcome differences. These analyses demonstrate the phenotypic complexity of children with autism, identify genetic programs underlying their heterogeneity, and suggest specific biological dysregulation patterns and mechanistic hypotheses.

Year:

2025

The growing availability of biological data resources has transformed research, yet their effective use remains challenging: selecting appropriate sources requires domain knowledge, data are fragmented across databases, and synthesizing results into reliable conclusions is labor-intensive. Although large language models promise to address these barriers, their impact in biomedicine has been limited by unsupported statements, incorrect claims, and lack of provenance. We introduce Alvessa, an evidence-grounded agentic research assistant designed around verifiability. Alvessa integrates entity recognition, orchestration of pre-validated biological tools, and data-constrained answer generation with statement-level verification against retrieved records, explicitly flagging unsupported claims and guiding revision when reliability criteria are not met. We evaluate Alvessa on dbQA from LAB-Bench and GenomeArena, a benchmark of 720 questions spanning gene and variant annotation, pathways, molecular interactions, miRNA targets, drug-target evidence, protein structure, and gene-phenotype associations. Alvessa substantially improves accuracy relative to general-purpose language models and performs comparably to coding-centric agents while producing fully traceable outputs. Using adversarial perturbations, we show that detection of fabricated statements depends critically on access to retrieved evidence. We further demonstrate application to drug discovery, where evidence-grounded synthesis enables identification of candidate targets missed or misattributed by literature-centered reasoning alone. Alvessa and GenomeArena are released to the community to support reproducible, verifiable AI-assisted biological research.

Year:

2025

In eukaryotes, most genes produce multiple transcript isoforms that diversify the transcriptome and proteome, serving as a key mechanism of functional regulation. Genetic variation can disrupt the RNA processing signals that shape isoform structure and abundance, yet modeling these effects at full-length isoform resolution remains challenging due to the complexity of transcript regulation. Here, we introduce Otari, an attention-based graph neural network framework trained on the human genomic sequence and long-read transcriptomes across 30 tissue types and brain regions. Otari predicts tissue-specific differential isoform abundance by integrating sequence-derived epigenetic and post-transcriptional signals, enabling isoform-resolved variant effect interpretation. Applied to large-scale variant datasets including an autism cohort, Otari uncovers patterns of isoform dysregulation undetectable at the gene level, such as variant-driven perturbations in isoform abundance and microexon usage implicated in autism pathophysiology. We provide Otari as a resource for powering isoform-level analyses across tissues at scale.

Year:

2025

Year:

2024

Year:

2024

Major depressive disorder (MDD) is a common mood condition affecting multiple brain regions and cell types. Changes in astrocyte function contribute to depressive-like behaviors. However, while neuronal mechanisms driving MDD have been studied in some detail, molecular mechanisms by which astrocytes promote depression have not been extensively explored. To uncover astrocyte contributions to MDD, we subjected male mice to chronic social defeat stress precipitated by encounters with a dominant male. Animals exposed to this treatment exhibit symptoms indicative of MDD, including reduced social interactions, anxiety, despair, and anhedonia. We then measured astrocyte translating mRNA expression changes in mice that underwent chronic social defeat and control animals using ribosome affinity purification. Bioinformatic analyses reveal significant alterations in the prefrontal cortex (PFC), consistent with previous studies implicating this brain region in MDD. Expression of genes encoding extracellular matrix (ECM) proteins, cell-cell interaction proteins, and proteins controlling glutamatergic synaptic function are significantly altered. These changes correlate with perturbation of glutamatergic transmission, measured by electrophysiology, and increased synaptic cleft size. Among ECM genes, increased expression of mRNA encoding the synaptic remodeling protein s ecreted p rotein a cidic and r ich in c ysteine ( Sparc ) correlates the most with the depressive phenotype. Furthermore, presence of SPARC and other ECM proteins in synaptosomes is also increased and overexpressing Sparc in PFC partially alleviates stress symptoms. Our results raise the possibility that increased expression of Sparc may be a natural protective mechanism against stress-induced synaptic dysfunction in depression.

Year:

2024

Year:

2024

Year:

2024

Year:

2023

Year:

2023

Year:

2023

Year:

2023

Collaborators (25)

Roni Oren

Head of Patient Derived Xenograft (PDX) Service and Human Tissue Samples Bank

Weizmann Institute of Science

ISRAEL
View details

Lyonna F Parise

Assistant Professor

Florida Atlantic University

UNITED STATES
View details

Francisco Martínez-Jiménez

Group Leader

Vall d'Hebron Institute of Oncology

SPAIN
View details

David A. Quigley

Assistant Professor

University of California, San Francisco

UNITED STATES
View details

Eliezer Van Allen

Professor

Harvard University

UNITED STATES
View details

Ran Zhang

Assistant Professor

University of North Carolina at Chapel Hill

UNITED STATES
View details

Alexander W. Wyatt

Assistant Professor

The University of British Columbia

CANADA
View details

Irene Ramos

Assistant Professor

Icahn School of Medicine at Mount Sinai

UNITED STATES
View details

Zijun Zhang

Asssistant Professor

Cedars-Sinai Medical Center

UNITED STATES
View details

Shifra Ben-Dor

Senior Staff Scientist

Weizmann Institute of Science

ISRAEL
View details

Ilan Dinstein

Empire Innovation Professor

University at Buffalo

UNITED STATES
View details

Radhika Iyer

Life Science Research Professional

Stanford University School of Medicine

UNITED STATES
View details

Niroshana Anandasabapathy

Associate Professor of Dermatology

Weill Cornell Medical College

UNITED STATES
View details

Abel Gonzalez-Perez

Co-PI

IRB Barcelona

SPAIN
View details

Guillermo Sapiro

Augustine Family Professor in Electrical and Computer Engineering

Princeton University

UNITED STATES
View details

Joaquin Mateo

Group Leader

Vall d´Hebron Institute of Oncology

SPAIN
View details

Matthias Kretzler

Research Professor

University of Michigan

UNITED STATES
View details

Jean-Pierre Roussarie

-

UNITED STATES
View details

Yishai Levin

Lab head

Weizmann Institute of Science

ISRAEL
View details

Kenny Chan

Assistant Professor

NYU School of Medicine

UNITED STATES
View details

Venugopalan Nair

Professor

Icahn School of Medicine at Mount Sinai

UNITED STATES
View details

Nuria Lopez-Bigas

ICREA Research Professor-Group Leader

Universitat Pompeu Fabra

SPAIN
View details

Caroline Menard

Associate Professor

Laval University

CANADA
View details

Austin D. Swafford

-

UNITED STATES
View details

Patricia Rodriguez-Rodriguez

Karolinska Institutet

SWEDEN
View details