XevaDB enables AI-driven longitudinal pharmacogenomic modeling in patient-derived xenografts
Patient-derived xenografts (PDXs) are critical models for translational oncology, but their computational use is limited by fragmented pharmacogenomic data, inconsistent response annotations, and poor access to raw longitudinal tumour-volume measurements. Here we present XevaDB (xevadb.ca), a standardized platform designed to support machine learning (ML) and artificial intelligence (AI) applications through the integration of longitudinal treatment and control-arm tumour growth curves with harmonized drug and gene annotations, response metrics, replicate-level experimental design, clinical annotation, and matched molecular profiles. XevaDB provides access to data from 689 PDX models across six tumour types, 69 drugs, 4,828 treatment-control experiments, and matched RNA-seq, copy-number, and mutation data for 337 models. Through four case studies, we show that preserving raw longitudinal response data enables analyses beyond conventional static endpoints: transcriptomic prediction of intrinsic tumour growth, image-based deep learning of drug-response trajectories, replicate-aware transfer learning from cell-line-trained models, and multi-omics prediction of paclitaxel response. These results establish XevaDB as a resource for sharing standardized longitudinal pharmacogenomic data and enabling reproducible AI/ML modeling, demonstrating how integrated PDX data can accelerate computational approaches in preclinical cancer research.
Authors
- Mitchell J. Elliott (ORCID: https://orcid.org/0000-0001-6711-7287)
- Arvind Singh Mer (ORCID: https://orcid.org/0000-0001-8510-7963)
- Jennifer Cruickshank (ORCID: https://orcid.org/0009-0007-4963-3430)
- Jennifer Silvester (ORCID: https://orcid.org/0000-0001-6087-4066)
- Nhu‐An Pham (ORCID: https://orcid.org/0000-0003-3063-0292)
- Samah El Ghamrasni (ORCID: https://orcid.org/0000-0003-4346-1360)
- David W. Cescon (ORCID: https://orcid.org/0000-0002-1080-0998)
- Aaron Dou (ORCID: https://orcid.org/0009-0007-8293-2635)
- Guanqiao Feng (ORCID: https://orcid.org/0000-0001-6118-3267)
- Ming‐Sound Tsao (ORCID: https://orcid.org/0000-0002-9160-5405)
- Chantal Tobin
- Geneviève Deblois (ORCID: https://orcid.org/0000-0002-3067-2807)
- Nikolina Radulovich (ORCID: https://orcid.org/0000-0002-8224-7263)
- Morag Park (ORCID: https://orcid.org/0000-0001-5400-606X)
- Matthew Boccalon
- Benjamin Haibe-Kains
- Meghan Mcguire
- Hellen Kuasne
- Taylor Bird (ORCID: https://orcid.org/0009-0009-3364-9870)
- Michael Tran
- Sisira Kadambat Nair
- Quan Li
Institutions
- University Health Network (CA)
- University of Ottawa (CA)
- University of Toronto (CA)
- Princess Margaret Cancer Centre (CA)
- McGill University (CA)
- Université de Montréal (CA)
Publication Details
- Journal
- Research Square
- Published
- 2026-11-19
- DOI
- https://doi.org/10.21203/rs.3.rs-11356792/v1
- Primary Topic
- Cancer Genomics and Diagnostics
- Type
- preprint