DiSTILL: A Hybrid Cloud-HPC Workflow System for Reproducible Spatial Transcriptomics Analysis
摘要
Spatial transcriptomics workflows increasingly combine large annotated data objects, notebook-based analyses, and resource-intensive statistical models that must be executed on high-performance computing (HPC) systems. In practice, these workflows are often difficult to reproduce because configuration, validation, stage execution, and artifact handling are fragmented across scripts and manually edited notebooks. We present (Disease Diagnosis from Spatial Transcriptomics via Interpretable Latent Learning), a hybrid cloudHPC workflow system for reproducible spatial transcriptomics (ST) analysis. DiSTILL combines an application programming interface (API) backend built with , a web frontend, a dataset and preset registry, and a Python pipeline generator that materializes run-specific execution bundles and submission scripts. The system supports local, Secure Shell (SSH)-mediated, and pull-based poller execution modes, enabling HPC submission in environments where persistent API-initiated automation is restricted. We describe the system through the lens of an inflammatory bowel disease (IBD) ST workflow that operationalizes the analytical pipeline of Tan into an auditable application layer. Accordingly, the contribution of this paper is a workflow systems contribution centered on reproducible execution, queue-based orchestration, configuration semantics, and deployment across a split cloudHPC architecture. The broader application goal of DiSTILL is to support user-supplied datasets that satisfy the schema assumptions of the wrapped analytical pipeline.
引用
@article{arxiv.2606.30693,
title = {DiSTILL: A Hybrid Cloud-HPC Workflow System for Reproducible Spatial Transcriptomics Analysis},
author = {Myles Joshua Toledo Tan and Vasco Gerardo Hinostroza Fuentes and Nikhil Yerra and Maria Kapetanaki and Parisa Rashidi and Kejun Huang and Panayiotis V. Benos},
journal= {arXiv preprint arXiv:2606.30693},
year = {2026}
}
备注
10 pages, 7 figures, 8 tables, submitted to and accepted for presentation at the 2026 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) in Athens, Greece