Work

SpatialPEFT: a parameter-efficient fine-tuning framework for spatial transcriptomics foundation models

Year: 2026

Type: article

Abstract: SUMMARY: SpatialPEFT is a unified parameter-efficient fine-tuning framework that enables the robust adaptation of large spatial transcriptomics foundation models (up to 1.4 billion parameters) on a single 16 GB consumer-grade GPU. By integrating Low-Rank Adaptation (LoRA), gradient checkpointing, and a spatial-aware adapter, it reduces peak VRAM by over 87% while substantially improving downstream spatial annotation accuracy. AVAILABILITY AND IMPLEMENTATION: SpatialPEFT is implemented in Python and released under the MIT license. The source code, documentation, and tutorials are freely available at https://github.com/applerplay/SpatialPEFT, with an archival snapshot deposited at Zenodo (DOI: 10.5281/zenodo.20725321).

Source: Bioinformatics

DOI: 10.1093/bioinformatics/btag503

Authors: Xin Zou, Xiujuan Lei

Institutions: Ningxia Normal University, Shaanxi Normal University

Language: English

Topic: Single-cell and spatial transcriptomics

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: gold

Estimated APC paid: $3,989

Funder: National Natural Science Foundation of China