MLN2SVG: domain-aware spatially variable gene detection using contrastive variational autoencoder and multi-level neighbor search

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not specified in abstract

• Primary Outcome: Consistent outperformance in clustering accuracy, robustness, and biological interpretability across multiple datasets

• Nnt Or Sensitivity: Improved detection of fine-grained spatial organization in breast cancer tertiary lymphoid structures

• Confidence Interval: Not reported

Clinical Application

High feasibility as computational tool requiring only spatial transcriptomics data input Highly relevant to Australian cancer research institutes and computational biology groups; could enhance precision medicine initiatives and support TGA-regulated diagnostic development Researchers using spatial transcriptomics for tissue analysis, particularly in cancer and neuroscience research

Abstract

Spatial transcriptomics (ST) technologies have transformed our ability to examine gene expression within intact tissues, yet accurately identifying spatially variable genes (SVGs) remains challenging due to spatial heterogeneity, data sparsity, and incomplete modeling of domain-level dependencies. To address these limitations, we propose MLN2SVG, a domain-aware framework that integrates contrastive variational autoencoding with a multi-level neighbor (MLN) search algorithm to jointly learn tissue domains and SVGs. MLN2SVG constructs a weighted spatial graph to capture both local and long-range spatial relationships, employing a deep contrastive variational autoencoder to align augmented and original data representations while preserving biological diversity. The MLN algorithm dynamically expands neighborhood connectivity to mitigate sparsity and enhance domain coherence. Across multiple human and mouse ST datasets, including dorsolateral prefrontal cortex, breast cancer, and brain tissues, MLN2SVG consistently outperformed existing methods in clustering accuracy, robustness, and biological interpretability. Notably, in breast cancer tissues, MLN2SVG uncovers fine-grained spatial organization of tertiary lymphoid structures, delineating region-specific immune architectures spanning intratumoral, tumor-edge, and extratumoral compartments. Through the integration of spatial domain discovery and SVG detection, MLN2SVG delivers a robust and biologically interpretable framework for uncovering the molecular and structural complexity of tissue organization.

References

1. 1.Hussain, S., Ayoub, M., Ye, F., & Liu, X. (2026). MLN2SVG: domain-aware spatially variable gene detection using contrastive variational autoencoder and multi-level neighbor search. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag210