Adaptive Weighting Contrastive Learning for Spatial Domain Identification in Spatial Transcriptomics

Le résumé fourni par la source

The rapid advancement of spatial transcriptomics has enabled the joint analysis of gene expression and spatial location data. This integration opens new avenues for uncovering tissue heterogeneity. Existing methods attempt to combine spatial and expression information to identify spatial domains. However, they often treat all information sources equally and do not account for their varying impact on results. To address this challenge, we propose AWCST, an adaptive weighted contrastive learning framework for spatial domain identification. AWCST first extracts spatial and expression latent representations and then fuses them using a multi-head attention mechanism. It measures the distributional differences between each view and the fused feature using Maximum Mean Discrepancy. These differences are converted into adaptive weights for the contrastive loss, enhancing the influence of high-quality information sources. Finally, we evaluate AWCST on two independent datasets to demonstrate its effectiveness.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.