{"ID":6497790,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09166","arxiv_id":"2607.09166","title":"COAST: Context-Aware Differential Learning for Gene Expression Prediction in Spatial Transcriptomics","abstract":"Spatial transcriptomics enables profiling of spatial gene expression but is limited by high cost and low throughput, motivating prediction from H\u0026E histopathology images. Existing context-aware methods mainly supervise absolute expression, while relative expression relationships between spots are rarely used explicitly. We propose COAST, a context-aware differential learning framework for spatial gene expression prediction. COAST conditions the local and global context features with type-specific modulation and aggregates the target and context spot tokens using a Transformer encoder to capture both fine-grained local patterns and slide-level structure. It is trained with a joint objective that combines absolute expression regression with signed differential regression between the target and context spots. Experiments on multiple spatial transcriptomics datasets show consistent improvements in correlation- and distribution-based metrics, demonstrating the effectiveness of context-aware differential learning for histology-based spatial gene expression prediction.","short_abstract":"Spatial transcriptomics enables profiling of spatial gene expression but is limited by high cost and low throughput, motivating prediction from H\u0026E histopathology images. Existing context-aware methods mainly supervise absolute expression, while relative expression relationships between spots are rarely used explicitly...","url_abs":"https://arxiv.org/abs/2607.09166","url_pdf":"https://arxiv.org/pdf/2607.09166v1","authors":"[\"Keunho Byeon\",\"Sunhong Park\",\"Jeewoo Lim\",\"Jin Tae Kwak\"]","published":"2026-07-10T07:50:23Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}