{"scope":{"layer":"general","tissue_scope":"unknown","species":"unknown","system":"unknown","evidence_level":"peer_reviewed","importance":"","importance_reason":""},"id":"VC0149","type":"paper","title":"stFormer integrates spatial ligand signaling into a foundation model for spatial transcriptomics","authors_or_org":"Cao S, Yang K, Cheng J, Li J, Shen H-B, Pan X, Yuan Y.","date":"2026-09-30","year":"2026","venue":"Cell Reports Methods","url":"https://doi.org/10.1016/j.crmeth.2026.101612","doi":"10.1016/j.crmeth.2026.101612","pmid":"42815472","brain_tumor_focus":"no","tags":["spatial-transcriptomics","foundation-model","ligand-receptor","in-silico-perturbation"],"tag_slugs":["foundation-model","in-silico-perturbation"],"tag_labels":["Foundation model","In-silico perturbation"],"tag_labels_zh":["基础模型","计算机模拟扰动"],"unmapped_tags":["spatial-transcriptomics","ligand-receptor"],"one_line_summary_en":"Cao et al. (Cell Reports Methods 2026): stFormer, a transformer for spatial transcriptomics that adds spatial ligand genes via cross-attention; pretrained on ~4.1 million spatial samples from public human Visium data; the abstract reports gains over scFoundation on clustering, batch correction, cell-type and gene-function prediction, and in silico perturbation of ligand-receptor signalling, plus two case studies.","one_line_summary_zh":"Cao 等（Cell Reports Methods 2026）：stFormer 是面向空间转录组的 Transformer，通过交叉注意力引入空间配体基因；在约 410 万个公开人类 Visium 空间样本上预训练；摘要报告其在聚类、批次校正、细胞类型与基因功能预测上优于 scFoundation，并可对配体-受体信号进行 in silico 扰动，另有两个案例研究。","verified":"yes","verification_source":"Crossref (title, 7 authors, 2026-09, article 101612) + Europe PMC (PMID 42815472, first publication 2026-09-30, abstract); Technology Networks 2026-10-13 (CAS press story) used only as lead; full text not read","page_url":"https://gliostate.com/library/VC0149/","api_url":"https://gliostate.com/api/items/VC0149.json","sameAs":["https://doi.org/10.1016/j.crmeth.2026.101612","https://pubmed.ncbi.nlm.nih.gov/42815472/"],"is_preprint":false,"facets":{"type":"https://gliostate.com/library/type/paper/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/foundation-model/","https://gliostate.com/library/tag/in-silico-perturbation/"]},"cited_by":[],"related":[{"id":"VC0009","title":"Transfer learning enables predictions in network biology.","shared_tags":["foundation-model","in-silico-perturbation"],"page_url":"https://gliostate.com/library/VC0009/","api_url":"https://gliostate.com/api/items/VC0009.json"},{"id":"VC0038","title":"ISP 3 Platform powered by Geneformer: Framework for Cross-Species, Sequential, and Multi-Gene In Silico Perturbation Screens with Application to iPS Cell State Transitions","shared_tags":["in-silico-perturbation"],"page_url":"https://gliostate.com/library/VC0038/","api_url":"https://gliostate.com/api/items/VC0038.json"},{"id":"VC0010","title":"Discovery of candidate therapeutic targets with Geneformer.","shared_tags":["in-silico-perturbation"],"page_url":"https://gliostate.com/library/VC0010/","api_url":"https://gliostate.com/api/items/VC0010.json"},{"id":"VC0072","title":"A method for in silico exploration of potential glioblastoma multiforme attractors using single-cell RNA sequencing.","shared_tags":["in-silico-perturbation"],"page_url":"https://gliostate.com/library/VC0072/","api_url":"https://gliostate.com/api/items/VC0072.json"},{"id":"VC0136","title":"AetherCell: A generative engine for virtual cell perturbation and in vivo drug discovery","shared_tags":["foundation-model"],"page_url":"https://gliostate.com/library/VC0136/","api_url":"https://gliostate.com/api/items/VC0136.json"},{"id":"VC0098","title":"Foundation Model Based on Routine Magnetic Resonance Imaging for Brain Tumor Molecular Profiling and Progression Prediction.","shared_tags":["foundation-model"],"page_url":"https://gliostate.com/library/VC0098/","api_url":"https://gliostate.com/api/items/VC0098.json"}]}