PulseAugur
EN
LIVE 14:48:10

New AI models integrate spatial omics data for biological insights

Researchers have developed HEIST, a hierarchical graph transformer model designed to analyze spatial transcriptomics and proteomics data. This model represents tissues as hierarchical graphs, capturing both spatial cell relationships and internal gene expression networks. Pretrained on a massive dataset of cells from various organs, HEIST demonstrates generalization to new data types and achieves state-of-the-art performance in tasks like clinical outcome prediction and cell type annotation. Another study introduces STAMP, a framework that uses spatial transcriptomics to guide pathology foundation models, enhancing their ability to infer molecular profiles from histology images by aligning transcriptomic data into functional pathways. AI

IMPACT These models advance AI's capability in biological research, enabling deeper understanding of cellular processes and disease prediction from complex omics data.

RANK_REASON The cluster contains two academic papers describing novel AI models and frameworks for biological data analysis.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Hiren Madhu, Jo\~ao Felipe Rocha, Tinglin Huang, Siddharth Viswanath, Smita Krishnaswamy, Rex Ying ·

    HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data

    arXiv:2506.11152v4 Announce Type: replace-cross Abstract: Single-cell transcriptomics and proteomics have become a great source for data-driven insights into biology, enabling the use of advanced deep learning methods to understand cellular heterogeneity and gene expression at th…

  2. arXiv cs.LG TIER_1 English(EN) · Fengtao Zhou, Yingxue Xu, Zhengyu Zhang, Yihui Wang, Zhengrui Guo, Ling Liang, Jiabo Ma, Cheng Jin, Ziyi Liu, Huajun Zhou, Hongyi Wang, Du Cai, Chenglong Zhao, Xi Wang, Can Yang, Yu Wang, Wenbin Li, Feng Gao, Zhe Wang, Zhenhui Li, Xiuming Zhang, Li Liang… ·

    Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model

    arXiv:2606.03644v1 Announce Type: new Abstract: Comprehensive molecular profiling is essential for modern precision oncology but remains hindered by prohibitive costs, specimen exhaustion, and protracted turnaround times. While pathology foundation models (PFMs) have demonstrated…