Pan-cancer AI atlas reveals diversity and spatial organization of tertiary lymphoid structures in tumors
By
Linghua Wang
Summary
Researchers built a pan-cancer atlas of tertiary lymphoid structures (TLSs) in human tumors, developing an AI-based framework to detect and characterize these immune hubs. The study found that TLSs vary in maturation state, spatial location, cellular composition, and organization. Intratumoral TLSs were associated with spatial gradients in tumor-intrinsic signaling. A scalable AI model was trained to detect and classify TLSs on standard pathology slides, and a composition-based TLS score was developed to assess their functional relevance across cancer types.
Source
Twitter / XPan-cancer AI atlas reveals diversity and spatial organization of tertiary lymphoid structures in tumorsscim.agKey quotes
· 5 pulledTertiary lymphoid structures (TLSs) form local immune hubs inside tumors, but they are diverse and not all are equally functional.
Cho et al. built a pan-cancer atlas and developed an artificial intelligence (AI)–based framework to detect and characterize TLSs in human tumors.
TLSs varied in maturation state, spatial location, cellular composition and organization.
Intratumoral TLSs were associated with spatial gradients in tumor-intrinsic signaling.
A scalable model was trained to detect and classify TLSs on standard pathology slides, and a composition-based TLS score was designed.
You might also wanna read
Integrating multi-layer intratumor heterogeneity analysis to advance cancer immunotherapy
This article examines intratumor heterogeneity (ITH) as a multidimensional problem in cancer biology. It discusses how tumors consist of div
UC San Diego AI Model Predicts Cancer Treatment Response from Tumor Genetics
UC San Diego researchers have developed an AI tool called iAtlas that can predict how a tumor will respond to treatment based solely on its
Gemma-Based AI Model Identifies Potential Cancer Therapy Pathway Through Conditional Immune Amplification
Researchers used a new 27 billion parameter foundation model called C2S-Scale 27B, built on Google's Gemma family of open models, to discove
blog.google·8mo ago
Multi-model transcriptomic atlas reveals shared inflammatory programs and epithelial-immune crosstalk in chronic colitis
This study by Fransson, Sorini, et al. presents a multi-model, longitudinal transcriptomic atlas of experimental chronic colitis, integratin
Reinforcement Learning Environment for LLMs in Cancer Diagnosis from Pathology Slides
A developer from Aluna (YC S24) presents a reinforcement learning environment for large language models focused on cancer diagnosis. The env
news.ycombinator.com·7mo ago
CEDAR platform releases cancer-specific epitope prediction tools and analysis pipelines for immuno-oncology research
The article describes the Cancer Epitope Database and Analysis Resource (CEDAR), a platform developed to address the challenge of accurately
doi.org·6d ago