Elliot Xie
@elliotxie.bsky.social
Biomedical Data Science Phd Student @ UW - Madison
Happy to share that our paper CASSIA has been officially published in Nature Communications!
Huge thanks to my PI Christina for her guidance and support, and to all my amazing group members for their contributions throughout this project.
Read the paper here: www.nature.com/articles/s41...
Huge thanks to my PI Christina for her guidance and support, and to all my amazing group members for their contributions throughout this project.
Read the paper here: www.nature.com/articles/s41...
CASSIA: a multi-agent large language model for automated and interpretable cell annotation - Nature Communications
Assigning cell types in single-cell RNA-seq is essential yet challenging, as it requires expertise, time, and is often subjective. Here, the authors present CASSIA, a multi-agent AI system that provid...
www.nature.com
December 24, 2025 at 11:36 AM
Happy to share that our paper CASSIA has been officially published in Nature Communications!
Huge thanks to my PI Christina for her guidance and support, and to all my amazing group members for their contributions throughout this project.
Read the paper here: www.nature.com/articles/s41...
Huge thanks to my PI Christina for her guidance and support, and to all my amazing group members for their contributions throughout this project.
Read the paper here: www.nature.com/articles/s41...
New SOTA LLM models are being released at a staggering pace. But how well do they really perform in single-cell annotation?
To answer this, our team built a real-time benchmark for evaluating state-of-the-art LLMs in single-cell annotation analysis using the CASSIA framework.
To answer this, our team built a real-time benchmark for evaluating state-of-the-art LLMs in single-cell annotation analysis using the CASSIA framework.
May 5, 2025 at 8:19 PM
New SOTA LLM models are being released at a staggering pace. But how well do they really perform in single-cell annotation?
To answer this, our team built a real-time benchmark for evaluating state-of-the-art LLMs in single-cell annotation analysis using the CASSIA framework.
To answer this, our team built a real-time benchmark for evaluating state-of-the-art LLMs in single-cell annotation analysis using the CASSIA framework.
🚀 Meet CASSIA: A Multi-Agent LLM for Single-Cell 🚀
Introducing CASSIA, our multi-agent LLM for scRNA-seq. It’s interpretable and boosts annotation accuracy by up to 41%, even for rare species (e.g., shark, pangolin). Perfect for immune or cancer subtypes!
Introducing CASSIA, our multi-agent LLM for scRNA-seq. It’s interpretable and boosts annotation accuracy by up to 41%, even for rare species (e.g., shark, pangolin). Perfect for immune or cancer subtypes!
February 19, 2025 at 8:33 PM
🚀 Meet CASSIA: A Multi-Agent LLM for Single-Cell 🚀
Introducing CASSIA, our multi-agent LLM for scRNA-seq. It’s interpretable and boosts annotation accuracy by up to 41%, even for rare species (e.g., shark, pangolin). Perfect for immune or cancer subtypes!
Introducing CASSIA, our multi-agent LLM for scRNA-seq. It’s interpretable and boosts annotation accuracy by up to 41%, even for rare species (e.g., shark, pangolin). Perfect for immune or cancer subtypes!