scGPT
PulseAugur coverage of scGPT — every cluster mentioning scGPT across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New PT-RAG model enhances gene perturbation response prediction
Researchers have developed PT-RAG, a novel retrieval-augmented generation module designed to improve the prediction of cellular responses to gene perturbations. This system enhances existing deep learning models by inco…
-
New interpretability method distinguishes model representation from input data
A new research paper proposes a method to better evaluate the interpretability of AI models by introducing the concepts of 'floor' and 'ceiling' reference points for probe scores. This approach aims to distinguish betwe…
-
New AI framework ELISA enhances single-cell genomics discovery
Researchers have developed ELISA, a novel interpretable framework designed to bridge the gap between single-cell RNA sequencing data and biological discovery. This hybrid generative AI agent unifies expression embedding…
-
Xaira Therapeutics unveils X-Cell model for AI-driven drug discovery
Xaira Therapeutics, led by Chief Discovery Officer Ci Chu and Chief AI Scientist Bo Wang, has developed the X-Cell model for drug discovery. This model is trained on X-Atlas, a novel dataset generated through CRISPR-bas…
-
AI framework FLAG predicts spatial gene expression from histology images
Researchers from the Shanghai Institute for Advanced Study, Shanghai Jiao Tong University, and Fudan University have developed FLAG, a novel framework for predicting spatial gene expression from histology images. This m…
-
AI models advance cell dynamics prediction with novel architectures
Researchers are developing new AI models to predict cellular dynamics and responses to perturbations. One approach, Chreode, uses a cell world model for one-step temporal predictions and has shown improvements in gene-s…