Tahoe-100M
PulseAugur coverage of Tahoe-100M — every cluster mentioning Tahoe-100M across labs, papers, and developer communities, ranked by signal.
-
LLM-Guided Retrieval improves molecular perturbation prediction
Researchers have developed a novel method called LLM-Guided Retrieval (LGR) to predict molecular responses to drug perturbations, a crucial step in drug discovery. LGR utilizes a large language model to identify and ran…
-
GeneSpeak-FP model retrieves drug targets from cell responses
Researchers have developed GeneSpeak-FP, a Transformer-based retrieval model designed to identify potential drug targets and compounds from cell-level transcriptional responses. The model analyzes perturbation signature…
-
New Classifier Discrimination Score (CDS) improves single-cell perturbation evaluation
Researchers have introduced a new metric called the Classifier Discrimination Score (CDS) to better evaluate single-cell perturbation data, particularly when classes overlap significantly. Traditional per-cell accuracy …
-
New data loader scDataset accelerates deep learning on large single-cell omics datasets
Researchers have developed scDataset, a PyTorch data loader designed to efficiently handle large-scale single-cell omics datasets for deep learning. This tool addresses the challenge of loading massive datasets that exc…