PulseAugur / Brief
EN
LIVE 14:32:03

Brief

last 24h
[2/2] 222 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. RESEARCH · arXiv cs.AI English(EN) · · [2 sources]

    GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics

    Researchers have developed GC-MoE, a novel method for estimating gene expression in individual cells from histopathological images. This approach utilizes a Mixture-of-Experts model guided by genomics to predict cell-type probabilities and gene expression, aiming to reduce the need for expensive single-cell measurements. The system incorporates cell-type-specific predictors and attention modules to capture gene programs and neighboring cell context, showing improved results over existing methods. AI

    IMPACT This method could significantly reduce the cost and complexity of spatial transcriptomics research by enabling gene expression prediction from standard histology images.

  2. TOOL · Hugging Face Daily Papers English(EN) ·

    What Makes a Representation Good for Single-Cell Perturbation Prediction?

    Researchers have developed PerturbedVAE, a new framework to improve single-cell perturbation prediction by addressing the imbalance between perturbation-invariant and perturbation-specific gene expression signals. Existing methods often fail to effectively capture the sparse, perturbation-specific information, leading to inaccurate predictions. PerturbedVAE explicitly separates these signals to recover causal representations, achieving state-of-the-art performance on benchmarks and improving out-of-distribution predictions. AI

    IMPACT Improves predictive accuracy in biological research by better isolating key genetic signals.