Annotation-Informed Block-Sparse Bayesian Modeling for cis-Expression Prediction
Researchers have developed a new Bayesian modeling technique called bsBSLMM to improve the prediction of gene expression based on genetic data. This method incorporates linkage disequilibrium (LD) block structure and a prior informed by transcription start sites to enhance accuracy. In tests across multiple datasets, bsBSLMM outperformed existing models in predicting gene expression and identifying relevant regulatory regions and disease-associated genes. AI