AI RESEARCH

Annotation-Informed Block-Sparse Bayesian Modeling for cis-Expression Prediction

arXiv CS.LG

ArXi:2606.00483v1 Announce Type: cross Genotype-based cis-expression prediction depends on accurately modeling local regulatory architecture. We present block-sparse Bayesian sparse linear mixed model (bsBSLMM), an extension of Bayesian sparse linear mixed model (BSLMM) that incorporates linkage disequilibrium (LD)-block spike-and-slab sparsity and a transcription start site (TSS)-informed SNP inclusion prior.