Sager J. Gosai

This study functionally characterizes 221,412 trait-associated variants using MPRA in 5 cell types, identifying 12,025 regulatory variants and revealing widespread epistasis and non-TF mechanisms.

GAME provides a standardized framework for benchmarking genomics models across tasks, enabling consistent evaluation and community contributions.

This study introduces MPAC, a machine learning model that predicts the cis-regulatory impact of non-coding variants, demonstrating its accuracy across diverse applications and datasets.

This paper designs synthetic cis-regulatory elements (CREs) that outperform natural ones in driving cell type-specific gene expression using deep learning and experimental validation.

The paper reports 109 non-coding CRISPR screens analyzing 13.3Mb of the genome, identifies CRE-gene links, and provides guidelines and tools for screening non-coding regulatory elements.

HCR-FlowFISH identifies cis-regulatory elements and their target genes by quantifying gene expression changes after CRISPR perturbations, using >270,000 perturbations to detect CREs for multiple genes.

This paper demonstrates that GPU-accelerated machine learning libraries significantly speed up and reduce the cost of computational genomics tasks like QTL mapping and Bayesian non-negative matrix factorization.

The paper isolates and sequences AGO-bound RNAs to study pre-miRNA processing in human and mouse cells, identifying novel pre-miRNAs and processing characteristics.