Jun Cheng

AlphaGenome Atlas predicts regulatory effects of non-coding variants across the human genome, improving their prioritization and interpretation.

AlphaGenome predicts functional genomic measurements from DNA sequences with high resolution and accuracy across multiple modalities, outperforming existing methods in variant effect prediction.

BERTMHC improves MHC class II peptide binding prediction using a transformer model and multiple instance learning, outperforming existing methods.

MTSplice predicts the effects of genetic variants on tissue-specific splicing in 56 tissues and identifies enrichment of autism-associated de novo mutations in brain splicing.

This study uses AI to predict immunogenic epitopes across SARS-CoV-2 variants, identifying vaccine candidates with broad population coverage.

The paper introduces MMSplice, a modular framework for predicting genetic variant effects on splicing, achieving performance comparable to state-of-the-art methods.

Kipoi provides a framework for standardized, reusable machine learning models in genomics, enabling tasks like variant effect prediction and model benchmarking.

This paper introduces a spline transformation module for deep neural networks to model distances in regulatory sequences, improving prediction accuracy for RNA-binding protein binding sites and splice branchpoints.

This study quantifies how mRNA sequence features influence stability in yeast, revealing key motifs and dependencies on degradation pathways.