Ben Lai

DecoderTCR improves TCR-pMHC interaction prediction using pretraining and entropy-guided decoding, achieving high AUROC scores without epitope-specific training.

The paper investigates DNA breathing's role in TF-DNA interactions using in vitro and in vivo data, finding correlations between breathing features near motifs and binding affinity across multiple TFs.

This paper introduces PLAN, a machine learning model for antibody humanization, showing improved humanness scores and mutation overlap with experimental validation.

DeepGWAS enhances GWAS signals for neuropsychiatric disorders using deep neural networks, improving locus detection in schizophrenia and validating results in other disorders.

This paper introduces a VAE-based generative model for protein design that generates high-quality 3D structures and outperforms existing methods in sequence design.

This paper introduces a deep SE(3)-equivariant model for inverse protein folding, achieving state-of-the-art results in sequence recovery and mutation effect prediction.

This paper introduces GAT-GO, a graph attention network that improves protein function prediction using predicted structure information, outperforming existing methods on benchmark datasets.

The paper introduces MetaChrom, a deep transfer learning framework for predicting epigenomic functions of genetic variants in neurodevelopment, showing improved accuracy over existing methods.