Yanjie Wei

VarDCL predicts pathogenic missense variants by integrating multimodal protein language model embeddings and self-distilled contrastive learning, achieving high performance on clinical variants.

RabbitVar is a somatic variant caller that achieves high accuracy and efficiency for small variants in cancer genomics, outperforming existing tools on real-world datasets.

AlloPED predicts allosteric sites using protein language models and machine learning, achieving high accuracy on benchmark datasets.

TransCodon is a Transformer-based model that predicts optimal synonymous codons by integrating species-specific information, 5'UTRs, and RNA structure, improving translational efficiency in heterologous hosts.

The paper predicts pathogenic mutations in allosteric proteins using a machine-learning model and identifies significant pathogenic mutations at allosteric sites.

The paper curates a database of disulfide bonds and their effects on protein thermostability, develops machine learning models to predict beneficial disulfide bonds, and demonstrates the utility of AlphaFold2 for this task.

RevGraphVAMP improves protein simulation analysis by combining graph neural networks and physical constraints, achieving higher accuracy in dimensionality reduction and state transition prediction.

This paper introduces IGModel, a deep learning framework that predicts protein-ligand docking RMSD and binding strength, achieving state-of-the-art performance on multiple benchmarks.

This study identifies distinct neurodevelopmental patterns in ASD and introduces LMFGCN, a deep-learning model that improves ASD classification by integrating cortical morphology data.

This paper generates and screens bioactive peptides using deep learning models, demonstrating their potential for therapeutic applications.

The paper introduces a generalist model for drug design that predicts multiple properties simultaneously, achieving faster virtual screening and drug development with explainability.

RabbitTClust clusters large bacterial genome datasets using MinHash sketches, achieving fast processing times for millions of genomes.

piRPheno is a manually curated database that provides experimentally supported piRNA-disease associations with confidence scores and clinical correlations.

This paper develops a machine learning model to identify iPS progenitor cells using microscopic image analysis, achieving over 52% precision in detecting these rare cells during early reprogramming.