Zhixiang Ren

The paper decodes pharmacodynamic intratumoral heterogeneity by linking single-cell transcriptomes with drug-response profiles across 24 cancer types, identifying regulatory mechanisms driving differential drug responses.

scEvolver enables continual cell-type annotation across expanding single-cell atlases, revealing cellular state transitions in disease contexts.

This paper introduces Tx2Mol, a framework that translates gene-expression signatures into candidate molecules, outperforming baselines in chemical plausibility and phenotypic preservation.

This paper improves variant effect prediction by modifying protein language models with sparse mechanistic features, achieving significant performance gains across multiple datasets.

This paper proposes a framework that transfers knowledge from multi-modal genomic data to gene expression-only models to improve drug response prediction.

DVE-stability predicts mutation-induced protein stability changes using a dual-view ensemble learning framework, achieving state-of-the-art performance on multiple benchmarks and showing strong generalization to rare beneficial mutations.

This paper develops a deep-learning framework to predict real-world prevalent SARS-CoV-2 mutations using in silico virus evolution and protein language models, achieving accurate predictions of future dominant mutations.

3D-Mol predicts molecular properties using 3D structure information by contrastive learning on 20M unlabeled data, outperforming baselines on 5 benchmarks.

This paper develops a framework for predicting single-cell drug responses using pharmacogenomic embeddings and few-shot transfer learning, showing improved accuracy and generalization.

The paper develops a scRNA-seq dataset of immune cells from 39 cancers and uses machine learning to identify cytokine expression patterns for cancer classification with 78.01% accuracy.

This paper introduces PepGenWOA, a generative model for bioactive peptide design that outperforms existing methods and enables efficient virtual screening.

This paper develops an AI-based simulation method to predict future high-risk SARS-CoV-2 variants by simulating RBD mutations and screening potential variants efficiently.

The paper uses a deep neural network to identify bioactive constituents in TCM prescriptions for colitis, finding that selected compounds effectively suppress disease progression in mice.

This study introduces SpliceBERT, a self-supervised pre-trained language model for RNA splicing prediction, showing improved performance in variant effect prediction and cross-species splice site identification.