Jie Zheng

This study identifies nine glucose-lowering drug targets with anti-aging potential mediated by DNA methylation in specific tissues using multi-omics genetic methods.

This paper introduces LukePi, a self-supervised pre-training framework for GNNs on biomedical knowledge graphs, which improves link prediction in low-data and distribution-shift scenarios.

PhysDock predicts protein-ligand complexes using a physics-guided diffusion model, achieving state-of-the-art performance in redocking and cross-docking benchmarks.

MiT4SL predicts synthetic lethality in cancer cell lines using multi-omics triplet representation learning, outperforming existing models in cell line-adapted scenarios.

This study uses large language models and ontologies to extract and explain protein-protein interactions from scientific literature, showing improved performance with parameter-efficient fine-tuning.

This study benchmarks machine learning methods for predicting synthetic lethality in cancer using matrix factorization and deep learning models, highlighting performance differences and emphasizing data and scenario importance.

MCLand is a Python program that visualizes Waddington's epigenetic landscape using Monte Carlo simulations to model gene regulatory networks and estimate cell state probabilities.

This study uses Mendelian randomization to investigate the causal effects of ABO protein levels on pregnancy outcomes, finding potential causal links to venous complications and haemorrhoids.

TMELand integrates data-driven GRN inference with model-driven landscape mapping to visualize and analyze cellular transition dynamics from single-cell transcriptomic data.

SynLethDB 2.0 is a database that compiles synthetic lethal gene pairs and related knowledge to aid in anticancer drug discovery, including over 16,000 new synthetic lethal interactions.

The paper organizes a DREAM challenge to benchmark predictive models of single-cell signaling using mass cytometry data from breast cancer cell lines.

This paper introduces GCATSL, a graph contextualized attention network for predicting synthetic lethality in human cancers, outperforming existing methods on multiple datasets.

The paper introduces a Monte Carlo method to model and visualize the Waddington's epigenetic landscape of gene regulatory networks, showing how attractors and paths between them represent stability in biological systems.