Yu Chen

This study benchmarks strategies for constructing single-cell genome-scale metabolic models across nine scRNA-seq datasets, evaluating accuracy, sensitivity, and computational feasibility.

This paper develops a large language model-based method to extract metabolic engineering strategies from research articles and trains a hybrid model to predict engineering targets, outperforming traditional approaches.

The paper shows that bacteria minimize proteome reallocation during metabolic transitions and introduces dMORP to simulate this process using omics data.

This paper identifies CTHRC1 as a therapeutic target and serum biomarker for aortic dissection, showing it regulates VSMC phenotype and aortic integrity via the ERK1/2 pathway.

The paper introduces FROG analysis to standardize reproducibility assessments of genome-scale metabolic models, resulting in full reproducibility of all tested models.

The paper develops Yeast-MetaTwin, a metabolic model for yeast that expands coverage of the metabolome using retrobiosynthesis and deep learning, revealing new insights into underground metabolism.

A substrate graph neural network plus protein-sequence CNN predicts enzyme kcat (test Pearson r 0.71), tracks mutation effects, and parameterizes enzyme-constrained models for 343 yeast/fungi species.

The paper develops a genome-scale model of the yeast protein secretory pathway to identify targets for improving recombinant protein production, finding that the secretory pathway has more limited capacity than metabolism.

The paper identifies nutrient uptake constraints in Lactococcus lactis using a proteome-constrained model and experimental data, showing how these constraints influence metabolic fluxes and fitness in nutrient-rich environments.