Xinyu Jiang

Xinyu Jiang

Auto-generated profile, based on publicly available information

Xinyu Jiang

Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 December 2025 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
RZRunze Zhang
Runze Zhang
XJXinyu Jiang
Xinyu Jiang
DCDuanhua Cao
Duanhua Cao
ZWZhaokun Wang
Zhaokun Wang
JYJie Yu
Jie Yu
MZMingyue Zheng
Mingyue Zheng
Understanding protein structure and dynamics is crucial for basic biology and drug design. Conventional methods often provide static conformations that inadequately capture protein flexibility. We present PackDock, a framework that integrates deep learning and physics-based modeling to represent protein–ligand interactions. PackDock’s core, PackPocket, uses diffusion models to sample diverse binding pocket conformations and predict ligand-induced changes. We validate PackDock through side-chain packing, redocking, and cross-docking experiments, demonstrating its ability to address protein flexibility challenges. In a real-world application, PackDock identified nanomolar affinity compounds with unreported scaffolds for the protein of interest. Additionally, it revealed key amino acid conformational changes, offering insights into protein–ligand interactions. By accurately predicting complex conformations in various scenarios, PackDock enhances our understanding of protein dynamics and provides perspectives for both basic biological research and drug discovery efforts.

1 October 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
DCDuanhua Cao
Duanhua Cao
ZFZhehuan Fan
Zhehuan Fan
JYJie Yu
Jie Yu
MCMingan Chen
Mingan Chen
XJXinyu Jiang
Xinyu Jiang
MZMingyue Zheng
Mingyue Zheng
Advances in protein structure prediction have created opportunities for structure-based drug design, yet translating structural knowledge into actionable small-molecule ligands remains difficult. Existing benchmarks often use simplified datasets and computational surrogates that poorly capture the heterogeneity and constraints of real-world drug discovery. We introduce MolGenBench, a comprehensive benchmark for de novo molecular generation and hit-to-lead optimization built on a large, structurally diverse dataset. Evaluation of 17 leading methods reveals persistent limitations, including weak virtual-screening performance, limited coverage of target-specific bioactive space, frequent high-risk structural motifs, poor target awareness, and reduced generalization to unseen proteins. Although some models improve three-dimensional conformation generation, they still struggle to produce active molecules reliably. MolGenBench provides standardized data, metrics, and analyses that connect structural prediction with practical molecular design and guide the development of more effective structure-based generative models.

30 June 2026 in Nature Communications
Verified
Journal Article
Open access
XJXinyu Jiang
Xinyu Jiang
MCMingan Chen
Mingan Chen
CZChuanlong Zeng
Chuanlong Zeng
DCDuanhua Cao
Duanhua Cao
JYJie Yu
Jie Yu
MZMingyue Zheng
Mingyue Zheng
Accurate descriptions of interactions between atoms are essential for molecular simulations used to study biology and support drug discovery. Existing force fields often face a trade-off between physical reliability, computational efficiency, and accuracy across unfamiliar molecules. Here we show that Residual Learning Force Field, a hybrid machine learning force field, can reduce this trade-off by combining simple physics-based descriptions of bonded interactions with learned corrections for remaining energetic effects. The two components are trained together through a three-step strategy so that each contributes complementary information. In tests covering drug-like molecules, molecular dimers, torsional energy profiles, energy-minimum structures, and biomolecular simulations, Residual Learning Force Field gives accurate and stable predictions across diverse systems. These results suggest that combining physical constraints with data-driven corrections can provide a practical route toward more reliable and efficient molecular simulation for biological research and drug discovery.

22 October 2025 in ChemRxiv
Verified
Preprint
Open access
PDF file
XJXinyu Jiang
Xinyu Jiang
MCMingan Chen
Mingan Chen
DCDuanhua Cao
Duanhua Cao
JYJie Yu
Jie Yu
RZRunze Zhang
Runze Zhang
MZMingyue Zheng
Mingyue Zheng
Accurate interatomic interaction modeling via force fields is critical for biological studies and drug discovery, but balancing accuracy and generalizability remains challenging. We introduce ResFF (Residual Learning Force Field), a hybrid machine learning force field that employs deep residual learning to integrate physics-based learnable molecular mechanics covalent terms with residual corrections from a lightweight equivariant neural network. Through a three-stage joint optimization, the two components are trained in a complementary manner to achieve optimal performance. Benchmarks show ResFF outperforms classical and neural network force fields in generalization (mean absolute error (MAE): 1.16 kcal/mol on Gen2-Opt, 0.90 kcal/mol on DES370K), torsional profiles (MAE: 0.45/0.48 kcal/mol on TorsionNet-500 and Torison Scan), and intermolecular interactions (MAE: 0.32 kcal/mol on S66×8). It also enables precise energy minima reproduction and stable molecular dynamics of biological systems. ResFF merges physical constraints with neural expressiveness, offering a robust tool for accurate and efficient molecular simulation.