Mingchen Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mingchen Xie has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Peng Lun
Department of Neurosurgery, the Affiliated Hospital of Qingdao University, Qingdao, China
2 shared publications - Xia Liu
Department of Neurosurgery, the Affiliated Hospital of Qingdao University, Qingdao, China
2 shared publications - Xiaodong Chen
Department of Neurosurgery, the Affiliated Hospital of Qingdao University, Qingdao, China
2 shared publications - Xueyan Li
Department of Neurosurgery, the Affiliated Hospital of Qingdao University, Qingdao, China
2 shared publications Bibo Wang
Department of orthopedics, Shanghai Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
1 shared publication- Bing Chen
Department of Neurosurgery, the Affiliated Hospital of Qingdao University, Qingdao, China
1 shared publication
Latest Publications
- Open Access
- 25 September 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (8) , 881
CMDA-Net: Auditable SHAP-based brain-tumor MRI classification, with a cross-modal dynamic-attention design for modality-robust segmentation
- 25 September 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (8) , 881
Open AccessCMDA-Net: Auditable SHAP-based brain-tumor MRI classification, with a cross-modal dynamic-attention design for modality-robust segmentation
- Open Access
- 22 September 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (8) , 875
HCTNet: a hierarchical hybrid convolution-transformer network with bidirectional cross-attention fusion for brain tumor MRI classification
- 22 September 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (8) , 875
Open AccessHCTNet: a hierarchical hybrid convolution-transformer network with bidirectional cross-attention fusion for brain tumor MRI classification
- Open Access
- 22 September 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (8) , 869
A multi-modal mixture-of-experts deep network with cross-pathway attention fusion and hierarchical Tree-SHAP attribution for interpretable heterogeneous prediction
- 22 September 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (8) , 869
Open AccessA multi-modal mixture-of-experts deep network with cross-pathway attention fusion and hierarchical Tree-SHAP attribution for interpretable heterogeneous prediction
- Open Access
- 24 November 2025
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1)
MoleProLink-RL: geometric transport for domain-policy reinforcement learning in drug-target interaction prediction
Accurate drug-target interaction (DTI) prediction is vital to modern discovery workflows, yet models trained in one setting often underperform when chemotypes, protein families, or assay conditions shift. MoleProLink-RL addresses this challenge as a model-first solution that couples chemically faithful representations with geometry-aware alignment and stability-aware decision making. The system combines graph-transformer drug encoders and residual protein embeddings with an unsupervised distribution alignment layer that respects molecular similarity through a DTI-aware transport distance complemented by kernel mean embeddings, while a lightweight reinforcement-learning objective regulates ranking stability across latent sub-environments under a small trust region to a supervised reference. Unlike pipelines that bolt adaptation onto frozen features or tune policies post hoc, MoleProLink-RL trains representation, alignment, and decisions end-to-end so that what the model learns to represent directly improves how it prioritizes candidates under shift. We provide a Fisher–Wasserstein view that clarifies why joint updates are safe in parameter space and effective on distribution space, and we validate the approach on Human, C. elegans, and Davis benchmarks with realistic class imbalance, comprehensive ablations, and diagnostics for calibration and interpretability. The result is a practical, data-efficient DTI model that maintains top-of-list precision when conditions change, narrowing the gap between benchmark performance and laboratory impact.
- 24 November 2025
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1)
Open AccessMoleProLink-RL: geometric transport for domain-policy reinforcement learning in drug-target interaction prediction
Accurate drug-target interaction (DTI) prediction is vital to modern discovery workflows, yet models trained in one setting often underperform when chemotypes, protein families, or assay conditions shift. MoleProLink-RL addresses this challenge as a model-first solution that couples chemically faithful representations with geometry-aware alignment and stability-aware decision making. The system combines graph-transformer drug encoders and residual protein embeddings with an unsupervised distribution alignment layer that respects molecular similarity through a DTI-aware transport distance complemented by kernel mean embeddings, while a lightweight reinforcement-learning objective regulates ranking stability across latent sub-environments under a small trust region to a supervised reference. Unlike pipelines that bolt adaptation onto frozen features or tune policies post hoc, MoleProLink-RL trains representation, alignment, and decisions end-to-end so that what the model learns to represent directly improves how it prioritizes candidates under shift. We provide a Fisher–Wasserstein view that clarifies why joint updates are safe in parameter space and effective on distribution space, and we validate the approach on Human, C. elegans, and Davis benchmarks with realistic class imbalance, comprehensive ablations, and diagnostics for calibration and interpretability. The result is a practical, data-efficient DTI model that maintains top-of-list precision when conditions change, narrowing the gap between benchmark performance and laboratory impact.