Ming-chen Xie

Mr. Ming-chen Xie

Department of Medicine, Qingdao University, Qingdao, Shandong, 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 November 2025 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
DXDonghao Xu
Donghao Xu
BWBibo Wang
Bibo Wang
DZDexing Zhu
Dexing Zhu
CZChenzhi Zheng
Chenzhi Zheng
HWHaitao Wu
Haitao Wu
CZchao zhang
chao zhang
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.

25 September 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
MXMing-chen Xie
Ming-chen Xie
XLXueyan Li
Xueyan Li
XLXia Liu
Xia Liu
XCXiaodong Chen
Xiaodong Chen
PLPeng Lun
Peng Lun
Reliable computer-aided analysis of brain-tumor MRI must be accurate, robust to the imaging conditions encountered in practice, and interpretable in a form that can be documented and reviewed. We present CMDA-Net, a framework built around two contributions. The first, which we validate experimentally, is an auditable classification pipeline: a 2D residual–CBAM classifier (CMDA-Cls) coupled with a SHAP-based interpretation layer that goes beyond heatmaps to emit a centre-versus-periphery separability metric and an attribution-weighted confusion matrix, archived in a versionable multi-sheet report to support post-hoc auditing. On the four-class Brain Tumor MRI benchmark, CMDA-Cls attains \(99.47\%\) accuracy and \(99.44\%\) macro-F1 on the full held-out test set (\(N{=}1311\)), with \(97.09\%\!\pm \!0.55\%\) accuracy under stratified 5-fold cross-validation, and the centre-to-periphery attribution ratio exceeds one for every class (from 1.17 on pituitary to 2.94 on meningioma), excluding peripheral-shortcut behaviour. The second contribution is architectural: a 3D multi-modal segmentation network (CMDA-Seg) that couples Cross-Modal Attention Fusion (CMAF), a survival-constrained Modality-Dropout (MoDrop) regularizer and a FiLM-conditioned decoder to fuse MRI modalities adaptively and to degrade gracefully when modalities are missing. Because a multi-parametric segmentation cohort was not available for this study, CMDA-Seg is presented as a design contribution whose four-modality evaluation is left to future work.

22 September 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
XLXueyan Li
Xueyan Li
MXMing-chen Xie
Ming-chen Xie
XLXia Liu
Xia Liu
XCXiaodong Chen
Xiaodong Chen
PLPeng Lun
Peng Lun
Heterogeneous multi-modal data that mixes categorical demographics, continuous biomarkers and high-dimensional binary indicators remains a long-standing challenge for deep learning, particularly when fusion across modalities is delegated to undifferentiated attention blocks and when the resulting predictor must be deployed under strict interpretability constraints. We propose a multi-modal mixture-of-experts deep network that injects modality-specific inductive bias into the fusion pipeline rather than treating heterogeneous streams as exchangeable token sequences. The model couples three dedicated encoders—a clinical encoder equipped with a learnable periodic embedding for the continuous variables, a dynamics encoder that re-orders binary indicators along a pseudo-temporal axis and processes them with stacked dilated temporal convolutions modulated by Feature-wise Linear Modulation, and a structural encoder that combines three Graph Attention layers with a Transformer block over a soft fully-connected graph—and integrates them through pairwise cross-pathway attention, gated fusion and a Top-2-of-6 Mixture-of-Experts router. The whole pipeline is trained end-to-end under a multi-task objective that jointly couples classification, evidential uncertainty estimation, auxiliary multi-label prediction and risk regression. To make the resulting predictor inspectable, we further design a four-layer Tree-SHAP attribution framework that operates on a distilled tree-based surrogate—trained to reproduce the deep model’s outputs rather than the raw label—and exposes the model at the global, sample, interaction and subgroup levels within a single coherent pipeline. On a programmatically simulated heterogeneous cohort of 420 cases spanning 21 multi-modal variables, the end-to-end network attains an AUC of \(0.994\pm 0.014\) and an accuracy of \(98.8\pm 1.2\,\%\) under \(5\times 5\) repeated stratified cross-validation; an extensive analysis shows that this cohort is near-linearly separable (so conventional baselines saturate as well), that performance degrades gracefully under simulated acquisition shift and reduced class separation, that a label-permutation control collapses to chance, and that the distilled surrogate reproduces the deep predictor (probability \(R^{2}{=}0.77\), class agreement \(94\,\%\)), which makes the subsequent attribution layer faithful by construction. The hierarchical attribution analysis further shows that eight features account for over \(80\,\%\) of the predictive signal, cross-modality interactions contribute \(55.6\,\%\) of the top-50 interaction strength, and the per-subgroup evidence chains remain strictly symmetric around the population expectation. Together, these results—reported with their limitations made explicit—establish PD-GliomaNet and its hierarchical Tree-SHAP companion as a transferable blueprint for accurate, uncertainty-aware and inspectable multi-modal deep learning on heterogeneous data.

22 September 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
MXMing-chen Xie
Ming-chen Xie
YXYifan Xu
Yifan Xu
CWChao Wang
Chao Wang
HWHaitao Wu
Haitao Wu
BCBing Chen
Bing Chen
Accurate brain tumor classification from magnetic resonance imaging (MRI) requires modelling both fine-grained local cues, such as tumor margins and intensity heterogeneity, and long-range contextual cues, such as the spatial relationship between the lesion and the surrounding anatomy. Convolutional neural networks (CNNs) capture the former but are limited by restricted receptive fields, whereas vision transformers (ViTs) capture the latter but underuse fine local structure. Existing hybrids typically combine the two by sequential stacking or late concatenation at the network tail, so local and global representations are not progressively aligned and seldom exchange information bidirectionally. We propose HCTNet, a four-stage hierarchical hybrid network in which a convolutional Local Feature Extractor (inverted-residual blocks with squeeze-and-excitation) runs in parallel with a transformer-based Global Feature Extractor (spatial-reduction self-attention at high resolution, standard multi-head self-attention at low resolution). The two branches are coupled by the proposed Cross-Attention Fusion Module, invoked after every paired block, which performs bidirectional cross-attention followed by a learnable channel-wise gated combination, so the representations are aligned and re-weighted throughout the backbone rather than only at the classifier head. For interpretability, we compute Grad-CAM and Integrated Gradients jointly on a shared explanation set and report per-image and per-class agreement (mask intersection-over-union and heatmap Pearson correlation). On the full canonical four-class Brain Tumor MRI benchmark (5, 712 training and 1, 311 held-out test slices), HCTNet attains \(97.79\%\) overall accuracy, a macro-averaged F1 of 0.977 and a macro-averaged one-vs-rest AUC of 0.998 with only 16.0M parameters. Under an identical from-scratch training protocol it matches or exceeds representative CNN, transformer and recent (2022-era) backbones—including ResNet-50, EfficientNetV2-S, ConvNeXt-T, Swin-T and Swin-V2-T—while using fewer parameters, and an ablation confirms that the proposed bidirectional Cross-Attention Fusion Module outperforms additive and concatenation fusion. The interpretability analysis further shows that Grad-CAM and Integrated Gradients expose complementary region-level and pixel-level evidence concentrated within the brain parenchyma.