publications

2025

1. JCIM

   

   KGG: Knowledge-Guided Graph Self-Supervised Learning to Enhance Molecular Property Predictions

   Van-Thinh To, Phuoc-Chung Van Nguyen, Gia-Bao Truong, Tuyet-Minh Phan, Tieu-Long Phan, Rolf Fagerberg, Peter F. Stadler, and Tuyen Ngoc Truong

   Journal of Chemical Information and Modeling, 2025

   PMID: 40916452

   Abs DOI Bib PDF Code

   Molecular property prediction has become essential in accelerating advancements in drug discovery and materials science. Graph Neural Networks have recently demonstrated remarkable success in molecular representation learning; however, their broader adoption is impeded by two significant challenges: (1) data scarcity and constrained model generalization due to the expensive and time-consuming task of acquiring labeled data and (2) inadequate initial node and edge features that fail to incorporate comprehensive chemical domain knowledge, notably orbital information. To address these limitations, we introduce a Knowledge-Guided Graph (KGG) framework employing self-supervised learning to pretrain models using orbital-level features in order to mitigate reliance on extensive labeled data sets. In addition, we propose novel representations for atomic hybridization and bond types that explicitly consider orbital engagement. Our pretraining strategy is cost efficient, utilizing approximately 250,000 molecules from the ZINC15 data set, in contrast to contemporary approaches that typically require between two and ten million molecules, consequently reducing the risk of potential data contamination. Extensive evaluations on diverse downstream molecular property data sets demonstrate that our method significantly outperforms state-of-the-art baselines. Complementary analyses, including t-SNE visualizations and comparisons with traditional molecular fingerprints, further validate the effectiveness and robustness of our proposed KGG approach. The key advantages of KGG are its data efficiency and architectural versatility, driven by orbital-informed representations. By distilling essential chemical knowledge from modest corpora, it avoids extensive pretraining and excels in low-data fine-tuning, providing a robust and chemically meaningful foundation for diverse GNN architectures.

   @article{kgg,
     author = {To, Van-Thinh and Van Nguyen, Phuoc-Chung and Truong, Gia-Bao and Phan, Tuyet-Minh and Phan, Tieu-Long and Fagerberg, Rolf and Stadler, Peter F. and Truong, Tuyen Ngoc},
     title = {KGG: Knowledge-Guided Graph Self-Supervised Learning to Enhance Molecular Property Predictions},
     journal = {Journal of Chemical Information and Modeling},
     volume = {65},
     number = {18},
     pages = {9443-9458},
     year = {2025},
     doi = {10.1021/acs.jcim.5c01068},
     note = {PMID: 40916452},
     keywords = {Drug discovery, graph neural networks, knowledge graph, self-supervised learning, orbital information},
   }

2. JCAMD

   

   Synergy of advanced machine learning and deep neural networks with consensus molecular docking for virtual screening of anaplastic lymphoma kinase inhibitors

   The-Chuong Trinh, Tieu-Long Phan, Van-Thinh To, Thanh-An Pham, Gia-Bao Truong, Lai Hoang Son Le, Xuan-Truc Dinh Tran, and Tuyen Ngoc Truong

   Journal of Computer-Aided Molecular Design, Sep 2025

   Abs DOI Bib

   This study addresses the urgent need for an AI model to predict Anaplastic Lymphoma Kinase (ALK) inhibitors for Non-Small Cell Lung Cancer treatment, targeting the ALK-positive mutation. With only five Food and Drug Administration approved ALK inhibitors currently available, effective drugs remain in demand. Leveraging machine learning (ML) and deep learning (DL), our research accelerates the precise screening of novel ALK inhibitors using both ligand-based and structure-based approaches. In ligand-based approach, an ensemble voting model comprising three base learners to classify potential ALK inhibitors, achieving promising retrospective validation results. Notably, the ML-based XGBoost algorithm exhibited compelling results with external validation (EV)-f1 score of 0.921, EV-Average Precision (AP) of 0.961, cross-validation (CV)-f1 score of and CV-AP of . Besides, the DL-based Artificial Neural Network (ANN) model demonstrated comparative performance with EV-f1 score of 0.930, EV-AP of 0.955, CV-f1 score of and CV-AP of . For structure-based approach, an XGBoost consensus docking model utilized scores from three molecular docking programs (GNINA 1.0, Vina-GPU 2.0, and AutoDock-GPU) as features. Combining these two approaches, we virtually screened 120,571 compounds, identifying three promising ALK inhibitors, CHEMBL1689515, CHEMBL2380351, and CHEMBL102714, that bind to the protein’s pocket and establish hydrophobic contacts in the hinge region through their ketone groups, resembling Alectinib’s interaction. Comparative analysis revealed traditional ML models outperformed Graph Neural Networks (GNN), highlighting the critical role of feature engineering and dataset size importance. The study recommends further in vitro testing to validate the prospective screening performance of these models. A graphical user interface is available at https://huggingface.co/spaces/thechuongtrinh/ALK_inhibitors_classification.

   @article{alk,
     author = {Trinh, The-Chuong and Phan, Tieu-Long and To, Van-Thinh and Pham, Thanh-An and Truong, Gia-Bao and Le, Lai Hoang Son and Tran, Xuan-Truc Dinh and Truong, Tuyen Ngoc},
     title = {Synergy of advanced machine learning and deep neural networks with consensus molecular docking for virtual screening of anaplastic lymphoma kinase inhibitors},
     journal = {Journal of Computer-Aided Molecular Design},
     year = {2025},
     month = sep,
     day = {15},
     volume = {39},
     number = {1},
     pages = {79},
     issn = {1573-4951},
     doi = {10.1007/s10822-025-00657-6},
     keywords = {ALK, computer-aided drug design, artificial intelligence, machine learning, benchmarking, consensus molecular docking},
   }

2024

1. ACS Omega

   

   Discovery of Vascular Endothelial Growth Factor Receptor 2 Inhibitors Employing Junction Tree Variational Autoencoder with Bayesian Optimization and Gradient Ascent

   Gia-Bao Truong, Thanh-An Pham, Van-Thinh To, Hoang-Son Lai Le, Phuoc-Chung Van Nguyen, The-Chuong Trinh, Tieu-Long Phan, and Tuyen Ngoc Truong

   ACS Omega, 2024

   Abs DOI Bib PDF Code

   In the development of anticancer medications, vascular endothelial growth factor receptor 2 (VEGFR-2), which belongs to the protein tyrosine kinase family, emerges as one of the most significant targets of interest. The ongoing Food and Drug Administration (FDA) approval of novel therapeutic medicines toward VEGFR-2 emphasizes the urgent need to discover sophisticated molecular structures that are capable of reliably limiting VEGFR-2 activity. Recognizing the huge potential of deep-learning-based molecular model advancements, we focused our study on exploring the chemical space to find small molecules potentially inhibiting VEGFR-2. To achieve this goal, we utilized the junction tree variational autoencoder in combination with two optimization approaches on the latent space: the local Bayesian optimization on the initial data set and the gradient ascent on nine FDA-approved drugs targeting VEGFR-2. The optimization results yielded a set of 493 uncharted small molecules. Quantitative structure–activity relationship (QSAR) models and molecular docking were used to assess the generated molecules for their inhibitory potential using their predicted pIC50 and binding affinity. The QSAR model constructed on RDK7 fingerprints using the CatBoost algorithm achieved remarkable coefficients of determination (R2) of 0.792 ± 0.075 and 0.859 with respect to internal and external validation. Molecular docking was implemented using the 4ASD complex with optimistic retrospective control results (the ROC-AUC value was 0.710 and the binding activity threshold was −7.90 kcal/mol). Newly generated molecules possessing acceptable results corresponding to both assessments were shortlisted and checked for interactions with the protein at the binding site on important residues, including Cys919, Asp1046, and Glu885.

   @article{vegfr2,
     title = {Discovery of Vascular Endothelial Growth Factor Receptor 2 Inhibitors Employing Junction Tree Variational Autoencoder with Bayesian Optimization and Gradient Ascent},
     author = {Truong, Gia-Bao and Pham, Thanh-An and To, Van-Thinh and Lai Le, Hoang-Son and Van Nguyen, Phuoc-Chung and Trinh, The-Chuong and Phan, Tieu-Long and Truong, Tuyen Ngoc},
     keywords = {Vascular endothelial growth factor receptor 2, junction tree variational autoencoder, bayesian optimization, gradient ascent},
     doi = {10.1021/acsomega.4c07689},
     url = {https://pubs.acs.org/doi/10.1021/acsomega.4c07689},
     journal = {ACS Omega},
     year = {2024},
   }

2023

1. KSE 2023

   

   A Graph Neural Network Model Enables Accurate Prediction of Anaplastic Lymphoma Kinase Inhibitors Compared to Other Machine Learning Models

   The-Chuong Trinh, Tieu-Long Phan, Van-Thinh To, Gia-Bao Truong, Thanh-An Pham, Hoang-Son Lai Le, Phuoc-Chung Van Nguyen, and Tuyen Ngoc Truong

   In 2023 15th International Conference on Knowledge and Systems Engineering (KSE), 2023

   Abs DOI Bib

   Anaplastic lymphoma kinase (ALK), a tyrosine kinase receptor, is identified as a crucial target in the progression of anticancer therapeutics for non-small cell lung cancer. This study has executed a Graph Neural Network (GNN) model and compared it with three machine learning (ML) models based on fingerprints for rapid anticancer bioactivity prediction. ALK inhibitors with IC50 values were extracted from the REAXYS database. Following preprocessing, these inhibitors constituted a dataset of 1664 molecules. Subsequently, GNN and ML models were constructed on a training set. The generalizability of these models was assessed by internal and external validation procedures. The graph neural network model yielded promising results, with an average precision of 0.879±0.041 and an F1 score of 0.804±0.049 in cross-validation. In external validation, the model achieved an average precision of 0.938 and an F1 score of 0.863, surpassing the results of the ML models. Therefore, we can infer that the predictive model developed using the GNN is apt for the problem at hand and can be utilized to predict the biological activity of novel ALK inhibitors.

   @inproceedings{kse,
     author = {Trinh, The-Chuong and Phan, Tieu-Long and To, Van-Thinh and Truong, Gia-Bao and Pham, Thanh-An and Lai Le, Hoang-Son and Van Nguyen, Phuoc-Chung and Ngoc Truong, Tuyen},
     booktitle = {2023 15th International Conference on Knowledge and Systems Engineering (KSE)},
     title = {A Graph Neural Network Model Enables Accurate Prediction of Anaplastic Lymphoma Kinase Inhibitors Compared to Other Machine Learning Models},
     year = {2023},
     volume = {},
     number = {},
     pages = {1--6},
     keywords = {Training,Knowledge engineering,Inhibitors,Biological system modeling,Lung cancer,Machine learning,Predictive models,Anaplastic lymphoma kinase,NSCLC,Graph neural network,Machine learning,Benchmarking},
     doi = {10.1109/KSE59128.2023.10299477},
     url = {https://ieeexplore.ieee.org/document/10299477},
   }

2. AFPS 2023

   

   Innovative Exploration of VEGFR-2 Inhibitors in chemical space with Gradient Ascent and Junction Tree Variational Autoencoder

   Gia-Bao Truong, Thanh-An Pham, Van-Thinh To, Hoang-Son Lai Le, Phuoc-Chung Van Nguyen, The-Chuong Trinh, Tieu-Long Phan, and Tuyen Ngoc Truong

   Asian Federation for Pharmaceutical Sciences 2023, Ha Noi, Vietnam (Poster presenter) , 2023

   Bib Poster

   @misc{afps2023_vegfr2,
     author = {Truong, Gia-Bao and Pham, Thanh-An and To, Van-Thinh and Lai Le, Hoang-Son and Van Nguyen, Phuoc-Chung and Trinh, The-Chuong and Phan, Tieu-Long and Truong, Tuyen Ngoc},
     title = {Innovative Exploration of VEGFR-2 Inhibitors in chemical space with Gradient Ascent and Junction Tree Variational Autoencoder},
     year = {2023},
   }

3. AFPS 2023

   

   New Thorough Molecular Docking Approach: A Virtual Screening Study Targeting the Colchicine Binding Site

   Hoang-Son Lai Le, Tieu-Long Phan, Gia-Bao Truong, The-Chuong Trinh, Van-Thinh To, Thanh-An Pham, Phuoc-Chung Van Nguyen, and Tuyen Ngoc Truong

   Asian Federation for Pharmaceutical Sciences 2023, Ha Noi, Vietnam (Best poster) , 2023

   Bib

   @misc{afps2023_docking,
     author = {Lai Le, Hoang-Son and Phan, Tieu-Long and Truong, Gia-Bao and Trinh, The-Chuong and To, Van-Thinh and Pham, Thanh-An and Van Nguyen, Phuoc-Chung and Truong, Tuyen Ngoc},
     title = {New Thorough Molecular Docking Approach: A Virtual Screening Study Targeting the Colchicine Binding Site},
     year = {2023},
   }