TPThanh-An Pham

Thanh-An Pham

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Thanh-An Pham has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Rank-Resolved Multi-Engine Docking and Optuna-Optimized Re-Ranking with ProDock for Virtual Screening

    by Lai Hoang Son Le, Thanh-An Pham, Ngoc-Tam Nguyen Tran, Phuoc-Chung Van-Nguyen, Tieu-Long Phan, Tuyen Ngoc Truong

    False positives in virtual screening often arise when a single docking score or top-ranked pose is treated as sufficient evidence for binding. We extend the previously introduced ProDock software from a database-backed docking platform into a rank-resolved, multi-engine workflow for automated preparation, docking, pose analysis, and optimized re-ranking. The extended workflow combines local docking with GNINA and global docking with DiffDock with pose-level descriptors, namely binding-site occupancy, ligand localization, interaction-fingerprint similarity, and steric clash counts, together with Optuna -based threshold optimization. Across 43 DUDE-Z targets, the archived benchmark outputs reported higher enrichment values for CNN-based GNINA scores after optimization. CNNaffinity PR-AUC changed from 0.197 to 0.294 and LogAUC from 0.708 to 0.763, whereas empirical affinity ROC-AUC changed from 0.770 to 0.758. Structural investigation of re-docked actives showed that re-ranked poses were more native-like, with improved binding-site occupancy, reduced centroid displacement, and greater recovery of co-crystal interactions. The extension provides a reproducible framework for combining complementary docking engines with interpretable pose-level metrics before hit selection, thereby aiding the identification of true-positive candidates in virtual screening.

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

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

    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 \(0.888\pm 0.039\) and CV-AP of \(0.939\pm 0.032\). 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 \(0.891\pm 0.037\) and CV-AP of \(0.934\pm 0.040\). 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.


  • Open Access

    SYNERGY OF ADVANCED MACHINE LEARNING AND DEEP NEURAL NETWORKS WITH CONSENSUS MOLECULAR DOCKING FOR ENHANCED POTENCY PREDICTION OF ALK INHIBITORS

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

    This study addresses the urgent need for novel Anaplastic lymphoma kinase (ALK) inhibitors in Non-Small Cell Lung Cancer (NSCLC) treatment, focusing on the ALK-positive mutation variant (5% of the cases). As only five Food and Drug Administration (FDA)-approved ALK inhibitors are on the market, the demand for effective drugs persists. Leveraging the power of Artificial Intelligence (AI) including machine learning (ML), and deep learning, our research aimed to expedite the screening of novel ALK inhibitors. Notably, the machine learning-based XGBoost algorithm exhibited compelling results with an external validation (EV)-f1 score of 0.921, and an EV-Average Precision (AP) of 0.961, alongside a cross-validation (CV)-f1 score of 0.888±0.039 and a CV-AP of 0.939±0.032. Besides, the deep learning-based Artificial Neural Network (ANN) model demonstrated excellent performance with an EV-f1 score of 0.930 and an EV-AP of 0.955, complemented by a CV-f1 score of 0.891±0.037 and a CV-AP of 0.934±0.040. The present study undertook a comparative analysis between the traditional ML models, the ANN model, and the Graph Neural Network (GNN) model, which is a product of our recent research endeavors. The findings reveal that, despite the advancements in neural network models, traditional machine learning models exhibited superior performance over the GNN model. During this research, these models were employed in conjunction with a consensus molecular docking model to screen a total of 120,571 compounds virtually, leading to the identification of three promising ALK inhibitors: CHEMBL1689515, CHEMBL2380351, and CHEMBL102714. The study recommends further molecular dynamic simulations, in vitro tests, target-specific experimental data acquisition for active learning, and application of advanced AI models like geometric interaction GNN and generative AI for molecular optimization.

  • Open Access

    Discovery of VEGFR-2 Inhibitors employing JunctionTree Variational Encoder with Local Latent SpaceBayesian Optimization and Gradient Ascent Exploration

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

    (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 towards 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 dataset 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 being 0.710 and the binding activity threshold being -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

  • Open Access

    Novel machine learning approach toward classification model of HIV-1 integrase inhibitors

    by Tieu-Long Phan, The-Chuong Trinh, Van-Thinh To, Thanh-An Pham, Phuoc-Chung Van Nguyen, Tuyet-Minh Phan, Tuyen Ngoc Truong

    HIV-1 (human immunodeficiency virus-1) has been causing severe pandemics by attacking the immune system of its host. Left untreated, it can lead to AIDS (acquired immunodeficiency syndrome), where death is inevitable due to opportunistic diseases. Therefore, discovering new antiviral drugs against HIV-1 is crucial. This study aimed to explore a novel machine learning approach to classify compounds that inhibit HIV-1 integrase and screen the dataset of repurposing compounds. The present study had two main stages: selecting the best type of fingerprint or molecular descriptor using the Wilcoxon signed-rank test and building a computational model based on machine learning. In the first stage, we calculated 16 different types of fingerprint or molecular descriptors from the dataset and used each of them as input features for 10 machine-learning models, which were evaluated through cross-validation. Then, a meta-analysis was performed with the Wilcoxon signed-rank test to select the optimal fingerprint or molecular descriptor types. In the second stage, we constructed a model based on the optimal fingerprint or molecular descriptor type. This data followed the machine learning procedure, including data preprocessing, outlier handling, normalization, feature selection, model selection, external validation, and model optimization. In the end, an XGBoost model and RDK7 fingerprint were identified as the most suitable. The model achieved promising results, with an average precision of 0.928 ± 0.027 and an F1-score of 0.848 ± 0.041 in cross-validation. The model achieved an average precision of 0.921 and an F1-score of 0.889 in external validation. Molecular docking was performed and validated by redocking for docking power and retrospective control for screening power, with the AUC metrics being 0.876 and the threshold being identified at −9.71 kcal mol−1. Finally, 44 compounds from DrugBank repurposing data were selected from the QSAR model, then three candidates were identified as potential compounds from molecular docking, and PSI-697 was detected as the most promising molecule, with in vitro experiment being not performed (docking score: −17.14 kcal mol−1, HIV integrase inhibitory probability: 69.81%)


  • Open Access

    Novel machine learning approach toward classification model of HIV-1 integrase inhibitors

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

    HIV-1 (Human immunodeficiency virus-1) has been causing severe pandemics by attacking the immune system of its host. Left untreated, it can lead to AIDS (acquired immunodeficiency syndrome), where death is inevitable due to opportunistic diseases. Therefore, discovering new antiviral drugs against HIV-1 is crucial. This study aimed to explore a novel machine learning approach to classify compounds that inhibit HIV-1 integrase and screen the dataset of repurposing compounds. The present study had two main stages: selecting the best type of fingerprint or molecular descriptor using the Wilcoxon signed-rank test and building a computational model based on machine learning. In the first stage, we calculated 16 different types of fingerprint or molecular descriptors from the dataset and used each of them as input features for 10 machine-learning models, which were evaluated through cross-validation. Then, a meta-analysis was performed with the Wilcoxon signed-rank test to select the optimal fingerprint or molecular descriptor types. In the second stage, we constructed a model based on the optimal fingerprint or molecular descriptor type. This data followed the machine learning procedure, including data preprocessing, outlier handling, normalization, feature selection, model selection, external validation, and model optimization. In the end, an XGBoost model and RDK7 fingerprint were identified to be the most suitable. The model achieved promising results, with an average precision of 0.928 ± 0.027 and an F1-score of 0.848 ± 0.041 in cross-validation. The model achieved an average precision of 0.921 and an F1-score of 0.889 in external validation. Molecular docking was performed and validated by redocking for docking power and retrospective control for screening power, with the AUC metrics being 0.876 and the threshold being identified at –9.71 kcal/mol. Finally, 44 compounds from DrugBank repurposing data were selected from the QSAR model, then three candidates were identified as potential compounds from molecular docking, and PSI-697 was detected as the most promising molecule, with in vitro experiment being not performed (docking score: -17.14 kcal/mol, HIV integrase inhibitory probability: 69.81%)

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

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

    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 $0.879\pm 0.041$ and an $F1$ score of $0.804\pm 0.049$ 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.