Hoang-Son Lai Le

Hoang-Son Lai Le

Organic Chemistry, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City, Hồ Chí Minh, Vietnam

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
14 April 2026 in Journal of the American Chemical Society
Verified
Journal Article
Open access
SASandeep Atla
Sandeep Atla
VVVeerabhadra Vulupala
Veerabhadra Vulupala
YAYugendar R. Alugubelli
Yugendar R. Alugubelli
LBLauren R. Blankenship
Lauren R. Blankenship
KYKai Yang
Kai Yang
WLWenshe Ray Liu
Wenshe Ray Liu
Anecdotal reports about smokers with low SARS-CoV-2 infection rates prompted a search for nicotine and its pyrolysis products as SARS-CoV-2 main protease (MPro) inhibitors. From this search, 3-vinylpyridine was discovered as a weak binder for the MPro S1 subsite and was used subsequently as a de novo starting point for covalent inhibitor design that quickly yielded a highly potent inhibitor, SR-A-174, with an IC50 value of 60 nM. Representing a novel class of MPro inhibitors, SR-A-174 features an N,N-diaryl-α,α-dichloroacetamide scaffold that facilitated rapid exploration of alternative covalent warheads and various N-substituents, leading to the identification of multiple inhibitors with potent antiviral activity. Eight such MPro inhibitor structures were determined, all demonstrating covalent binding to catalytic Cys145 of MPro. In six determined structures, binding is dominated by the covalent bond plus van der Waals contacts, which contrasts with the extensive hydrogen bond networks formed with peptidomimetic inhibitors such as nirmatrelvir. Strikingly, two N,N-diaryl-α,α-dichloroacetamide inhibitors exhibit an unprecedented dual covalent modification mode of the catalytic dyad, forming bonds to both Cys145 and His41 with a concomitant loss of both chlorides and displacing the inhibitors from the S1 subsite. This dyad-targeting reactivity suggests a novel route for bioconjugation of both cysteine and histidine.

18 October 2023
Verified
Conference Paper
Closed access
TTThe-Chuong Trinh
The-Chuong Trinh
TPTieu-Long Phan
Tieu-Long Phan
VTVan Thinh To
Van Thinh To
GTGia-Bao Truong
Gia-Bao Truong
APAn Thanh Pham
An Thanh Pham
NTNgoc-Tuyen Truong
Ngoc-Tuyen 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.

22 April 2026 in Journal of Cheminformatics
Verified
Journal Article
Open access
PDF file
TPTuyet-Minh Phan
Tuyet-Minh Phan
TPTieu-Long Phan
Tieu-Long Phan
CNChung Nguyen
Chung Nguyen
HLHoang-Son Lai Le
Hoang-Son Lai Le
VTVan Thinh To
Van Thinh To
Peter F. StadlerPeter F. Stadler
Peter F. Stadler
Background: Quantitative structure-activity relationship (QSAR) models are central to computer-aided drug discovery and predictive toxicology, but practical adoption is often impeded by ad-hoc tooling, inconsistent validation protocols, and poor reproducibility. Objective: We introduce , a modular, reproducible workbench that formalizes end-to-end QSAR development while permitting independent use of each component. Methods: composes interchangeable modules for standardization, feature generation, splitting (including scaffold- and cluster-aware splits), preprocessing, outlier handling, scaling, feature selection, model training and tuning, statistical comparison, conformal calibration, and applicability-domain assessment. The pipeline can run end-to-end to produce versioned artifact bundles (serialized models) and analyst-oriented reports suitable for deployment and audit. Results: On representative benchmarks evaluated under Bemis–Murcko scaffold split, attains state-of-the-art descriptor-based performance: the lowest mean RMSE across the regression suite (, , ; mean RMSE $$0.658\pm 0.11$$ 0.658 ± 0.11 ), including a substantial improvement on (RMSE $$0.494$$ 0.494 vs. $$0.731$$ 0.731 for a leading graph method). On quantum mechanical benchmarks, demonstrated superior performance on the single-task dataset and maintained competitive results on the multi-task dataset. For classification, achieves the top ROC–AUC on (91.4%) while remaining competitive across other benchmark (overall classification average $$70.4\pm 11.6$$ 70.4 ± 11.6 ). Crucially, all predictions are accompanied by cross-conformal prediction and explicit applicability-domain flags that identify out-of-distribution entries, enabling calibrated and decision support. Availability: is released on , , and ; all releases embed full provenance (parameters, package versions, checksums) to ensure reproducibility. Scientific contribution: (i) enforces best-practice, group-aware validation together with formal statistical comparisons across models, (ii) integrates calibrated uncertainty quantification (cross-conformal prediction) and applicability-domain diagnostics for interpretable, risk-aware predictions, and (iii) exposes both a composable developer API and a one-click pipeline that generates deployment-ready artifacts and human-readable reports, demonstrated on representative benchmarks.

15 September 2025 in Journal of Computer-Aided Molecular Design
Verified
Journal Article
Closed access
PDF file
TTThe-Chuong Trinh
The-Chuong Trinh
TPTieu-Long Phan
Tieu-Long Phan
VTVan Thinh To
Van Thinh To
APAn Thanh Pham
An Thanh Pham
GTGia-Bao Truong
Gia-Bao Truong
NTNgoc-Tuyen Truong
Ngoc-Tuyen Truong

4 November 2025 in ChemRxiv
Verified
Preprint
Open access
PDF file
TPTuyet-Minh Phan
Tuyet-Minh Phan
TPTieu-Long Phan
Tieu-Long Phan
PVPhuoc-Chung Van-Nguyen
Phuoc-Chung Van-Nguyen
HLHoang-Son Lai Le
Hoang-Son Lai Le
VTVan Thinh To
Van Thinh To
Peter F. StadlerPeter F. Stadler
Peter F. Stadler
Background: Quantitative structure–activity relationship (QSAR) models are central to computer-aided drug discovery and predictive toxicology, but practical adoption is often impeded by ad-hoc tooling, inconsistent validation protocols, and poor reproducibility. Objective: We introduce ProQSAR, a modular, reproducible workbench that formalizes end-to-end QSAR development while permitting independent use of each component. Methods: ProQSAR composes interchangeable modules for standardization, feature generation, splitting (including scaffold- and cluster-aware splits), preprocessing, outlier handling, scaling, feature selection, model training and tuning, statistical comparison, conformal calibration, and applicability-domain assessment. The pipeline can run end-to-end to produce versioned artifact bundles (serialized models, transformers, split indices, provenance metadata) and analyst-oriented reports suitable for deployment and audit. Results: On representative MoleculeNet benchmarks evaluated under Bemis–Murcko scaffold-aware protocols, ProQSAR attains state-of-the-art descriptor-based performance: the lowest mean RMSE across the regression suite (ESOL, FreeSolv, Lipophilicity; mean RMSE 0.658 ± 0.12), including a substantial improvement on FreeSolv (RMSE 0.494 vs. 0.731 for a leading graph method). For classification, ProQSAR achieves the top ROC–AUC on ClinTox (91.4%) while remaining competitive on BACE and BBBP (overall classification average 75.5 ± 11.4). Crucially, all predictions are accompanied by cross-conformal prediction and explicit applicability-domain flags that identify out-of-scope inputs, enabling calibrated, risk-aware decision support. Availability: ProQSAR is released on PyPI, Conda, and Docker Hub; all releases embed full provenance (parameters, package versions, checksums) to ensure reproducibility. Scientific contribution: ProQSAR (i) enforces best-practice, group-aware validation together with formal statistical comparisons across models, (ii) integrates calibrated uncertainty quantification (cross-conformal prediction) and applicability-domain diagnostics for interpretable, risk-aware predictions, and (iii) exposes both a composable developer API and a one-click pipeline that generates deployment-ready artifacts and human-readable reports, demonstrated on representative benchmarks.

24 July 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
HLHoang-Son Lai Le
Hoang-Son Lai Le
APAn Thanh Pham
An Thanh Pham
NTNgoc-Tam Nguyen Tran
Ngoc-Tam Nguyen Tran
CNChung Nguyen
Chung Nguyen
TPTieu-Long Phan
Tieu-Long Phan
NTNgoc-Tuyen Truong
Ngoc-Tuyen 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.