Hui Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hui Shen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Haiying Yu
Zhejiang Normal University
2 shared publications - Bangyu Chen
College of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, China
1 shared publication - Chen Zhou
College of Geography and Environmental Sciences, Zhejiang Normal University, Yingbin Avenue 688, Jinhua 321004, China
1 shared publication - Chenqiang Yang
Zhejiang Key Laboratory of Digital Intelligence Monitoring and Restoration of Watershed Environment, College of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, China
1 shared publication - Dehua Xia
School of Environmental Science and Engineering Sun Yat‐sen University Guangzhou 510275 P.R. China
1 shared publication - Dingren Ma
Zhejiang Key Laboratory of Digital Intelligence Monitoring and Restoration of Watershed Environment, College of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, China
1 shared publication
Latest Publications
- Open Access
A High-Performance and Interpretable pKa Prediction Framework Integrating Count-Based Fingerprints and Ensemble Learning
The acid dissociation constant (pKa) is a fundamental parameter governing the environmental fate of organic compounds. Accurate pKa prediction remains challenging, as traditional binary Morgan fingerprints (B-MF) fail to capture stoichiometric information critical for modeling substituent effects. This study developed an interpretable machine learning framework for pKa prediction by integrating count-based Morgan fingerprints (C-MF) with ensemble algorithms. Through systematic comparison across four algorithms (Catboost, XGBoost, GBDT, RF), C-MF consistently outperformed B-MF due to its ability to quantify functional group multiplicity. Subsequent SHAP-based recursive feature elimination (SHAP-RFE) optimized the model, identifying Catboost with only 81 features as the optimal architecture, achieving a test-set R2 of 0.890 and RMSE of 1.026. SHAP analysis revealed that the model’s decisions are driven by chemically intuitive features, forming a hierarchical framework where primary ionizable sites set the baseline pKa and electronic modifiers fine-tune it. The applicability domain, defined using the ADSAL method, yielded high-confidence predictions (R2 = 0.926). External validation on an independent open-source dataset containing 6876 acidic compounds, combined with results from ADSAL application domain characterization, enabled accurate pKa prediction for 390 compounds within the application domain (R2 = 0.890, RMSE = 0.942). This further confirms the model’s strong generalizability. This work provides a robust and generalizable tool for high-performance pKa prediction, with significant potential for applications in environmental risk assessment.
Open AccessA High-Performance and Interpretable pKa Prediction Framework Integrating Count-Based Fingerprints and Ensemble Learning
The acid dissociation constant (pKa) is a fundamental parameter governing the environmental fate of organic compounds. Accurate pKa prediction remains challenging, as traditional binary Morgan fingerprints (B-MF) fail to capture stoichiometric information critical for modeling substituent effects. This study developed an interpretable machine learning framework for pKa prediction by integrating count-based Morgan fingerprints (C-MF) with ensemble algorithms. Through systematic comparison across four algorithms (Catboost, XGBoost, GBDT, RF), C-MF consistently outperformed B-MF due to its ability to quantify functional group multiplicity. Subsequent SHAP-based recursive feature elimination (SHAP-RFE) optimized the model, identifying Catboost with only 81 features as the optimal architecture, achieving a test-set R2 of 0.890 and RMSE of 1.026. SHAP analysis revealed that the model’s decisions are driven by chemically intuitive features, forming a hierarchical framework where primary ionizable sites set the baseline pKa and electronic modifiers fine-tune it. The applicability domain, defined using the ADSAL method, yielded high-confidence predictions (R2 = 0.926). External validation on an independent open-source dataset containing 6876 acidic compounds, combined with results from ADSAL application domain characterization, enabled accurate pKa prediction for 390 compounds within the application domain (R2 = 0.890, RMSE = 0.942). This further confirms the model’s strong generalizability. This work provides a robust and generalizable tool for high-performance pKa prediction, with significant potential for applications in environmental risk assessment.
- Open Access
Chlorination of Aromatic Amino Acids: Elucidating Disinfection Byproducts, Reaction Kinetics, and Influence Factors
In the face of ongoing water pollution challenges, the intricate interplay between dissolved organic matter and disinfectants like chlorine gives rise to potentially harmful disinfection byproducts (DBPs) during water treatment. The exploration of DBP formation originating from amino acids (AA) is a critical focus of global research. Aromatic DBPs, in particular, have garnered considerable attention due to their markedly higher toxicity compared to their aliphatic counterparts. This work seeks to advance the understanding of DBP formation by investigating chlorination disinfection and kinetics using tyrosine (Tyr), phenylalanine (Phe), and tryptophan (Trp) as precursors. Via rigorous experiments, a total of 15 distinct DBPs with accurate molecular structures were successfully identified. The chlorination of all three AAs yielded highly toxic chlorophenylacetonitriles (CPANs), and the disinfectant dosage and pH value of the reaction system potentially influence chlorination kinetics. Notably, Phe exhibited the highest degradation rate compared to Tyr and Trp, at both the CAA:CHOCl ratio of within 1:2 and a wide pH range (6.0 to 9.0). Additionally, a neutral pH environment triggered the maximal reaction rates of the three AAs, while an acidic condition may reduce their reactivity. Overall, this study aims to augment the DBP database and foster a deeper comprehension of the DBP formation and relevant kinetics underlying the chlorination of aromatic AAs.
Open AccessChlorination of Aromatic Amino Acids: Elucidating Disinfection Byproducts, Reaction Kinetics, and Influence Factors
In the face of ongoing water pollution challenges, the intricate interplay between dissolved organic matter and disinfectants like chlorine gives rise to potentially harmful disinfection byproducts (DBPs) during water treatment. The exploration of DBP formation originating from amino acids (AA) is a critical focus of global research. Aromatic DBPs, in particular, have garnered considerable attention due to their markedly higher toxicity compared to their aliphatic counterparts. This work seeks to advance the understanding of DBP formation by investigating chlorination disinfection and kinetics using tyrosine (Tyr), phenylalanine (Phe), and tryptophan (Trp) as precursors. Via rigorous experiments, a total of 15 distinct DBPs with accurate molecular structures were successfully identified. The chlorination of all three AAs yielded highly toxic chlorophenylacetonitriles (CPANs), and the disinfectant dosage and pH value of the reaction system potentially influence chlorination kinetics. Notably, Phe exhibited the highest degradation rate compared to Tyr and Trp, at both the CAA:CHOCl ratio of within 1:2 and a wide pH range (6.0 to 9.0). Additionally, a neutral pH environment triggered the maximal reaction rates of the three AAs, while an acidic condition may reduce their reactivity. Overall, this study aims to augment the DBP database and foster a deeper comprehension of the DBP formation and relevant kinetics underlying the chlorination of aromatic AAs.