Integrating Machine Learning and Nano-QSAR Models to Predict the Oxidative Stress Potential Caused by Single and Mixed Carbon Nanomaterials in Algal Cells

Environmental Toxicology and Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 7, 2025

Abstract In silico methods are increasingly important in predicting the ecotoxicity of engineered nanomaterials (ENMs), encompassing both individual and mixture toxicity predictions. It is widely recognized that ENMs trigger oxidative stress effects by generating intracellular reactive oxygen species (ROS), serving as a key mechanism their cytotoxicity studies. However, existing still face significant challenges induced ENMs. Herein, we utilized laboratory-derived data machine learning to develop quantitative nanostructure-activity relationship (nano-QSAR) classification regression models, aiming predict five carbon (fullerene, graphene, graphene oxide, single-walled nanotubes, multi-walled nanotubes) binary mixtures on Scenedesmus obliquus cells. We constructed nano-QSAR models combining zeta potential (ζP) with C4.5 decision tree, support vector machine, artificial neural network, naive Bayes, K-nearest neighbor algorithms. Moreover, three integrating features including ζP, hydrodynamic diameter (DH), specific surface area (SSA) logistic regression, random forest, Adaboost The Accuracy, Recall, Precision harmonic mean Recall (F1-score) values these were all higher than 0.600, indicating an excellent performance distinguishing whether CNMs have generate ROS. addition, using DH, SSA descriptors, combined tree forest gradient boosting, algorithm, successfully four applicable application domains (all training testing points lie within 95% confidence intervals), goodness-of-fit (Rtrain2 ≥ 0.850), robustness (cross-validation R2 0.650) well predictive power (Rtest2 0.610). method developed would establish fundamental basis for more precise evaluations ecological risks posed materials from mechanistic standpoint.

Language: Английский

---

Predicting the dissolution of metal-based nanoparticles by means of QSPRs and the effect of data augmentation

NanoImpact, Journal Year: 2025, Volume and Issue: unknown, P. 100547 - 100547

Published: Feb. 1, 2025

Particle dissolution is a critical process in the environmental fate assessment of metal-based nanoparticles (MNPs). Numerous attempts have been made previously to adequately quantify (kinetics), however, existing data and models are generally limited few nanomaterials or specific time points. Hence, they only capture phases process. This study aimed develop Quantitative Structure-Property Relationship (QSPR) model predict ion release (in %) MNPs for different points water chemistry conditions. Furthermore, many machine learning frequently plagued by lack recently augmentation has suggested as method mitigate this issue. Therefore, we also investigated effects on QSPRs. Following collection from literature, QSPR were generated results indicate with adequate performance (R2 > 0.7). Results demonstrated significant improvements increasing amounts applied augmentation. However, deeper evaluation highlighted that can lead misleading overoptimistic evaluation. Thus, proper necessary when evaluating Variable importance analysis revealed "initial concentration" features related size shape most factors The predictive here MNP improve nanomaterial testing efficiency guide experimental design.

Language: Английский

---

Applications of conceptual density functional theory in reference to quantitative structure–activity / property relationship

Molecular Physics, Journal Year: 2024, Volume and Issue: 122(23)

Published: March 22, 2024

To predict the biological effects of chemical compounds based on mathematical and statistical relationships, quantitative structure–activity relationship (QSAR) approach is used. Based molecular characteristics diverse substances, Quantitative Structure–Property Relationship (QSPR) techniques estimate physiochemical attributes whereas Structure Toxicity (QSTR) used as a link between structure species its toxicity. These ligand-based computational screening methods offer cost-effective replacement for laboratory-based procedures. Different QSTR models are established to understand activities related Density Functional Theory (DFT) ab-initio examine external acute toxicity using Quantum Chemical (QC) descriptors electron correlation contribution. Conceptual (CDFT) global local have wide applications in analysing various physical species. The like hardness, electronegativity, electrophilicity index, HOMO–LUMO energy, enthalpy found reliable model terms available experimental data. Various through Multi Linear Regression (MLR) analysis which links calculated with their activities. In this review, CDFT-based descriptors, described detail QSAR / QSPR/ studies.

Language: Английский

---

Application of Machine Learning in Nanotoxicology: A Critical Review and Perspective

Environmental Science & Technology, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 7, 2024

The massive production and application of nanomaterials (NMs) have raised concerns about the potential adverse effects NMs on human health environment. Evaluating by laboratory methods is expensive, time-consuming, often fails to keep pace with invention new materials. Therefore,

Language: Английский

---

Predicting the Aquatic Toxicity of Pharmaceutical and Personal Care Products: A Multitasking Modeling Approach

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(3), P. 1246 - 1246

Published: Jan. 26, 2025

Pharmaceutical and Personal Care Products (PPCPs) have become a significant environmental concern due to their widespread use, persistence, potential toxicity, often referred as forever chemicals. This study aims develop validate robust in silico models for predicting the aquatic toxicity of PPCPs. To do so, we resorted ECOTOX database employed Python-based tool prepare curate dataset. Multitasking Quantitative Structure–Toxicity Relationship (mt-QSTR) were then developed employing Box–Jenkins moving average approach, incorporating both linear non-linear frameworks based on diverse feature selection algorithms machine learning techniques. further improve external predictivity, consensus modeling approach was also implemented. The most accurate model achieved an overall predictive accuracy exceeding 85%, providing valuable insights into structural features influencing PPCP toxicity. Key factors contributing high included lipophilicity, mass density, molecular mass, reduced electronegativity. work offers foundation designing safer PPCPs with impact, aligning sustainable chemical development goals.

Language: Английский

---

Development of a deep neural network model based on high throughput screening data for predicting synergistic estrogenic activity of binary mixtures for consumer products

Journal of Hazardous Materials, Journal Year: 2025, Volume and Issue: 489, P. 137650 - 137650

Published: Feb. 22, 2025

Language: Английский

---

Assessing the Toxicity of Quantum Dots in Healthy and Tumoral Cells with ProtoNANO, a Platform of Nano-QSAR Models to Predict the Toxicity of Inorganic Nanomaterials

Challenges and advances in computational chemistry and physics, Journal Year: 2025, Volume and Issue: unknown, P. 109 - 132

Published: Jan. 1, 2025

Language: Английский

---

Machine learning reshapes the paradigm of nanomedicine research

Acta Pharmaceutica Sinica B, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Language: Английский

---

Predicting the Time-Dependent Toxicities of Binary Mixtures of Five Antibiotics to Vibrio qinghaiensis sp.-Q67 Based on the QSAR Model

Environment & Health, Journal Year: 2024, Volume and Issue: 2(7), P. 465 - 473

Published: April 17, 2024

Antibiotics may be exposed in a mixed state natural environments. The toxicity of antibiotic mixtures exhibits time-dependent characteristics, and data on the is also relatively lacking. In this study, toxicities 45 binary composed five antibiotics were investigated against Vibrio qinghaiensis sp.-Q67 (Q67) at multiple exposure times (4, 6, 8, 10, 12 h). Quantitative structure–activity relationship (QSAR) models developed for predicting mixtures. results showed that best QSAR presented coefficient determination (R2) (0.818–0.913) explained variance prediction leave-one-out (Q2LOO) (0.781–0.894) predictive ability (Q2F1, Q2F2, Q2F3 > 0.682, concordance correlation 0.859). R2 values outperformed (0.628–0.810) conventional concentration addition (0.654–0.792) independent action models. Furthermore, higher Q2LOO 4 h compared to other times. Specifically, model 30% effective (EC30) had 0.902 0.883, while 50% (EC50) 0.913 0.894. CATS2D_04_DP descriptor was found most dominant negatively correlated factor influencing Q67 nine over reduction number DP pharmacophore point pairs with topological distance represented molecules primary cause rise Q67.

Language: Английский

---

Prediction of Dynamic Toxicity of Nanoparticles Using Machine Learning

Toxics, Journal Year: 2024, Volume and Issue: 12(10), P. 750 - 750

Published: Oct. 15, 2024

Predicting the toxicity of nanoparticles plays an important role in biomedical nanotechnologies, particular creation new drugs. Safety analysis can identify potentially harmful effects on living organisms and environment. Advanced machine learning models are used to predict a nutrient solution. In this article, we performed comparative current state research field nanoparticle using methods; trained regression model for predicting quantitative depending their concentration solution at fixed point time with achieved metrics values MSE = 2.19 RMSE 1.48; multi-class classification class Accuracy 0.9756, Recall 0.9623, F1-Score 0.9640, Log Loss 0.1855. As result analysis, concluded good predictive ability models. The optimal dosages under study were determined as follows: ZnO 9.5 × 10

Language: Английский

---