Browse Articles
Discover research articles across all indexed journals
Temperature analysis and ampacity evaluation of HV cable joints based on thermal flow coupling and measurable data
Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics
Abstract This work introduces a hybrid computational approach in which degree-based topological descriptors are harnessed with the aid of advanced regression models and artificial neural networks (ANNs) to predict the crucial physicochemical properties of 17 drugs for the treatment of bladder cancer. Each molecule is assigned a molecular graph, from which a series of topological descriptors such as Zagreb indices, Randic index, Atom Bond Connectivity (ABC), and Symmetric Division Degree (SSD)are computed. These indices are used as input features by various regression models along with linear, cubic, and feedforward ANNs. The performance of the models is analyzed using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination $$(R^2)$$ . ANNs showed the best predictive performance with the $$R^2$$ value achieving 0.99. Moreover, SHAP (SHapley Additive exPlanations) analysis was used to explain the contribution of each descriptor toward the models’ predictions. The findings validate the promise of the combination of graph-theoretic descriptors with the tools of machine learning to achieve solid and interpretable models of molecular property prediction, which hold the potential for drug discovery and optimization in oncologic applications.
Lacticaseibacillus rhamnosus attenuates uremic toxins in patients with nondialysis chronic kidney disease through the anti-inflammatory molecules
How allergens make us cough and wheeze — by poking holes in airway cells
Identifying and evaluating the challenges of geriatric healthcare service provision in Iran: evidence from a mixed-methods study
Author Correction: Adhesive anti-fibrotic interfaces on diverse organs
Flood-prone area mapping using a synergistic approach with swarm intelligence and gradient boosting algorithms
Predicting stunting status among under five children in ethiopia using ensemblemachine learning algorithms
Advancing deep learning for expressive music composition and performance modeling
The ocean's deepest animal ecosystem
A qualitative study on ethical issues related to the use of AI-driven technologies in foreign language learning
My AI chatbot thinks my idea is fundable
Identifying monthly rainfall erosivity patterns using hourly rainfall data across India
Abstract Rainfall erosivity is a key dynamic factor of water erosion estimation, with a significant spatial and temporal variation. This study presents a comprehensive analysis of the spatial patterns and monthly distribution of rainfall erosivity across India, using data from 261 hourly and 2,525 monthly rainfall stations covering the period from 1969 to 2021. In India, monthly rainfall erosivity and related attributes—such as the kinetic energy of erosive rainfall, the number of erosive events, and peak hourly rainfall intensity—have been systematically examined for the first time. Monthly erosivity estimates derived from hourly data were linked with monthly rainfall, enabling a simplified and efficient estimation approach. To predict monthly erosivity based on rainfall, temperature, and topographic variables, we developed and evaluated three modeling approaches: linear regression, a machine learning-based XGBoost model, and an ensemble model. XGBoost outperformed the others, achieving a median coefficient of determination (R2) of 0.97, while the ensemble model also performed well with a median R2 of 0.96. Additionally, a Geographically Weighted Regression (GWR) approach was applied for spatial interpolation, yielding accurate high-resolution erosivity maps with a median R2 of 0.90. The results also demonstrate that erosivity peaks during the summer monsoon months (June to September), with July exhibiting the highest value due to intense rainfall and high kinetic energy. Notably, the analysis revealed that nearly 32% of India experiences monthly erosivity exceeding 2,000 MJ mm ha−1 h−1 month−1 in July alone. In contrast, non-monsoon months showed considerably lower erosivity levels across most of the country. A statistically significant long-term increase was detected in January, with an average rise of +0.86 MJ mm ha−1 h−1 month−1 in total erosivity and + 0.1 mm h−1 in maximum 60-min rainfall intensity annually. While acknowledging certain limitations, this study provides valuable insights into erosive rainfall characteristics, enhances rain-driven erosion assessment, and supports the development of timely and location-specific soil conservation strategies across India.