Browse
Recent Submissions
Item Stochastic Differential Equation-Driven GANs for Simulating Variable Drug Absorption in the Gastrointestinal Tract(2026-05-26) Dhivya S.; Divya M K; Gandhiraja RVariability in drug absorption within the gastrointestinal (GI) tract remains a major challenge in pharmacokinetic modeling and oral drug development. Traditional compartmental models often fail to capture stochastic fluctuations due to gastric emptying, pH variations, and motility patterns. This paper proposes a novel framework combining Stochastic Differential Equations (SDEs) with Generative Adversarial Networks (GANs) — termed SDE-GAN — to simulate realistic, time-varying drug absorption profiles. The SDE component models the inherent randomness of GI physiology, while the GAN refines generated trajectories to match empirical absorption data. Using in vitro and in vivo absorption datasets, we demonstrate that SDE-GAN outperforms deterministic models and vanilla GANs in terms of distributional accuracy (p < 0.05, Kolmogorov– Smirnov test). Our results indicate improved simulation of inter- and intra-subject variability, with potential applications in virtual bioequivalence trials.Item Utilizing 2d And 3d Convolutional Neural Networks For Predicting Protein-Ligand Binding Affinity(2026-05-26) Supriya A; Munilakshmi B; Nishchitha Bhe accurate prediction of protein-ligand binding affinity remains a cornerstone challenge in computational drug discovery, directly influencing hit identification, lead optimization, and compound prioritization. Traditional experimental methods such as isothermal titration calorimetry and surface plasmon resonance, while accurate, are hindered by high costs and low throughput. This paper presents a comprehensive investigation of 2D and 3D Convolutional Neural Network (CNN) architectures for protein-ligand binding affinity prediction. We systematically evaluate multiple CNN-based approaches, including 2D CNNs operating on molecular graphs and ligand images, 3D CNNs processing voxelized protein-ligand complexes, and hybrid architectures combining both paradigms. Using the PDBbind v2020 dataset comprising 19,443 protein-ligand complexes and the CASF-2016 core set for benchmarking, we demonstrate that 3D-CNN models achieve superior performance with Pearson correlation coefficients of 0.82-0.86 and RMSE values of 1.27-1.00 on the CASF-2016 benchmark. Hybrid attention-based architectures such as HAC-Net and CGDeepAff further improve performance, achieving Pearson's R of 0.846-0.855 and Spearman's ρ of 0.843-0.861. Our results reveal that 3D spatial representations capture critical geometric complementarity features that 2D approaches miss, while 2D methods offer superior computational efficiency for high-throughput screening. We also identify key challenges including data quality limitations, model interpretability concerns, and generalization to novel protein targets. This paper concludes by outlining future research directions, emphasizing the potential of multi-modal architectures, attention mechanisms, and geometric deep learning for advancing binding affinity prediction toward clinical implementationItem Kuvempu natakadhali jyathyathita parikalpana(Seshadripuram Research Foundation, 2026) Sowmya, H. L.Item Explainable Ai for Environmental Decision Support: Interpreting Deep Learning Models In Climate Science(2025-12-30) Vengatesh T; Kishor Barasu Bhangale; Ronicca M.Deep learning (DL) models have demonstrated high accuracy in climate science applications but suffer from "blackbox" opacity, hindering their adoption in environmental decision-making. This research bridges this gap by integrating Explainable AI (XAI) techniques with DL models to enhance transparency in climate predictions. Using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture, we forecast regional temperature anomalies and interpret outputs via SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model- agnostic Explanations). Our methodology is validated on ERA5 reanalysis data (1980–2025), achieving a prediction RMSE of 0.86°C. XAI analysis reveals that oceanic heat fluxes and atmospheric pressure patterns are critical drivers of anomalies. The framework empowers policymakers with actionable insights, ensuring DL models are both accurate and trustworthy for climate action.