School of Science & Technology (SST)

Permanent URI for this communityhttp://10.0.2.71:4000/handle/123456789/439

Browse

Start date: 2026Subject: search.filters.subject.Printing

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    An Explainable 3D Graph-Transformer Framework for Hepatotoxicity Prediction with Scaffold-Aware Evaluation
    (IEEE, 2026) Mishra, Suraj; Kanauzia, Rohit et al.
    Drug-induced hepatotoxicity continues to be a major factor in post-market removal and late-stage drug attrition. While graph neural networks have shown promise in predicting chemical toxicity, many existing approaches rely on random data splits and offer limited interpretability, thereby reducing their reliability in real-world screening scenarios. This study presents an explainable 3D graph-Transformer framework for hepatotoxicity prediction that integrates geometric inductive bias, rigorous scaffold-based evaluation, and multiple complementary explainability approaches. Molecular structures are encoded, and spatial linkages are captured using a 3D-equivariant graph neural network. Next, a graph-level Transformer is used to model long-range atomic interactions. Five-fold scaffold cross-validation is used to assess the model on a curated hepatotoxicity dataset of 8,538 molecules obtained from Tox21 liver-related assays. We use three different explainability techniques to guarantee transparency: atom-level perturbation analysis, integrated gradients, and transformer attention visualization. Experimental results show that the proposed framework achieves 91.8% accuracy with perfect recall on the evaluated splits, while generating explanations that are chemically significant and consistent with recognized hepatotoxic substructures. The suggested method is appropriate for early-stage toxicity screening and decision support because it combines multi-view explainability with robust out-of-distribution evaluation.
  • No Thumbnail Available
    Item
    Leveraging Machine Learning in Digital Payroll and Payment Playforms Redifining HR Practices in the FinTech Era
    (IEEE, 2026) Rao, P.Venkateswara; Chhabra, Gunjan et al.
    The objective of this research paper is to explore how Machine Learning (ML) could potentially be used to transform the HR process within Digital Payroll & Payment Platforms in today's Fintech industry. We did this through development of a Reinforcement Learning (RL) model in a simulated environment, utilizing artificial data to measure various Performance Metrics including Efficiency, Fairness, Fraud Prevention and Employee Satisfaction. Our results indicated that our AI-enabled model outperformed the AI-free Baseline Model in terms of Reward Convergence, Satisfaction Index, Transaction Success Rate with Fraud Attempted, and Scalable Adaptability as the Workforce Size increased. Additionally, we conducted Ablation Testing for Features, which confirmed the importance of engineered features to produce desired outcomes. These results clearly indicate that Intelligent Payroll Platforms have the potential to reduce employee stress, increase employee trust and provide Human Resource Managers with tools to create Financial Operations that are both Sustainable and Employee-Centered.