She is an accomplished academician, researcher, and pharmaceutical scientist with over 13 years of experience in pharmaceutical education, research, and industry. She earned her Ph.D. in Pharmaceutical Chemistry from the University of Dhaka and has established a distinguished career integrating teaching excellence with impactful research in pharmaceutical sciences. Currently serving as an Assistant Professor in the Department of Pharmacy at the University of Asia Pacific (UAP), Bangladesh, she is actively involved in teaching undergraduate and postgraduate courses, supervising student research projects, and leading funded research initiatives in phytochemistry, pharmacology, and drug discovery. Prior to joining UAP, she held academic positions at Primeasia University and Manarat International University, where she contributed significantly to curriculum development, laboratory enhancement, academic administration, and student mentoring. Earlier in her career, she gained industrial experience as an R&D Formulation Officer at Incepta Pharmaceuticals Ltd. Her research interests encompass phytochemistry, in vitro pharmacology, medicinal chemistry, and in silico drug design, resulting in more than 39 peer-reviewed publications in reputed international journals, including Molecules, Heliyon, and the Journal of Biomolecular Structure and Dynamics. She has received prestigious recognitions such as the National Science and Technology (NST) Ph.D. Fellowship and the University of Dhaka Ph.D. Scholarship. As Principal Investigator, she currently leads an IRID-funded project on the phytochemical and pharmacological evaluation of Atalantia kwangtungensis for drug discovery. She actively serves as a reviewer for international scientific journals and is proficient in molecular modeling, computational chemistry, scientific writing, and research publication management. Through her dedication to teaching, research, and innovation, she continues to contribute meaningfully to the advancement of pharmaceutical sciences and the development of future healthcare professionals.

Decoding the Phytochemical Space: Artificial Intelligence in Natural Product Drug Discovery and Formulation Design Objective: This presentation elucidates the transformative role of Artificial Intelligence (AI) in overcoming the traditional bottlenecks of natural product drug discovery (NPDD) and development, a field revitalized by computational advancements. Introduction: Natural products (NPs) are a cornerstone of pharmacotherapy, yet their clinical translation is hindered by the labor-intensive, time-consuming, and costly nature of traditional discovery pipelines. Traditional methods often struggle with the immense chemical complexity of plants, inefficient screening, and the "re-discovery" of known compounds. This presentation explores how AI-driven approaches, including machine learning (ML), deep learning (DL), and generative models, are systematically decoding the phytochemical space to accelerate the development of intelligent phytopharmaceuticals. Methodology and Key Findings: Accelerated Phytochemical Discovery: We demonstrate the power of AI in activity prediction, mechanism inference, and compound prioritization. Techniques such as graph neural networks and tree ensembles are effectively applied to oncology, anti-infective, and anti-inflammatory drug discovery, efficiently navigating the vast chemical space of NPs. Recent studies confirm that AI-assisted drug discovery can generate novel, optimized analogs from parent plant compounds, validated by molecular dynamics and ADMET predictions. Advanced Structural Elucidation: The historically rate-limiting step of characterizing unknown compounds is being revolutionized. We showcase the use of AI-based structure annotation tools (e.g., DeepSAT) and transformer-based models (e.g., NMRMind) to rapidly elucidate planar structures and expand accessible chemical diversity from complex spectral data (NMR, MS). Predictive ADMET Profiling: To address the poor bioavailability and toxicity challenges of phytochemicals, AI-driven in-silico tools are deployed to predict Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties. This allows for the early selection of drug-like candidates with favorable pharmacokinetics, significantly reducing late-stage failures. Multi-Omics Integration: AI is essential for integrating high-throughput multi-omics data (genomics, transcriptomics, proteomics, metabolomics). This systems-level approach enables comprehensive mapping of biosynthetic pathways, identification of biomarkers, and a deeper understanding of complex disease mechanisms, thereby powering precision medicine initiatives. Intelligent Pharmaceutical Manufacturing: The application of AI extends to the industrial scale, optimizing quality control (QC) for herbal products. ML models evaluate complex phytochemical profiles to detect adulteration and ensure batch-to-batch consistency, while AI-powered systems enhance process monitoring and standardization. Proposed Framework (NP-ScreenR): We present a novel, AI-driven workflow (NP-ScreenR) for anticancer drug discovery from natural products. This multi-stage framework integrates AI-powered plant selection, LC-MS/MS profiling, dereplication, molecular representation, and multi-objective ranking to shortlist high-potential candidates for wet-lab validation, creating an active learning loop for continuous model improvement. Conclusion and Future Outlook: AI is not merely an assistive tool but a fundamental paradigm shift in natural product research. By decoding the phytochemical space, we are moving from serendipitous discovery to rational, data-driven design. While challenges such as data quality and model interpretability persist, the convergence of AI, multi-omics, and automation promises to unlock the full therapeutic potential of nature's pharmacy, leading to safer, more effective, and personalized phytopharmaceuticals.