AI-Driven Spectroscopy Automation & Biochemical Toxicity Analysis

A cross-disciplinary research project conducted at the Indian Institute of Technology (IIT), Indore, that bridges the gap between bench-top wet-lab research and automated, AI-driven data processing. This project focuses on evaluating the biochemical toxic effects of metallic nanoparticles on microalgal growth while building computer vision automation algorithms to streamline analysis.

📊 Research Findings & Key Results

• Longitudinal Toxicity Tracking: Monitored and evaluated biochemical toxicity profiles across 24 distinct testing units over a rigorous 28-day testing cycle.
• Dose-Dependent Observations: Quantified a direct, dose-dependent decrease in microalgal cell growth and photosynthetic activity caused by exposure to metallic nanoparticles.

🛠️ System Architecture & Automation

• AI-Driven Characterization: Engineered an automated algorithm utilizing Computer Vision principles to parse, interpret, and streamline structural spectroscopy data (XRD, UV-Vis, Raman, FTIR).
• High-Throughput Processing: Designed to eliminate manual plotting and analysis bottlenecks, translating structural material properties into biological impact metrics automatically.

🧰 Analytical Tools & Techniques

• Language/Frameworks: Python, OpenCV, NumPy, SciPy
• Laboratory Instrumentation & Data Profiles: X-ray Diffraction (XRD), UV-Vis Spectroscopy, Raman Spectroscopy, Fourier-Transform Infrared Spectroscopy (FTIR), Zeta Potential analysis