VISIPEDIA-Automated Web-based System for Chemical Compound Analysis

The analysis of chemical compounds plays a crucial role in fields ranging from education to drug discovery, yet accessing detailed molecular information typically requires specialized software and domain expertise. This paper introduces VISI-PEDIA, an automated, web-based system designed to simplify chemical compound analysis by focusing on essential molecular attributes. VISIPEDIA combines deep learning, image processing, and web technologies to provide a user-friendly, accessible tool for molecular data retrieval. By integrating the Flask web framework with RDKit, a cheminformatics library, VISIPEDIA enables users to input compound names and receive immediate, structured data output, including molecular formula, chemical weight, number of rings, and IUPAC (International Union of Pure and Applied Chemistry) name. Testing on 50 benchmark compounds showed 75 % accuracy in SMILES conversion and property extraction. Additionally, VISIPEDIA incorporates image-based molecular recognition powered by deep learning models, including Convolutional Neural Networks (CNNs) and ResNet18, to support structure analysis from molecular images, achieving 92.7% classification accuracy. This hybrid approach allows the platform to process and interpret both text-and image-based chemical data, making it versatile for educational and research applications. User feedback from 20 participants highlighted system usability and response time, affirming its utility. The system’s design emphasizes accessibility, empowering students, educators, and researchers to engage in molecular analysis without requiring extensive background knowledge. Potential applications of VISIPEDIA span academic research, chemistry education, and preliminary drug discovery research, establishing it as a scalable and impactful solution in the field.