Pooja Chandrashekar

Quality Assurance Engineer with background in biotechnology and extensive experience in utilizing computational techniques for drug discovery and machine learning algorithms for disease diagnosis. Proficient in molecular docking and data analysis, with a proven track record of achieving high accuracy in diagnostic models. Passionate about leveraging technology to improve healthcare outcomes and committed to continuous learning and professional development.

Silico Screening of Compounds for Alzheimer’s Diseases

Overview - This project leverages advanced computational techniques and software to streamline the drug discovery process, focusing on a plant-based compound and its potential therapeutic applications.

• Involved using a plant-based compound Karanjin and modifying it to better target the disease.
• Screen the potential chemical drug from millions of compounds for efficient validation and to predict the predominant binding mode of ligand with a protein of known 3D structure.
• Molecular docking to identify molecules that are most likely binding to a specific protein target and affect the protein's activity.

Tool - Auto dock software for molecular docking 

Machine Learning to Detect Parkinson’s Diseases

Overview - This project leverages advanced machine learning algorithms to diagnose Parkinson's disease with high accuracy, providing a reliable tool for healthcare professionals and a valuable database for ongoing and future treatment efforts.

• Used machine learning to classify audio signals feature dataset to diagnose parkinsons.
• Machine Learning algorithms for data analysis achieved the mean accuracy of more than 95% which shows remarkable rectification and makes this system more reliable.
• Database which can be used as past record and will help in future for treatment and thus contributing in easier health management.

Tool - Google Colab Python

• Entrepreneurship university of Illinois at Urbana champaign - Coursera
• Algae biotechnology university of San Diego - Coursera