Researcher - Data Curation for Machine Learning in Drug Discovery
As a researcher, I developed and implemented machine learning models for drug discovery projects, which required intensive labeling and classification of molecular and chemical data sets. The process involved curating, annotating, and preparing scientific data for AI model training and validation. I collaborated in AI-based workflows for pharmacophore modeling, feature extraction, and unsupervised learning to identify and label relevant therapeutic candidates. • Labeled complex molecular data including compound structures and protein-ligand interactions for classification tasks. • Used internal/proprietary Python pipelines and Linux environments for scientific data annotation and model training. • Supported the annotation of datasets for both supervised and unsupervised learning models in drug discovery. • Participated in dataset construction and quality assurance for AI model effectiveness.