I enjoy making things. Here are a selection of projects that I have worked on over the years.
An open-access registry, selection wizard, and interactive benchmark dashboard for chemical and biological vector representations. Indexes foundation models across five modalities: small molecules, proteins, complexes, chemical reactions, and nucleic acids, with a programmatic JSON API.
An interactive, visual, first-principles web guide to computer-aided drug design. Covers 18 modules across ligand-receptor binding, molecular docking, pharmacophore modeling, QSAR, molecular dynamics, generative design, and ADMET prediction, each with hands-on browser playgrounds.
A flexible Python framework for building, validating, and applying gradient boosting-based QSAR models, with built-in support for molecular fingerprints, hyperparameter optimization, and model interpretation.
An automated Python script for structure-based virtual screening with AutoDock Vina, handling batch ligand preparation, parallel docking, and result parsing for large compound libraries.
A Jupyter Notebook pipeline for building QSAR classification models for bioactivity prediction, supporting descriptor calculation, feature selection, model training, and applicability domain assessment.
A machine learning ensemble model for predicting drug blood-brain barrier permeability, deployed as an interactive Streamlit web application for rapid compound screening.
