Scientific Overview
ATOM Modeling Pipeline (AMPL)
An open-source, modular, extensible software pipeline for building and sharing models to advance in silico drug discovery
The ATOM Modeling PipeLine (AMPL) extends the functionality of DeepChem and supports an array of machine learning and molecular featurization tools. AMPL is an end-to-end data-driven modeling pipeline to generate machine learning models that can predict key safety and pharmacokinetic-relevant parameters. AMPL has been benchmarked on a large collection of pharmaceutical datasets covering a wide range of parameters. The AMPL manuscript was accepted for publication in American Chemical Society and it is available on GitHub.
Introducing the AMPL Tutorial Series
Our tutorial series is designed to help our user community take a hands-on approach to employing AMPL through step-by-step guidance. Whether you prefer reading documentation or watching walkthroughs, we offer both written and YouTube video tutorials to support different learning styles.
These tutorials assume you are an intermediate Python user or new to machine learning, and are intended to help you build a foundational framework for doing meaningful work.
The series walks you through an end-to-end machine learning pipeline for predicting chemical properties. We have created easy to follow tutorials that walk through the steps necessary to install AMPL, curate a dataset, effectively train and evaluate a machine learning model, and use that model to make predictions.
Our tutorials are easy to follow and built to support practical, real-world applications.
Explore the written tutorials or the video tutorials.
Current Research Projects
Scientists at ATOM are tackling a wide range of challenges in drug design. Read our recent abstracts to learn more about our ongoing projects.
