If you have questions for Thomas, please go to the forum and post them there. The category will be open until 12 September 2023.


Many computational scientific workflows can be expressed as graphs. This abstraction is useful to modularize and reuse existing components, as well as provide parallelization and ease reproducibility. Existing tools represent the computation as a directed acyclic graph (DAG), thus allowing efficient execution by parallelization of concurrent branches. These systems can however generally not express cyclic and conditional workflows, i.e., control flow. We therefore developed Maize, a workflow manager for cyclic and conditional graphs based on the principles of flow-based programming. By running each node of the graph concurrently in separate processes and allowing communication at any time through dedicated inter-node channels, arbitrary graph structures can be executed. In this webinar, I will give an introduction to Maize and demonstrate solutions to common problems in computational chemistry and early-stage drug discovery projects, such as de-novo small molecule generation, docking, and their combination in an active learning pipeline.


Thomas Löhr is currently a Senior Scientist in the Molecular AI group at AstraZeneca, working on combining physics-based approaches to protein-ligand binding with generative machine learning models. He previously completed a PhD in the Centre for Misfolding Diseases at the University of Cambridge, working on computational methods to study the kinetics and thermodynamics of disordered proteins. He has also contributed method developments to the open-source PLUMED project for enhancing molecular dynamics simulations.