Navigating the Maize: Cyclic and conditional computational graphs for molecular simulation

TL;DR

Maize is a workflow manager that enables execution of cyclic and conditional computational graphs in molecular simulation, enhancing flexibility and modularity beyond traditional DAG-based systems.

Contribution

The paper introduces Maize, a novel workflow system capable of handling cyclic and conditional graphs using flow-based programming principles, expanding computational graph expressiveness.

Findings

Successfully applied to drug design active learning tasks

Effectively manages reactivity prediction pipelines

Demonstrates flexibility over traditional DAG systems

Abstract

Many computational chemistry and molecular simulation workflows can be expressed as graphs. This abstraction is useful to modularize and potentially 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. 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. We demonstrate the effectiveness of the tool on a dynamic active learning task in computational drug design, involving the use of a small molecule generative model and an associated scoring system, and on a reactivity prediction pipeline using quantum-chemistry and semiempirical approaches.