Modeling Multi-Step Scientific Processes with Graph Transformer Networks
This addresses the challenge of efficiently exploring high-dimensional parameter spaces in experimental research, though it is incremental as it builds on existing graph learning methods.
This work tackled the problem of predicting multi-step experimental outcomes in material science, chemistry, and biology by using graph learning, specifically a graph transformer network, which outperformed linear models in scenarios with hidden interactions and sequence-dependent features, achieving better performance on real-world data for predicting spectral properties.
This work presents the use of graph learning for the prediction of multi-step experimental outcomes for applications across experimental research, including material science, chemistry, and biology. The viability of geometric learning for regression tasks was benchmarked against a collection of linear models through a combination of simulated and real-world data training studies. First, a selection of five arbitrarily designed multi-step surrogate functions were developed to reflect various features commonly found within experimental processes. A graph transformer network outperformed all tested linear models in scenarios that featured hidden interactions between process steps and sequence dependent features, while retaining equivalent performance in sequence agnostic scenarios. Then, a similar comparison was applied to real-world literature data on algorithm guided colloidal atomic layer deposition. Using the complete reaction sequence as training data, the graph neural network outperformed all linear models in predicting the three spectral properties for most training set sizes. Further implementation of graph neural networks and geometric representation of scientific processes for the prediction of experiment outcomes could lead to algorithm driven navigation of higher dimension parameter spaces and efficient exploration of more dynamic systems.