Exploring Graph Traversal Algorithms in Graph-Based Molecular Generation
Overview
Medical Informatics
Authors
Affiliations
Here, we explore the impact of different graph traversal algorithms on molecular graph generation. We do this by training a graph-based deep molecular generative model to build structures using a node order determined via either a breadth- or depth-first search algorithm. What we observe is that using a breadth-first traversal leads to better coverage of training data features compared to a depth-first traversal. We have quantified these differences using a variety of metrics on a data set of natural products. These metrics include percent validity, molecular coverage, and molecular shape. We also observe that by using either a breadth- or depth-first traversal it is possible to overtrain the generative models, at which point the results with either graph traversal algorithm are identical.
Zhang X, Gao H, Qi Y, Li Y, Wang R Molecules. 2025; 30(1.
PMID: 39795076 PMC: 11721775. DOI: 10.3390/molecules30010018.
The importance of graph databases and graph learning for clinical applications.
Walke D, Micheel D, Schallert K, Muth T, Broneske D, Saake G Database (Oxford). 2023; 2023.
PMID: 37428679 PMC: 10332447. DOI: 10.1093/database/baad045.
Wei R, Khaniya U, Mao J, Liu J, Batista V, Gunner M Photosynth Res. 2022; 156(1):101-112.
PMID: 36307598 DOI: 10.1007/s11120-022-00973-0.
Carbone J, Ghidini A, Romano A, Gentilucci L, Musiani F Molecules. 2022; 27(20).
PMID: 36296477 PMC: 9610523. DOI: 10.3390/molecules27206884.
Thomas M, OBoyle N, Bender A, de Graaf C J Cheminform. 2022; 14(1):68.
PMID: 36192789 PMC: 9531503. DOI: 10.1186/s13321-022-00646-z.