Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach

Summary: Here we present EdgeSHAPer, a workflow for explaining graph neural networks by approximating Shapley values using Monte Carlo sampling. In this protocol, we describe steps to execute Python scripts for a chemical dataset from the original publication; however, this approach is also applicab...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Andrea Mastropietro, Giuseppe Pasculli, Jürgen Bajorath
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Elsevier 2022-12-01
Edice:	STAR Protocols
Témata:	Bioinformatics Chemistry Computer sciences
On-line přístup:	http://www.sciencedirect.com/science/article/pii/S2666166722007675
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!