In drug design, compound potency prediction is a popular machine learning application. Graph neural networks (GNNs) predict ligand affinity from graph representations of protein–ligand interactions typically extracted from X-ray structures. Despite some promising findings leading to claims that GNNs can learn details of protein–ligand interactions, such predictions are also controversially viewed. For example, evidence has been presented that GNNs might not learn protein–ligand interactions but memorize ligand and protein training data instead. We have carried out affinity predictions with six GNN architectures on community-standard datasets and rationalized the predictions using explainable artificial intelligence. The results confirm a strong influence of ligand—but not protein—memorization during GNN learning and also show that some GNN architectures increasingly prioritize interaction information for predicting high affinities. Thus, while GNNs do not comprehensively account for protein–ligand interactions and physical reality, depending on the model, they balance ligand memorization with learning of interaction patterns.

Learning characteristics of graph neural networks predicting protein–ligand affinities / Mastropietro, Andrea; Pasculli, Giuseppe; Bajorath, Jürgen. - In: NATURE MACHINE INTELLIGENCE. - ISSN 2522-5839. - (2023). [10.1038/s42256-023-00756-9]

Learning characteristics of graph neural networks predicting protein–ligand affinities

Andrea Mastropietro
Primo
;
Giuseppe Pasculli
Secondo
;
2023

Abstract

In drug design, compound potency prediction is a popular machine learning application. Graph neural networks (GNNs) predict ligand affinity from graph representations of protein–ligand interactions typically extracted from X-ray structures. Despite some promising findings leading to claims that GNNs can learn details of protein–ligand interactions, such predictions are also controversially viewed. For example, evidence has been presented that GNNs might not learn protein–ligand interactions but memorize ligand and protein training data instead. We have carried out affinity predictions with six GNN architectures on community-standard datasets and rationalized the predictions using explainable artificial intelligence. The results confirm a strong influence of ligand—but not protein—memorization during GNN learning and also show that some GNN architectures increasingly prioritize interaction information for predicting high affinities. Thus, while GNNs do not comprehensively account for protein–ligand interactions and physical reality, depending on the model, they balance ligand memorization with learning of interaction patterns.
2023
chemoinformatics; graph neural networks; explainable artificial intelligence
01 Pubblicazione su rivista::01a Articolo in rivista
Learning characteristics of graph neural networks predicting protein–ligand affinities / Mastropietro, Andrea; Pasculli, Giuseppe; Bajorath, Jürgen. - In: NATURE MACHINE INTELLIGENCE. - ISSN 2522-5839. - (2023). [10.1038/s42256-023-00756-9]
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1691854
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 0
social impact