A novel preclinical secondary pharmacology resource illuminates target-adverse drug reaction associations of marketed drugs

Sutherland, Jeffrey J.; Yonchev, Dimitar; Fekete, Alexander; Urbán, László

doi:10.1101/2023.01.31.526400

Cited by 1 publication

(1 citation statement)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other methods rely on structure-based representations of the protein-compound complex, taking solved structures as input for machine-learning algorithms [16][17][18][19]. Accumulation of high-quality data derived from biochemical and biophysical screening [20], besides novel algorithms, has empowered such methods, although the underlying limitation, namely only a limited number of complex structures is solved, remains. Nevertheless, screening procedures are progressively being complemented or replaced by modelling procedures [21,22].…”

Section: Introductionmentioning

confidence: 99%

G-PLIP: Knowledge graph neural network for structure-free protein-ligand bioactivity prediction

Crouzet,

Lieberherr,

Atz

et al. 2023

Preprint

View full text Add to dashboard Cite

Protein-ligand interaction (PLI) shapes efficacy and safety profiles of small-molecule drugs. Most existing methods rely on resource-intensive computation to predict PLI based on structural information. Here we show that a light-weight graph neural network (GNN), trained with quantitative PLIs of a small number of proteins and ligands, is able to predict the strength of unseen PLIs. The model has no direct access to structural information of protein-ligand complexes. Instead, the predictive power is provided by encoded knowledge of proteins and ligands, including primary protein sequence, gene expression, protein-protein interaction network, and structural similarities between ligands. Our novel model performs competitively with or better than structure-aware models. Our results suggest that existing PLI-prediction methods may be further improved by using omics data and representation learning techniques that embed biological and chemical knowledge.

show abstract