A machine learning method for the identification and characterization of novel COVID-19 drug targets

Abstract

In addition to vaccines, the World Health Organization sees novel medications as an urgent matter to fight the ongoing COVID-19 pandemic. One possible strategy is to identify target proteins, for which a perturbation by an existing compound is likely to benefit COVID-19 patients. In order to contribute to this effort, we present GuiltyTargets-COVID-19 ( https://guiltytargets-covid.eu/ ), a machine learning supported web tool to identify novel candidate drug targets. Using six bulk and three single cell RNA-Seq datasets, together with a lung tissue specific protein-protein interaction network, we demonstrate that GuiltyTargets-COVID-19 is capable of (i) prioritizing meaningful target candidates and assessing their druggability, (ii) unraveling their linkage to known disease mechanisms, (iii) mapping ligands from the ChEMBL database to the identified targets, and (iv) pointing out potential side effects in the case that the mapped ligands correspond to approved drugs. Our example analyses identified 4 potential drug targets from the datasets: AKT3 from both the bulk and single cell RNA-Seq data as well as AKT2, MLKL, and MAPK11 in the single cell experiments. Altogether, we believe that our web tool will facilitate future target identification and drug development for COVID-19, notably in a cell type and tissue specific manner.

Figure 1

Screenshot of the GuiltyTargets-COVID-19 web application available at https://guiltytargets-covid.eu/.

Figure 2

First degree neighbors of the (a) AKT3 and (b) PIK3CA proteins. Nodes are colored according to their associations: light orange means no virus or human association was found, dark orange indicates only human association, purple signifies viral association, and and dark blue nodes are proteins with associations to both viral mechanisms and human processes. The neighboring proteins and their associations for AKT3 and PIK3CA are outlined in Supplementary Data S1 and S2, respectively.

Figure 3

Venn diagram of the number of prioritized targets from the bulk RNA-Seq datasets.

Figure 4

Screenshot of part of the adverse effect network for the AKT3 protein.

Figure 5

Idea behind GuiltyTargets: information about differentially expressed genes and putative COVID-19 drug targets are mapped to a constructed tissue specific PPI network. Subsequently, GuiltyTargets applies network representation learning to embed the attributed graph into an Euclidean space. This positive-unlabeled model is used to rank unlabeled proteins with respect to their likelihood of being COVID-19 drug targets.

Figure 6

Ranking performance of GuiltyTargets measured by the AUC within a 10 times repeated, stratified 5-fold cross-validation. The boxplots show the distribution of the AUC over the 10 cross-validation repetitions. Top: performances on bulk RNA-Seq. Bottom: performances on single cell RNA-Seq.