DrugnomeAI is an ensemble machine-learning framework for predicting druggability of candidate drug targets

• Published in: Communications biology Vol. 5; no. 1; p. 1291
• Main Authors: Raies, Arwa, Tulodziecka, Ewa, Stainer, James, Middleton, Lawrence, Dhindsa, Ryan S., Hill, Pamela, Engkvist, Ola, Harper, Andrew R., Petrovski, Slavé, Vitsios, Dimitrios
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 24.11.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/2397; 631/154/555; 631/1647/48; Biology; Biomedical and Life Sciences; Chimeras; Drug Delivery Systems; Genes; Genomes; Humans; Life Sciences; Machine Learning; Monoclonal antibodies; Protein interaction; Proteins; Proteolysis; Software; Stochasticity; Therapeutic targets
• ISSN: 2399-3642; 2399-3642
• DOI: 10.1038/s42003-022-04245-4

The druggability of targets is a crucial consideration in drug target selection. Here, we adopt a stochastic semi-supervised ML framework to develop DrugnomeAI, which estimates the druggability likelihood for every protein-coding gene in the human exome. DrugnomeAI integrates gene-level properties from 15 sources resulting in 324 features. The tool generates exome-wide predictions based on labelled sets of known drug targets (median AUC: 0.97), highlighting features from protein-protein interaction networks as top predictors. DrugnomeAI provides generic as well as specialised models stratified by disease type or drug therapeutic modality. The top-ranking DrugnomeAI genes were significantly enriched for genes previously selected for clinical development programs ( p value < 1 × 10 −308 ) and for genes achieving genome-wide significance in phenome-wide association studies of 450 K UK Biobank exomes for binary ( p value = 1.7 × 10 −5 ) and quantitative traits ( p value = 1.6 × 10 −7 ). We accompany our method with a web application ( http://drugnomeai.public.cgr.astrazeneca.com ) to visualise the druggability predictions and the key features that define gene druggability, per disease type and modality. DrugnomeAI predicts the druggability likelihood for every protein-coding gene in the human exome by small molecules, monoclonal antibodies, and proteolysis-targeting chimeras (PROTACs).