DeepDrug as an expert guided and AI driven drug repurposing methodology for selecting the lead combination of drugs for Alzheimer's disease

Abstract

Alzheimer's Disease (AD) significantly aggravates human dignity and quality of life. While newly approved amyloid immunotherapy has been reported, effective AD drugs remain to be identified. Here, we propose a novel AI-driven drug-repurposing method, DeepDrug, to identify a lead combination of approved drugs to treat AD patients. DeepDrug advances drug-repurposing methodology in four aspects. Firstly, it incorporates expert knowledge to extend candidate targets to include long genes, immunological and aging pathways, and somatic mutation markers that are associated with AD. Secondly, it incorporates a signed directed heterogeneous biomedical graph encompassing a rich set of nodes and edges, and node/edge weighting to capture crucial pathways associated with AD. Thirdly, it encodes the weighted biomedical graph through a Graph Neural Network into a new embedding space to capture the granular relationships across different nodes. Fourthly, it systematically selects the high-order drug combinations via diminishing return-based thresholds. A five-drug lead combination, consisting of Tofacitinib, Niraparib, Baricitinib, Empagliflozin, and Doxercalciferol, has been selected from the top drug candidates based on DeepDrug scores to achieve the maximum synergistic effect. These five drugs target neuroinflammation, mitochondrial dysfunction, and glucose metabolism, which are all related to AD pathology. DeepDrug offers a novel AI-and-big-data, expert-guided mechanism for new drug combination discovery and drug-repurposing across AD and other neuro-degenerative diseases, with immediate clinical applications.

Keywords: Aging pathways; Alzheimer’s Disease; DeepDrug; Directed biomedical graph; Expert-led AI drug-repurposing; Graph neural network; Immunological; Inflammation; Lead combination of AD drugs; Long genes; Neuro-degenerative; Pathway convergence; Somatic and germline mutations.

Fig. 1

DeepDrug Framework and Novelties.

Fig. 2

Box Plot of Drug Combination Scores. This figure shows the scores of all drug combinations, from two-drug combinations up to six-drug combinations, grouped by the number of drugs in the drug combination, including the minimum, 25th percentile, median, 75th percentile, and maximum scores. The leading drug combination has been selected from the top five-drug combinations, which is the optimal number of drugs in drug combinations based on the cut-off point where the maximum score has been reached.

Fig. 3

DeepDrug Prediction of the Five-drug Combination in the Embedding Space.

Fig. 4

DeepDrug Prediction of Five-drug Combinations and Drug-target-gene Interaction Network.

Fig. 5

Expert-guided AI-driven DeepDrug Framework.

Fig. 6

A Simplified Version of Signed Directed Biomedical Graph.

Fig. 7

The 310 Gene Nodes Incorporating Expert-led Knowledge.

Fig. 8

Graph Neural Network to Embed Drug and Gene Nodes and Its Novelties.

Algorithm 1

Model Training.

Fig. 9

ROC and Precision-recall Curves of the GNN Model.

Fig. 10

The Cut-off Point to Determine the Number of Top Drug Candidates.

Algorithm 2

Lead Drug Combination Selection.