Although advances have been taking place in the pharmaceutical industry over the past years, the development of new drugs even takes about ~15 years and 800 million to one billion dollars. To cope with this problem, drug repurposing is a newly emerging technique in which existing drugs treat various other diseases. It has been a promising approach because of the opportunity for reduced development timelines and overall costs. It maximizes the potential usage of the existing drugs and increases the number of new drugs. It is a low-cost method of repurposing medications for new medical purposes.

In the past few years, various computational approaches have been used in drug repurposing, such as in-silico drug repurposing. Several articles are present in which there is a discussion of how computational methods such as artificial intelligence (AI) and Machine learning (ML) based on network propagation, matrix factorization, and completion are used. So here, Artificial intelligence (AI) and many computational methods accelerate drug repurposing.

Several machine learning (ML) and artificial intelligence (AI) algorithms have been developed to discover drug-repurposing systematic leads using big data resources, thereby speeding up the drug development process.

How Artificial Intelligence Helps in Drug Repurposing

Drug development, artificial intelligence, and real-world data such as electronic health records are used. This technique is cheaper, faster, and more effective. It will enhance the data extraction method from various papers, patents, and other documents and predict which drugs will be used for another disease.

The availability of big data sets from genomics and proteomics and pharmacological in vivo and in vitro studies helps in drug repurposing.

Some tools and software were developed by a scientist who is used for drug repurposing.

Recent Development in Drug Remodeling Using Artificial Intelligence

Artificial-based methods used in COVID-19 drug repurposing:

The mechanism of drug repurposing comes to be an effective tool in the Covid-19 drug. In a recent study, some network-based methodological approaches show the interconnection between the virus-host interactome and the drug targets in the human interactome network. There is the suggestion of 16 repurposed drugs for the treatment of Covid 19. There is another method called graph representation learning. The construction of medical knowledge graphs containing relationships between different medical entities (e.g., diseases, drugs, and proteins) predicts new links between approved drugs and diseases.

In a recent experiment, Gyes and colleagues performed a method based on a graph neural network and presented a study of SARS-CoV-2 in which they suggested 81 potential repurposing drugs. BenevolentAI’s knowledge graph is an extensive repository of structured medical information which includes numerous connections extracted from the scientific literature by Machine learning. This method predicted that a drug used in rheumatoid arthritis shows potential in treating COVID-19 disease by inhibiting AP2-associated protein kinase 1. His team constructed a graph of 15 million edges across 39 relationships connecting drugs, diseases, proteins, genes, and pathways from a sizeable scientific corpus of 24 million PubMed publications. Using Amazon web services computing resources and graph representation learning techniques, their team identified around 41 repurposed drug candidates.

• Future of artificial intelligence in drug repurposing:

  Artificial intelligence is emerging as a promising method in the pharmaceutical industry, where new drugs take lots of time and money. It is an advanced method used to accelerate the process of drug repurposing for the treatment of various diseases in less time. In these years, pharmaceutical scientists, Computer scientists, statisticians, and physicians have been using big data, including biological data, clinical data, pre-clinical data, and open data, to provide better therapeutics. When we couple Artificial intelligence with big data, it will improve the drug repurposing effectiveness and efficiency. It Needs sophistication and technical and conceptual knowledge. Previously, Drug repurposing relied only on clinical observation. But nowadays, clinical trials, patents, and scientific literature can improve the screening process. Deep learning and other methods can reduce imbalances in positive and negative data. Although there are some challenges in this emerging process due to their data heterogeneity, low quality, and insufficient data sharing by some pharmaceutical companies, there is also some security and interpretability of the models. It Needs sophistication and technical and conceptual knowledge. It is difficult to identify novel drug outcomes in some conditions because AI compares the data and results.

How Can We Help You?

Ingenious e-Brain is a global provider of intellectual property, technology, and market research solutions. IeB can give detailed statistics on AI in drug repurposing and the different elements impacting the growth of AI in drug repurposing through technology intelligence. We can help find developments, strategic activities, potential targets for acquisition or partnership, white spaces in the domain, and other details.