DRUG DISCOVERY is the first step of the value chain that identifies new candidate therapeutics for treating or curing human diseases. It is the initial stage of research and development (R&D) and involves the identification and optimization of potential new drugs. Successful candidates that meet the regulatory requirements applied to drug discovery move into the clinical trial phase, where they are tested for efficacy and safety in humans.
The four main stages of drug discovery generally take five to six years to complete. Drug discovery is a long, expensive, and often unsuccessful process.
First screening and hit identiﬁcation– High-throughput screening of large libraries of chemicals to test their ability to modify the target positive hits are selected for further validation.
Hit to lead selection-Hits are conﬁrmed and analogue clusters are synthesized three to six molecule clusters with better aﬃnity and drug properties are selected.
Lead optimization (drug candidate selection)– Lead molecules are further modiﬁed and improved a few drug candidates are selected (1 in 5000 from initial screening).
Pre-clinical testing– In vivo assays are performed to test pharmacodynamics, pharmacokinetics, and toxicity of novel candidates 1 in 25 drug candidates that enter pre-clinical phase are selected for clinical trial studies.
Why Artificial Intelligence in Drug Discovery? Why now?
- AI-enabled solutions are emerging as a crucial tool for transforming the process of researching disease mechanisms of action and revolutionizing the understanding of how drugs bind to targets, improving specificity.
- AI can also help cross-reference published scientific literature with alternative information sources, including clinical trials information, conference abstracts, public data-banks, and unpublished datasets.
- AI solutions have the potential to kick-start the productivity of the entire R&D process.
- Reduce timelines for drug discovery and improve the agility of the research process. The successful application of innovative technologies could speed up the discovery and pre-clinical stages by a factor of 15.
- Increase the accuracy of predictions on the efficacy and safety of drugs. Currently, only one out of ten drugs are approved after clinical trials. Most fail due to efficacy and safety issues. Given the growing cost of bringing a drug to market, a ten percent improvement in the accuracy of predictions could save billions of dollars spent on drug development.
- While AI will have a role to play in the development of biologics, so far, its use is largely focused on chemical, small molecule research applications. The use of AI technologies to improve drug discovery is still at the early stages and the applications available today are pre- cursors to wider scopes such as biologics AI.
AI algorithms -Mining the data
In drug discovery, AI algorithms mostly use research data or available information on the 3D structure and binding properties of small molecules to ‘recognize’ the target specificity with greater accuracy than has been possible previously, using the same deep learning (DL) processes used for face recognition. This same concept is used to identify unwanted interactions causing toxicity.
There are an increasing number of relevant sources of data for AI-enabled discovery and drug candidate selection. Relevant data sources include:
- The completed international human genome project in 2003 and the subsequent ‘omics’ (genomics, metabolomics, proteomics, and structural genomics) revolutions, including the completion of the UK’s 100,000 Genomes Project in 2018.
- Proprietary and public research findings-About 80 percent of scientific data is available only in intellectual property files. Grant applications and conference presentations are also rich in information that could be relevant to identifying new drug targets.
- Data related to the 90 percent of drugs that do not make it is a valuable source of information for AI applications, including identifying unwanted interactions.
- Small molecule libraries and protein structure information from research and clinical data. Each small molecule database is on average composed of 10 million compounds. By the mid- 2000S, the available academic, commercial, and proprietary databases of small molecules world- wide contained information related to 100 million different compounds.
Ever wondered how AI start-ups are accelerating to find potential Covid-19 therapies?
Drug re-purposing is one of the fastest and safest methods, as the drugs are already being used to treat other conditions, therefore, leading to fewer chances of adverse reactions. Artificial intelligence holds significant promise for bio-pharma companies to expedite the drug re-purposing process.
London-based BenevolentAI, used its AI-based drug discovery platform to identify drugs that could disrupt certain viral entry pathways of COVID-19, thus inhibiting the replication process. Researchers screened inhibitors of AP2-associated protein kinase 1 (AAK1). AAK1 is a known regulator of endocytosis and its disruption may inhibit the entry of the virus into cells. In a process that took just three days to complete, over 370 AAK1 inhibitors were identified, 47 of which are approved for use, with six showing the most promise.
Japanese start-up Elix, harnessed a variety of neural networks to predict the chemical properties of molecules that can help to destroy COVID-19. The start-up’s AI tool screened a library of 350 million drug-like molecules to find potential drugs to treat COVID-19. Among the drug candidates identified by Elix’s AI tool was remdesivir, which recently received emergency use authorisation from the FDA to treat COVID-19 patients.
Singapore’s Gero, leveraged AI to quickly screen already existing drug molecules to treat COVID-19. Some of the identified drugs that are potentially effective include niclosamide, nitazoxanide, afatinib and reserpine.
Artificial Intelligence in the drug discovery market is projected to increase at a compound annual growth rate (CAGR) of 40.8 percent from 2019 to 2024. In the next five to ten years, the number of companies using AI for drug discovery will increase exponentially and new drugs capable of treating very precise pathologies will become the norm. Significant advances in the techniques used will evolve to produce next generation AI methods and provide the framework for precision medicine to become mainstream.