|Artificial intelligence is the brain behind almost all the new technological devices today / Photo by: Willyam Bradberry via Shutterstock|
Artificial intelligence is the brain behind almost all the new technological devices today. Companies and industries across the world are investing in AI not only to meet the increasing demand for it in our society but also out of fear of being left behind.
According to The Wall Street Journal, a US business-focused, English-language international daily newspaper based in New York City, the Deloitte’s State of AI in the Enterprise report revealed that 63% of over 1,900 executives from companies believe that AI technologies are critically important to their business success today. It is projected that the figure will reach 81% in the next two years. Today, organizations are using a variety of AI technologies to achieve their goals, including machine learning (61%), natural language processing (60%), computer vision (56%), and deep learning (51%).
The progress of AI has also reached drug discovery and development. A new report by Market Research Inc. shows that AI in the drug discovery market is projected to grow at a CAGR of +40% between 2019 to 2025. The technology’s sophisticated algorithms can improve a wide range of applications in drug discovery, medical imaging and diagnostics, and patient data and risk analysis.
AI in Drug Discovery
Traditionally, a drug discovery project begins with basic research to identify targets that may be susceptible to attack, including a disease-related protein receptor on the surface of particular cells. The scientists then use techniques to see which compounds bind the target like high-throughput screening. To fine-tune the structure or test other features, they conduct various methods of biological and chemical testing. In short, research and development undergo a lengthy process.
Most of the time, these procedures not only take many years to complete, but also cost billions of dollars. Aside from that, patients during trials/experiments are exposed to side effects that are hard to predict. Unfortunately, going through these long processes and managing risks don’t guarantee that certain drug discovery would be successful. It still has to go through regulatory approval from a respective regulatory agency like the US Food and Drugs Administration (FDA).
A lot of companies want to change this. Applying technologies to the traditional framework to modernize the drug testing process is one way to do so. Innovation in industries like drug discovery would provide benefits to the overall healthcare sector, especially the main target of these drugs. However, the misapplication of technologies like AI can have unintended harmful consequences. A good example of this is the case of social media since the rise of algorithms. Today, misinformation spreads faster than the truth.
|Traditionally, a drug discovery project begins with basic research to identify targets that may be susceptible to attack, including a disease-related protein receptor on the surface of particular cells / Photo by: Gorodenkoff via Shutterstock|
Nonetheless, many AI applications are now rampant in several drug discovery studies/projects. For instance, a model that can identify previously unknown cancer mechanisms using tests on more than 1,000 cancerous and healthy human cell samples was previously developed by the researchers from biotechnology company Berg, near Boston, Massachusetts. According to Nature, the world's leading multidisciplinary science journal, the team used AI in generating and analyzing huge amounts of biological and outcomes data from patients to highlight key differences between diseased and healthy cells.
“We are turning the drug-discovery paradigm upside down by using patient-driven biology and data to derive more-predictive hypotheses, rather than the traditional trial-and-error approach,” Niven Narain, Berg’s co-founder and chief executive, said.
How AI Can Help in Drug Discovery
One of the ways AI can aid drug discovery is by helping authorities understand the mechanisms of disease; generate data, models, or novel drug candidates; design or redesign rugs; establish biomarkers; design and run clinical trials; run preclinical experiments, and even analyze real-world experience. The technology can also help companies in aggregating and synthesizing huge amounts of data needed for clinical trials, thus shortening the drug development process.
AI can be used in reducing the risks of drug discovery. Most of the time, scientists conduct several experiments to find solutions to a specific drug or healthcare problem. While there are positive results in these trials, negative results are evident. The process of experimentation can significantly change through the emergence of prediction tools based on AI. According to The Varsity, the official student newspaper of the University of Toronto, AI prediction tools have the potential to narrow the starting point from which researchers have to begin experimenting. Also, AI can guide scientists toward potential avenues for success by eliminating incompatible solutions, which can save both time and money.
The book “Prediction Machines: The Simple Economics of Artificial Intelligence” co-written by Dr. Avi Goldfarb, a professor at the Rotman School of Management, stated that AI prediction tools can have significant and specialized meaning to the pharmaceutical industry. For instance, it can “increase the success [rate] of early-stage experiments in the drug discovery process and increase the number of successful drugs that come to market.”
A recent study conducted by Alex Zhavoronkov, Ph.D., an expert in artificial intelligence for drug discovery and aging research, demonstrated the power of AI to markedly accelerate the design and experimental validation of a new molecule using a GAN approach. According to EurekAlert!, an online science news service featuring health, medicine, science and technology news from leading research institutions and universities, Zhavoronkov stated that AI can be used to search for good drug molecules in the vastness of chemical space, which is one of the key challenges in drug discovery today.
“The work provides compelling evidence that AI can learn from historical datasets to generate novel molecular compounds with drug-like properties, and helps clarify how AI can be used to improve the speed of drug development,” Mark DePristo, former Head of Genomics at Google Brain, said.
This only shows that AI can transform and ignite changes in any industry it enters. The potential benefits of the technology to drug discovery can significantly make traditional processes faster, thus, garnering immediate results.
|The technology can also help companies in aggregating and synthesizing huge amounts of data needed for clinical trials, thus shortening the drug development process / Photo by: SUWIT NGAOKAEW via Shutterstock|