The Future of Artificial Intelligence and Biotechnology
Often regarded as robots that will soon take over the world, AI holds a notorious reputation as something that we should fear. However, AI has also been coined as the key to unlocking a new range of therapeutics in areas such as precision medicine and orphan diseases.
What is Artificial Intelligence (AI)? Artificial Intelligence is when a machine is taught to conduct tasks that usually require human intelligence. Over time, as a machine continues to solve different tasks, it is able to learn from its mistakes and, ideally, perform with more accuracy given an adequate learning set. Combining the adaptability of AI with large datasets that are unanalyzable by humans may help advance our understanding of the unknown diseases and cures.
To discuss the importance of AI, Dr. Ivica Labuda, the Director of the Biotechnology Program, organized a webinar titled: “The AI and Machine Learning in Biotechnology – Industry Panel Discussion.” The event, held on September 28th, 2021, included speakers Anna Paola Carrieri, Tomas Drgon, Gigi Minsky, and Henry Minski and discussed how AI can solve unsolvable issues and how AI has impacted their field.
In this article, we will discuss some areas in which AI will revolutionize the biotechnology field.
Elusive 3D protein structures
Proteins are one of the four macromolecules that are essential for life. They are involved in developing antibodies for our immune systems; serve as messenger molecules; aid in tissue repair and more. There have been great advancements in protein structure research, where scientists have used conventional methods such as X-ray crystallography and nuclear magnetic resonance, allowing the scientific community to identify 187,000 structures to date. Despite these advances, there are many proteins whose structures have not been determined with confidence and new methods ought to be used.
Recently, a team of researchers in the UK have created an AI machine learning platform called AlphaFold, which aims to use previous data collected by scientists to predict protein structure and build 3D protein models. This technology has already proven to be accurate and occurs at a fraction of the time that older methods would require. The use of AI to identify drug targets will revolutionize the field by identifying new proteins at a quicker rate, allowing us to more effectively create drugs and therapeutics for deadly diseases such as muscular dystrophy and cystic fibrosis.
The Diagnosis and Treatment of Mental Health Illnesses
The search for preemptively identifying mental health illnesses such as depression and addictive behaviors has puzzled scientists and is a heavily funded area of pharmaceutical research. Recent advancements in AI have shown how preventative medicine can allow physicians and scientists to take immediate action.
Stanford University’s Dr. Leanne Williams recently unveiled research using an AI program that observes brain waves of patients diagnosed with depression to predict what antidepressant therapies will work best for them. In addition, AI is currently being used to identify certain behavioral loops in addicts to determine how their recovery process is going and can identify when a patient might be prone to relapse, at which point a doctor or scientist can intervene and help patients.
One main reason why it is hard to diagnose and treat individuals with mental health illnesses is because each person may require a different course of treatment, and it is often difficult to determine what form of personalized medicine is best for a patient. Artificial Intelligence offers a unique way to advance personalized medicine. The ability of AI to learn from past mistakes allows it to learn and adapt for future use, allowing it to become stronger and more accurate over time. The ability to detect when someone is struggling with a mental health illness allows other interventions to occur before it is too late.
In closing, the introduction of AI into the world has great value in the biotechnology field, especially the pharmaceutical industry. At many points in history, new forms of technology and new ideas have been scrutinized, feared and ignored. Take the case of Dr. Kati Kariko, the woman whose mRNA research was regarded as “unusable” and was often at risk of losing her job due to her field of study. Three decades later, her research was used as the basis of the SARS-CoV-2 mRNA vaccines produced by Pfizer-BioNTech and Moderna, a holy grail during a deadly pandemic. To make sure AI doesn’t face roadblocks that hinder its potential, we must adapt the way we identify drug targets and work to create a Golden Age of personalized and targeted therapeutics, one deadly disease at a time.
Written by: Neha Somineni
Edits by: Kyle A. DiVito, PhD
References:
“Alphafold: A Solution to a 50-Year-Old Grand Challenge in Biology.” Deepmind, https://deepmind.com /blog/article/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology.
Erin McNemar, MPA. “Artificial Intelligence Therapy Reduces Depression and Anxiety.” HealthITAnalytics, HealthITAnalytics, 19 July 2021, https://healthitanalytics.com/news /artificial-intelligence-therapy-reduces-depression-and-anxiety.
Kolata, Gina. “Kati Kariko Helped Shield the World from the Coronavirus.” The New York Times, The New York Times, 8 Apr. 2021, https://www.nytimes.com/2021/04/08/health/coronavirus-m rna-kariko.html.
White, Author Tracie, et al. “AI Predicts Effective Depression Treatment Based on Brainwave Patterns.” Scope, Logo Left ContentLogo Right Content 10,000+ Posts Scope Stanford University School of Medicine Blog, 24 June 2020, https://scopeblog.stanford.edu/2020/06/24/ai-predicts-effective-depression-treatment-based-on-brainwave-patterns/.