Life Extension Magazine®

Scientist studying the effects of inisilico medicine

Insilico Medicine Wages War on Aging and Disease

Dr. Alex Zhavoronkov uses deep neural network artificial intelligence to analyze, understand, and mitigate human aging.

By Michael Downey.

Scientists relentlessly seek new drugs and nutrients that target chronic diseases and the aging process. But progress remains frustratingly slow, as evidenced by:

  • It is estimated to take from about seven to over 10 years, and an average of more than $1 billion, to bring a drug to market,
  • Only about 12% of drugs entering clinical trials gain FDA approval, and
  • The cost of drug development increased by roughly 8.5% per year in the past decade.1

Alex Zhavoronkov, PhD, is on an ambitious mission to change all that.

Insilico Medicine, the drug development company that he founded in 2014, has instituted a novel way to dramatically speed up the ability to identify compounds that may not only attack human aging, but simultaneously treat illnesses such as heart disease, cancer, and diabetes.2

Deep Neural AI

Dr. Zhavoronkov is employing the deep neural network form of artificial intelligence to understand human aging.3

Neural networks are a type of, or an aspect of, artificial intelligence and machine learning.4 These terms are becoming more familiar to us, since they play an increasingly important role in our lives. Neural networks attempt to simulate the way human neurons interact during learning. A neural network is "deep" when it contains many layers of simulated neurons.5

Insilico has already made gains in using artificial intelligence (AI) and different computer programs to accelerate the phases of new drug development.6,7

The company's AI platform, known as Pharma.AI, uses millions of data sources and samples (including patents, medical journals, clinical trial reports, and test data such as RNA sequencing). There are three distinct arms comprising this AI platform:

  • PandaOmics, which reduces the time required to identify and analyze drug targets,8
  • Chemistry 42, which utilizes data to design new drugs (by predicting active drug molecules),9 and
  • InClinico, which designs and makes predictions about clinical trials.10

These arms of the Insilico AI platform lead directly to preclinical and clinical trials. As an example, Insilico's candidate to treat the lung disease idiopathic pulmonary fibrosis was the first to be discovered and designed using AI. This drug is already in phase 1 clinical trials.11,12

In 2019, Insilico published research in Nature Biotechnology showing that its approach was able to find six promising treatments for idiopathic pulmonary fibrosis in just 21 days.13

Robotic Lab

Huge savings in drug development costs could be realized if the lab testing procedure were automated. So, the next step for Dr. Zhavoronkov is a fully automated robotic lab.

The lab will be powered by its own AI system and will employ robots to conduct experiments.9

"These robots are faster and more precise than humans," notes Zhavoronkov. "As they perform experiments, they feed the AI system with data."14

This robotic lab has been in the design phase for two years and is expected to be fully operational within months.

Geroprotectors and Autophagy Activators

A unique aspect of Insilico's research into dietary ingredients is its focus on geroprotectors, interventions/compounds that mitigate the process of aging and aim to extend lifespan in animals and humans.15 It is hoped that this could eventually facilitate a young, healthy state in older human tissues.16

This research has enabled the company to identify nutrients that target drivers of aging such as cellular senescence and declining stem cell health. These nutrient-based geroprotectors could be used to create formulations that promote longevity.

Another cause of aging is reduced autophagy, or "cellular housekeeping."17,18

Autophagy declines with age and poor diet, causing cells to become overwhelmed by damage and metabolic waste. This leads to accelerated aging and risk for chronic disease.18

Working in collaboration with Life Extension®, scientists at Insilico identified two nutrients that work together to activate autophagy: luteolin and piperlongumine.

Luteolin, a flavonoid found in many plants, works by increasing the activity of AMPK,19,20 an enzyme that activates autophagy.21 In preclinical and phase 1 clinical trials, stimulating AMPK has been shown to improve metabolic health22,23 and increase lifespan.24

Luteolin also inhibits signaling of mTOR, a protein that shuts off autophagy.25-27

Piperlongumine is a compound isolated from the long pepper plant. It has been shown in animal and cell studies to activate autophagy by inhibiting mTOR signaling, which is considered a beneficial longevity mechanism.29,30

Together, these nutrients can help keep cells functioning youthfully for improved health.

What You Need to Know

Using Technology to Fight Aging

  • Insilico Medicine is using a form of artificial intelligence (AI) that helps to find compounds/drugs quickly and efficiently with the potential to treat disease and prolong life.
  • Working with Life Extension®, scientists at Insilico have found two nutrients that activate autophagy ("cellular housekeeping"), which keeps cells functioning youthfully: luteolin and piperlongumine.
  • Insilico's founder, Dr.Alex Zhavoronkov, has also used AI to identify five blood components that are predictive of biological age: albumin, glucose, alkaline phosphatase, urea, and erythrocytes.
  • Using AI and robotics, Insilico aims to develop new, personalized drugs that can simultaneously target disease and aging itself.

Human Aging Clocks

Dr. Zhavoronkov was inspired in his efforts by the promise of predicting human age through the use of what are known as DNA methylation clocks.31

Predicting biological age can be valuable in human longevity studies. That's because it offers a relatively quick way to measure whether a therapeutic intervention will successfully slow or reverse aging, rather than having to wait decades for a lifespan to play out.

Dr. Zhavoronkov trained deep neural networks on 60,000 human blood samples, which identified five blood components that are predictive of age:32

  • Albumin, a protein that carries hormones, vitamins, and enzymes,
  • Glucose,
  • Alkaline phosphatase or ALP, an enzyme involved in processes throughout the body,
  • The waste product urea, and
  • Erythrocytes, red blood cells packed with hemoglobin.

When these five components are inputted to proprietary software and analyzed, they can be helpful in predicting a patient’s biological age.

Looking Ahead

Dr. Zhavoronkov's goals in longevity biotechnology are wide-ranging:

  • Discover drugs to target aging and disease simultaneously,
  • Develop better aging clocks to track human biological aging,
  • Personalize drugs, employing robotics and AI to individualize drug discovery,
  • Open research hospitals that use AI and robotics to bring longevity innovations closer to people in need, and
  • Develop cryobiology innovations, including rapidly freezing, reheating, and reviving organs, animals, and humans.

Insilico licenses its AI platform to other pharmaceutical companies to help them accelerate their drug development programs. Zhavoronkov has also founded Longevity Medicine, which offers a degree course in longevity for medical professionals.33

Still, Dr. Zhavoronkov can't help but feel frustrated.

"Many very talented human beings choose to focus on inventing, making, and selling stuff and content that people can easily live without," he notes, "instead of contributing to fighting [aging], the one silent enemy."

If you have any questions on the scientific content of this article, please call a Life Extension Wellness Specialist at 1-866-864-3027.


  1. Available at: . Accessed April, 15, 2023.
  2. Available at: . Accessed April, 15, 2023.
  3. Available at: . Accessed April, 15, 2023.
  4. Available at: . Accessed July 11, 2023.
  5. Tuladhar A, Moore JA, Ismail Z, et al. Modeling Neurodegeneration in silico With Deep Learning. Front Neuroinform.20212021-November-19;15:748370.
  6. Ren F, Ding X, Zheng M, et al. AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor. Chem Sci.2023Feb 8;14(6):1443-52.
  7. Available at: . Accessed July 11, 2023.
  8. Available at: . Accessed April, 19, 2023.
  9. Available at: . Accessed April, 19, 2023.
  10. Available at: . Accessed July 11, 2023.
  11. Available at: . Accessed April, 19, 2023.
  12. Wynne CJ. A Phase 1, Evaluate the Safety, Tolerability, and Pharmacokinetics of INS018_055 in Healthy Subjects. 2022.
  13. Zhavoronkov A, Ivanenkov YA, Aliper A, et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat Biotechnol. 2019Sep;37(9):1038-40.
  14. Available at: . Accessed July 13, 2023.
  15. Yang J, Peng S, Zhang B, et al. Human geroprotector discovery by targeting the converging subnetworks of aging and age-related diseases. Geroscience.2020Feb;42(1):353-72.
  16. Aliper A, Belikov AV, Garazha A, et al. In search for geroprotectors: in silico screening and in vitro validation of signalome-level mimetics of young healthy state. Aging (Albany NY). 2016Sep 24;8(9):2127-52.
  17. Cheon SY, Kim H, Rubinsztein DC, et al. Autophagy, Cellular Aging and Age-related Human Diseases. Exp Neurobiol.2019Dec 31;28(6):643-57.
  18. McHugh D, Gil J. Senescence and aging: Causes, consequences, and therapeutic avenues. J Cell Biol.2018Jan 2;217(1):65-77.
  19. Zhang X, Zhang QX, Wang X, et al. Dietary luteolin activates browning and thermogenesis in mice through an AMPK/PGC1alpha pathway-mediated mechanism. Int J Obes (Lond).2016Dec;40(12):1841-9.
  20. Liu S, Su Y, Sun B, et al. Luteolin Protects Against CIRI, Potentially via Regulation of the SIRT3/AMPK/mTOR Signaling Pathway. Neurochem Res. 2020Oct;45(10):2499-515.
  21. Li Y, Chen Y. AMPK and Autophagy. Adv Exp Med Biol.2019;1206:85-108.
  22. Zhang L, Han YJ, Zhang X, et al. Luteolin reduces obesity-associated insulin resistance in mice by activating AMPKalpha1 signalling in adipose tissue macrophages. Diabetologia.2016Oct;59(10):2219-28.
  23. Fouqueray P, Bolze S, Dubourg J, et al. Pharmacodynamic effects of direct AMP kinase activation in humans with insulin resistance and non-alcoholic fatty liver disease: A phase 1b study. Cell Rep Med.2021Dec 21;2(12):100474.
  24. Burkewitz K, Weir HJ, Mair WB. AMPK as a Pro-longevity Target. Exp Suppl.2016;107:227-56.
  25. Wang Q, Wang H, Jia Y, et al. Luteolin reduces migration of human glioblastoma cell lines via inhibition of the p-IGF-1R/PI3K/AKT/mTOR signaling pathway. Oncol Lett.2017Sep;14(3):3545-51.
  26. Raina R, Pramodh S, Rais N, et al. Luteolin inhibits proliferation, triggers apoptosis and modulates Akt/mTOR and MAP kinase pathways in HeLa cells. Oncol Lett.2021Mar;21(3):192.
  27. Wu HT, Lin J, Liu YE, et al. Luteolin suppresses androgen receptor-positive triple-negative breast cancer cell proliferation and metastasis by epigenetic regulation of MMP9 expression via the AKT/mTOR signaling pathway. Phytomedicine.2021Jan;81:153437.
  28. Ryu J, Kim MJ, Kim TO, et al. Piperlongumine as a potential activator of AMP-activated protein kinase in HepG2 cells. Nat Prod Res. 2014;28(22):2040-3.
  29. Liu J, Liu W, Lu Y, et al. Piperlongumine restores the balance of autophagy and apoptosis by increasing BCL2 phosphorylation in rotenone-induced Parkinson disease models. Autophagy.2018;14(5):845-61.
  30. Makhov P, Golovine K, Teper E, et al. Piperlongumine promotes autophagy via inhibition of Akt/mTOR signalling and mediates cancer cell death. Br J Cancer.2014Feb 18;110(4):899-907.
  31. Horvath S. DNA methylation age of human tissues and cell types. Genome Biol.2013;14(10):R115.
  32. Putin E, Mamoshina P, Aliper A, et al. Deep biomarkers of human aging: Application of deep neural networks to biomarker development. Aging (Albany NY). 2016May;8(5):1021-33.
  33. Available at: . Accessed April, 19, 2023.