July 17, 2024

Chemists Use Machine Learning and Molecular Modeling to Discover Potential Anticancer Drugs

Scientists from RUDN University and collaborators from China have employed machine learning and molecular modeling to identify a group of potential anticancer drugs that inhibit the enzyme responsible for uncontrolled cell division. The findings of their study were recently published in the journal Biomedicines.

The enzyme in question, cyclin-dependent kinase 2 (CDK 2), plays a crucial role in regulating cell division. While CDK 2 is not necessary for healthy cells, it is essential for the uncontrolled growth of cancer cells. Inhibiting the activity of CDK 2 can effectively restrain tumor growth, making the search for effective CDK 2 inhibitors a priority.

To address this, the chemists from RUDN University and their Chinese counterparts utilized computer research methods, specifically machine learning and molecular modeling. This approach allowed them to identify several potential CDK 2 inhibitors.

CDK 2 has long been recognized as a promising target for cancer treatment, as the development of inhibitors for this enzyme is critical in antitumor therapy. Despite its importance, researchers have yet to discover a selective inhibitor specifically targeting CDK 2. However, a number of inhibitors have undergone clinical trials.

In their study, the researchers employed machine learning methods to identify candidate drugs. By building several models, they were able to pinpoint active CDK 2 inhibitors with an impressive 98% accuracy. Each of the 25 potential inhibitors identified by the machine learning models was then subjected to molecular docking to test their efficacy.

Out of the 25 candidates, three compounds stood out as the most promising. To further evaluate their potential, the chemists utilized molecular dynamics simulations, comparing the behavior and stability of the three compounds with that of the reference compound dalpiciclib. The results showed that all three compounds displayed higher stability and compactness when compared to dalpiciclib.

Despite the promising findings, the researchers note that their study has certain limitations. To confirm the inhibitory activity and potential therapeutic efficacy of the identified compounds, further in-depth clinical trials, both in vitro and in vivo, are necessary. Additionally, when developing these drugs, it will be crucial to assess their effect on off-target interactions and potential toxicity.

Alexander Novikov, Ph.D. in Chemistry and a senior researcher at the Joint Institute of Chemical Research of RUDN University, highlights the importance of their research, stating that the development of effective inhibitors for CDK 2 will have significant implications in the treatment of cancer. However, further studies and trials are required to fully explore the therapeutic potential of the identified compounds.

In conclusion, the use of machine learning and molecular modeling techniques has enabled chemists to identify a group of potential anticancer drugs that inhibit CDK 2. This discovery holds promise for the development of novel and effective therapies for cancer treatment. However, more extensive research is needed to validate the findings and evaluate the compounds’ potential as targeted inhibitors for CDK 2.

1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it