Rejecting Cellular senescence and keeping away from senile diseases, University of Edinburgh has issued three "AI anti-aging prescriptions"

Tech 2023-07-24 21:09:50 Source: Network

Content Overview:Studies have shown that Cellular senescence is closely related to cancer, type 2 diabetes, Osteoarthritis, virus infection and other diseases. Although drugs for clearing aging cells have gradually become a research and development hotspot

Content Overview:Studies have shown that Cellular senescence is closely related to cancer, type 2 diabetes, Osteoarthritis, virus infection and other diseases. Although drugs for clearing aging cells have gradually become a research and development hotspot. However, due to the lack of fully characterized molecular targets, few anti-aging compounds (Senolytics) have been discovered. Recently, a research result was published in the international journal Nature Communications, and researchers have discovered three new types of Senolytics.
Keywords:Senolytics machine learning XGBoost

This article was first published on the HyperAI super neural WeChat public platform~

Since ancient times, people have always pursued immortality. Surprisingly, in recent years, topics such as anti-aging and longevity have been moving from the mysterious and elusive healthcare industry to the widely recognized healthcare industry. In general cognition, aging is the process of slow weakening of bodily functions, which is irreversible. Therefore, humans can only let nature take its course and let nature take its course. However, what many people do not understand is that,As early as 2018, the World Health Organization announced in the International Code of Diseases that aging is a treatable disease.

In the broad definition of aging, Cellular senescence is one of the hot research directions of scientists recently. The so-called Cellular senescence is a phenomenon characterized by the cessation of cell division.Normally, the human immune system is able to effectively clear senescent cells, but as age increases, this clearance function gradually weakens. In addition to causing deterioration of vision and limited mobility, it is also prone to various diseases such as cancer and Alzheimer's disease.

In 2015, Dr. James L. Kirkland and others from the Mayo Clinic discovered the first anti-aging drugs (Senolytics) that could clear aging cells,Senolytics refers to small molecule compounds that selectively induce cell death in aging cells, and their names are derived from Senescence (aging) and Lytic (destruction).In the latest research, the University of Edinburgh and the University of Cantabria have found three kinds of Senolytics - Ginkgetin, Periplocin and Oleendrin, using machine learning, and verified their anti-aging effects in human cell lines.The study has been published in the journal Nature Communications under the title 'Discovery of Senolytics in machine learning'.

Figure 1: The research findings have been published in NatureCommunications

Paper address:

https://www.nature.com/articles/s41467-023-39120-1#Sec2

Experimental process

data set

data set 58 Senolytics LOPAC-1280 Prestwick FDA-approved-1280 Senolyticsdata setIt contains a total of 2523 compounds, with Senolytics accounting for 2.3%.

Figure 2: Compounds used to train machine learning models

A:The training data comes from multiple channels.

B:58 Senolytics sources used for training, including the number of compounds and cell lines from each source.

model training

data set Senolyticsdata setIn this process, they used the Random forest (RF) model to calculate the average Gini index reduction of each feature, and selected 165 most important features, thus reducing the number of features and the complexity of the model.

The Gini index measures the degree of confounding of samples in a node, and a lower value indicates that the samples in the node are purer.

165 data set Senolytics Senolytics Senolytics Senolytics data set 5 3 F1

At first, researchers mainly focused on Support Vector Machines (SVM) and RF models, but after experiments, it was found that their performance was not ideal.At the same time, they also evaluated other models with different complexity, including Logistic regression, Naive Bayes classifier, and SMOTE, but the results showed that the performance of these models was not as good as SVM and RF models.

Therefore, researchers developed the XGBoost model based on RF performance as a benchmark,The prediction ability is improved by iteratively training the decision Tree model.As shown in Figure 3b, the XGBoost model has improved in accuracy, recall, and F1 score, performing best among all considered models.

Figure 3: Training Machine Learning Model

A:model training

B:The performance of three machine learning models, the Bar chart shows the average performance index calculated in the 5-fold cross validation, and the error bar represents a standard deviation.

data set HyperAI

https://doi.org/10.5281/zenodo.7870357

experimental result

Firstly, researchers screened 21 compounds that may have anti-aging activity from over 4340 compounds. Subsequently, they conducted tests on these 21 compounds,As shown in Figure 4, three of them have the function of scavenging senescent cells: Periplocin and Oleendrin (two Cardiac glycoside that have not yet been determined to be able to scavenge senescent cells) and Ginkgetin (a natural non-toxic double Flavonoid).

Figure 4: Periplocin, Oleandrin, and Ginkgetin have a scavenging effect on aging cells

C:Experimental verification. Three out of 21 compounds showed anti-aging activity: Ginkgetin, Oleandrin, and Periplocin; The thermodynamic diagram shows the mean of n=3 repeated experiments. Ouabain in the figure is a known Senolytics.

D:Dose response curves of three newly discovered anti-aging compounds. SI is the anti-aging index.

Experimental processResearchers also found that the newly discovered Oleandrin has stronger anti-aging properties compared to Ouabain, especially at low concentrations.Therefore, researchers compared the anti-aging activity of Periplocin, Oleandrin, and Ouabain at low concentrations of 10nM.

Figure 5: Comparison of anti-aging performance of Periplocin, Oleandrin, and Periplocin at low concentrations

A:The figure shows the tissue Petri dish of IMR90ER: RAS (senescent cells) and IMR90ER: STOP (control group) under the condition of 100nM4OHT culture. Within the next 72 hours, treat with 10nMOleandrin, Ouabain, and Periplocin, as well as DMSO (control).

B:Evaluate cell survival rate through quantitative analysis.

As shown in Figure 5b, low concentrations of Ouabain and Periplocin did not exhibit significant cytotoxicity in IMR90-ER: STOP and IMR90-ER: RAS,After treatment with Oleandrin, the survival rate of senescent cells in IMR90-ER: RAS significantly decreased, indicating that Oleandrin has strong anti-aging activity at lower drug concentrations.experimental result Machine learning has been able to successfully identify anti-aging compounds and also found Oleandrin with stronger anti-aging properties than existing anti-aging compounds.

AI driven drug discovery

AI is very effective in helping us discover new candidate drugs, especially in the early stages of drug discovery

The study's work VanessaSmer Barreto emphasizes the importance of close collaboration among data scientists, chemists, and biologists. She stated:model trainingThis cooperation mode provides new opportunities for accelerating AI application and is expected to promote the innovation and development of Drug development.

At present, although AI has made breakthroughs in new drug development, it still faces some challenges, such as data quality and reliability, algorithm interpretability, and model generalization ability.With the continuous progress of technology and the increase of data resources, the application prospect of AI in Drug development is still very broad.By strengthening data sharing and interdisciplinary cooperation, we can better utilize the advantages of AI, accelerate the discovery and development of new drugs, and bring benefits to human health.

Reference article:

[1] http://zixun.69jk.cn/shwx/79532.html

[2] https://en.wikipedia.org/wiki/Cellular_senescence#Characteristics_of_senescent_cells

[3] https://newatlas.com/medical/machine-learning-algorithm-identifies-natural-anti-aging-chemicals/

[4] https://www.sohu.com/a/673349496_121124375

[5] https://www.ed.ac.uk/institute-genetics-cancer/news-and-events/news-2023/ai-algorithms-find-drugs-that-could-combat-ageing

[6] http://www.stcn.com/article/detail/904319.html

This article was first published on the HyperAI super neural WeChat public platform~

Disclaimer: The content of this article is sourced from the internet. The copyright of the text, images, and other materials belongs to the original author. The platform reprints the materials for the purpose of conveying more information. The content of the article is for reference and learning only, and should not be used for commercial purposes. If it infringes on your legitimate rights and interests, please contact us promptly and we will handle it as soon as possible! We respect copyright and are committed to protecting it. Thank you for sharing.(Email:[email protected])

Mobile advertising space rental

Tag: Rejecting Cellular senescence and keeping away from senile diseases