Artificial intelligence identifies cancer killer cells. Using artificial intelligence, scientists have developed a predictive model to identify the most powerful cancer-killing immune cells and deliver cancer immunotherapy.

Artificial intelligence identifies cancer killer cells

A new predictive model can be used in conjunction with multiple algorithms for personalized cancer treatment that matches treatment to the unique cellular makeup of each patient’s tumors.

According to Science Daily, “Alexandre Harari” from the “Ludwig Cancer Research Center”, who supervised this research along with “Rémy Pétremand”, a graduate of this center, said: Artificial intelligence in cell therapy is a new work and may be able to change the treatment method and provide new clinical options to patients.

Cellular immunotherapy involves extracting immune cells from a patient’s tumor, engineering them to enhance their natural cancer-fighting abilities, and transplanting them back into the body after they have grown. T cells are one of two main types of white blood cells, or lymphocytes, that circulate in the blood and seek out cells infected with viruses or cancer.

T cells that infiltrate solid tumors are known as tumor-infiltrating lymphocytes (TILs). However, not all tumor-infiltrating lymphocytes are effective in recognizing and attacking tumor cells. Harari explained: Actually, only a part of the lymphocytes react to the tumor and most of them are observers. The challenge we faced was to identify a small number of tumor-infiltrating lymphocytes. These lymphocytes are equipped with T cell receptors that can recognize antigens on the tumor.

To do this, Harari and his team developed an artificial intelligence-based predictive model called TRTpred that can rank T-cell receptors, or TCRs, based on their target tumor reactivity. To develop TRTpred, they used 235 T-cell receptors collected from patients with metastatic melanoma who had previously been classified as tumor-reactive or non-reactive. The research group loaded the gene expression profile of T cells bearing each T cell receptor into a machine learning model to identify patterns that distinguish tumor-reactive T cells from their inactive counterparts.

TRTpred can learn from a T-cell population and create a rule to apply to a new population, Harari explained. So, when faced with a new T-cell receptor, the model can read its profile and predict whether the tumor will respond.

The TRTpred model analyzed tumor-infiltrating lymphocytes in 42 patients with melanoma and gastrointestinal, lung, and breast cancers and identified tumor-reactive T cell receptors with 90% accuracy. The researchers modified their tumor-infiltrating lymphocyte selection process by using a secondary filter that screens only tumor-reactive T cells; That is, only cells that have a strong connection to tumor antigens.

“TRTpred is exclusively predictive of whether or not the T cell receptor is reactive to the tumor, but some tumor-reactive receptors make a strong binding to tumor cells and are therefore very effective,” Harari said. While others do it out of laziness. Distinguishing between strong and weak connections indicates effectiveness.

The researchers showed that T cells identified as tumor reactants by TRTpred and the secondary algorithm are often located in tumors. The findings of this study are in line with other studies that show that effective T cells usually penetrate deep into the tumor.

Next, the researchers introduced a third filter to maximize the detection of tumor antigens. “We want to maximize the chance that tumor-infiltrating lymphocytes will target as many different antigens as possible,” Harari said.

This final filter organizes T cell receptors into several groups based on similar physical and chemical properties. The hypothesis of the researchers is that the T cell receptors in each cluster recognize the same antigen. “So we choose one T-cell receptor in each cluster to amplify to increase the chance of targeting a specific antigen,” said Vincent Zoete, a researcher at the Ludwig Cancer Research Center who developed the T-cell receptor clustering algorithms.

Read more: Discovery of 32 new cancer drugs with the help of artificial intelligence

The researchers call the combination of TRTpred and algorithmic filters “MixTRTpred”.

To validate their method, Harari’s group implanted human tumors into mice, extracted T-cell receptors from their tumor-infiltrating lymphocytes, and used the MixTRTpred system to identify tumor-reactive T cells and multiple antigens in the target tumor. put. Next, they engineered T cells obtained from mice to express T cell receptors and showed that these cells could destroy tumors when transferred to mice.

“George Coukos”, one of the researchers of this project, who is planning to launch the first stage of clinical trial to test this technology in patients, said: This method promises to overcome some of the shortcomings of treatment based on tumor infiltrating lymphocytes. Especially for patients dealing with tumors that are unable to respond to such treatments. Our joint efforts are creating a completely new way of T-cell therapy.

This research was published in “Nature Biotechnology” magazine.

An artificial intelligence platform developed at the University of California San Diego was able to produce 32 new drugs to target cancer in trials.

Discovery of 32 new cancer drugs with the help of artificial intelligence

UC San Diego scientists have developed a machine learning algorithm for simulating the time-consuming chemistry of the early stages of drug discovery, which could significantly simplify the process and enable the delivery of new treatments.

According to the official website of the University of California San Diego, identifying new drugs for further improvement usually involves thousands of individual experiments, but the new AI platform can provide the same results in a fraction of the time. Scientists used this new platform to produce 32 new cancer drugs.

The technology is part of a new but growing trend in pharmaceutical science to use artificial intelligence to improve drug discovery and development.

“Trey Ideker” (Trey Ideker), a professor of the Department of Medicine at the University of California San Diego School of Medicine and the senior researcher of this project said: “A few years ago, artificial intelligence was a dirty word in the pharmaceutical industry, but now this trend is the opposite because biotechnology startups without addressing AIs find it difficult to raise capital in their business. AI-driven drug discovery has become a very active area in pharma, but unlike methods developed in corporations, we make our technology open-source and available to anyone who wants to use it.

The new platform, called POLYGON, is unique among drug discovery AI platforms because it can identify molecules with multiple targets. Meanwhile, existing drug discovery protocols currently prioritize single-target treatments. Multitargeted drugs are of interest to clinicians and scientists because of their potential to provide similar benefits to combination therapy while having fewer side effects.

Eidker said: Finding and developing a new drug takes years and costs millions of dollars; Especially if it is a multipurpose drug. The few multi-target drugs we have have been discovered largely by chance, but this new technology could take luck out of the equation and usher in a new generation of precision medicine.

The scientists trained POLYGON on a database of more than one million known bioactive molecules, containing detailed information about chemical properties and known interactions with protein targets. By learning from the patterns in the database, the POLYGON algorithm can generate the original chemical formulas for new drugs that are likely to have properties such as the ability to inhibit specific proteins.

Just as artificial intelligence is now very good at producing original drawings and images, such as creating images of human faces based on arbitrary characteristics such as age or gender, POLYGON can also produce original molecular compounds based on desired chemical properties. In this case, instead of telling the AI how old we want our face to be, we tell it that we want our future drug to interact with disease proteins.

To test POLYGON, scientists used it to generate hundreds of drugs that target different pairs of cancer-related proteins. Of these, they produced 32 molecules that had the strongest predicted interactions with MEK1 and mTOR proteins. These two are cell signaling proteins that are promising targets for combination cancer therapy. Inhibiting both proteins together is enough to kill cancer cells; Even if the containment of one of them is not done alone.

The researchers found that the drugs they developed had significant activity against MEK1 and mTOR, but showed few off-target reactions with other proteins. This suggests that one or more of the drugs identified by POLYGON could target both proteins as cancer therapies, providing a list of options for fine-tuning by human chemists.

Related article: Transforming invasive cancer cells into healthy cells!

“After you get the drugs, you still have to do other chemical work to make those drug options into a single, effective treatment,” Edker said. We cannot and should not try to remove human expertise from the drug discovery process, but rather shorten some of the steps in the process.

Despite this caution, scientists are optimistic about AI’s potential for drug discovery. Eidker added: It will be very exciting to see how this concept will be implemented in the next decade, both in the university and in the private sector. The capabilities of artificial intelligence are virtually endless.

This research was published in “Nature Communications” magazine.

A vaccine made with messenger RNA (mRNA) technology against glioblastoma, a deadly form of brain cancer, has shown promise in a new clinical trial.

Brain cancer vaccine success in human trials

Glioblastoma is one of the deadliest cancers for which few treatment options are available.

Now, a small human clinical trial has shown the efficacy of an mRNA vaccine that rapidly primes the immune system to fight tumors, with promising results, according to NA.

Glioblastoma is the most common form of brain cancer and unfortunately, it is also known as the most aggressive brain cancer.

Glioblastoma is the most common primary malignant tumor of the central nervous system that occurs in the spinal cord or brain. The origin of this tumor is from astrocyte cells (a type of glial cell).

Treatment for glioblastoma includes a combination of surgical removal, radiation therapy, and chemotherapy, but the disease almost always recurs, and patients with it usually survive only about a year after diagnosis, with only about 5 percent of patients surviving more than five years.

A new study from the University of Florida may soon provide these patients with a better option, the mRNA cancer vaccine.

The technology, best known for COVID-19 vaccines, has been shown to quickly prime the immune system to more effectively attack glioblastoma in mice, dogs, and now humans.

As you may remember from the critical days of 2020 and 2021 due to the outbreak of the COVID-19 pandemic, mRNA molecules are essentially natural blueprints that tell cells which proteins to produce and by engineering them to produce harmless versions of the proteins. Associated with pathogens, the immune system can be trained to fight off a true invader when it appears.

Following the real-world success of these treatments during the pandemic, the possibility of adapting mRNA therapies for cancer has emerged with interesting early results.

University of Florida researchers say this new version has two key improvements. First, the vaccine is personalized using samples taken from the patient’s tumor cells. Second, the delivery mechanism is more complex, which ultimately leads to a stronger immune response.

Related article: Testing a vaccine that reduces liver tumors

“Instead of injecting single particles, we inject clusters of particles that are wrapped around each other like the layers of an onion, like a bag full of onions,” said Elias Sayor, senior author of the study. In less than 48 hours, we can see that these tumors change from the so-called cold state, which indicates very few immune cells and a muted immune response, to a warm and highly active immune response state.

He added: This was very surprising. Given how quickly this happened, what it told us is that we were able to activate the early part of the immune system quickly against these cancers, and that’s very important for unlocking the downstream effects of the immune response.

This small clinical trial approved by the US Food and Drug Administration (FDA) was designed to test safety and feasibility and included only four patients with glioblastoma. RNA was extracted from each patient’s tumor after surgical resection, then the mRNA was amplified and wrapped into particle clusters. It was then injected into patients, where it stimulated an immune response.

The team says it’s too early to fully assess the vaccine’s clinical effects, but patients spent more time disease-free and survived longer than expected.

A large-scale trial will be conducted soon, including up to 24 patients, to determine the optimal and safe dose of this vaccine. Next, the next phase of the experiment includes 25 children.

This research was published in the journal Cell.