Summary: Three high school students from different countries identified new therapeutic targets for glioblastoma multiforme (GBM) using artificial intelligence.
The AI screened datasets from the National Center for Biotechnology Information and found new therapeutic targets implicated in treating both aging and GBM.
The teens used AI to analyze the genes and identified three that were strongly correlated with both aging and glioblastoma and could serve as potential therapeutic targets for new drugs.
Source: Insilico Medicine
Three high school students – Andrea Olsen from Oslo, Norway; Zachary Harpaz from Boca Raton, Florida; and Chris Ren from Shanghai, China – co-authored a paper using a generative artificial intelligence (AI) engine for target discovery from Insilico Medicine (“Insilico”) called PandaOmics to identify new therapeutic targets for glioblastoma multiforme (GBM). GBM is the most aggressive and common malignant brain tumor, accounting for 16% of all primary brain tumors.
The findings were published on April 26 in the journal Aging.
Olsen, a student at Sevenoaks School in Kent, UK, began interning at Insilico Medicine in 2021, after discovering her interest in neurobiology and technology.
For the current paper, the fifth scientific paper she has co-authored before turning eighteen, she and other researchers used PandaOmics to screen datasets from the Gene Expression Omnibus repository maintained by the National Center for Biotechnology Information and found new therapeutic targets implicated for treating both aging and glioblastoma multiforme.
Ren, a student at Shanghai High School International Division, has an interest in biology and biomarkers and joined them in the summer of 2022.
While there would seem to be a clear connection between aging and cancer, Olsen says their findings were more nuanced. “Sometimes, instead of aging, the body switches to cancer mechanisms, which was really interesting to discover.”
She hypothesized that “the body is trying to preserve itself in a way that it is switching back to embryonic processes of cell division.” GBM is caused by a genetic mutation that leads to uncontrolled growth of glial cells, or cells that surround neurons in the brain. Even with existing therapies, the median survival for GBM patients is only 15 months.
Harpaz, a student at Pine Crest School in Ft. Lauderdale, had an early interest in computer science and AI and soon developed a passion for biology as well. “I wanted to combine my two favorite topics, computer science and biology, into what I think is the most interesting field of biology – aging research,” Harpaz says.
He discovered generative AI drug discovery company Insilico Medicine whose founder and CEO, Alex Zhavoronkov, PhD, connected him with Olsen.
The two young researchers began collaborating on the glioblastoma project and ultimately presented findings at the Aging Research and Drug Discovery (ARDD) conference in Copenhagen, where they together launched the Youth Longevity Association (TYLA).
In this latest paper, the three teens used PandaOmics to analyze the genes and identified three that were strongly correlated with both aging and glioblastoma and could serve as potential therapeutic targets for new drugs.
“We selected the genes that were overlapped to be highly correlated in 11 of the 12 datasets, and we split our data into young, middle aged, and senior groups,” said Harpaz.
“We mapped this to the importance of the gene expression to survival.” After identifying two genetic targets for glioblastoma and aging – CNGA3 and GLUD1 – they cross-referenced their findings with earlier findings from Insilico around genes strongly correlated with aging and identified a third target – SIRT1.
“I learned a lot about conducting a research project,” said Ren, who helped review the three targets.
“The PandaOmics platform really made the project accessible to me. As a high school sophomore, I did not have sufficient experience for advanced research and analysis, however, I was still able to navigate the PandaOmics platform after a brief period of training to process and compare datasets of glioblastoma.”
The students say they are eager to continue their studies in AI and biology into college and to move the GBM research forward from target discovery to drug development.
“The best way to take this research further is going to be using Insilico’s Chemistry42 software, where we can take the targets we identified through PandaOmics and generate small molecules, potential drugs, with these targets that have the potential to treat glioblastoma and aging at the same time,” says Harpaz.
Prior to her internship at Insilico, Olsen says: “I never knew that AI could be so helpful in finding completely new therapeutic targets. For me, that was an incredible opportunity to dive into the field of research, aging, longevity, and neuroscience. It really kick-started my entire career.”
“I am truly impressed by the commitment of these young researchers,” says Zhavoronkov. “I hope their work will inspire other young people excited about science and technology to look at how they can use AI tools to discover new targets and treatments for both aging and disease.”
Identification of dual-purpose therapeutic targets implicated in aging and glioblastoma multiforme using PandaOmics – an AI-enabled biological target discovery platform
Glioblastoma Multiforme (GBM) is the most aggressive and most common primary malignant brain tumor.
The age of GBM patients is considered as one of the disease’s negative prognostic factors and the mean age of diagnosis is 62 years. A promising approach to preventing both GBM and aging is to identify new potential therapeutic targets that are associated with both conditions as concurrent drivers. In this work, we present a multi-angled approach of identifying targets, which takes into account not only the disease-related genes but also the ones important in aging.
For this purpose, we developed three strategies of target identification using the results of correlation analysis augmented with survival data, differences in expression levels and previously published information of aging-related genes. Several studies have recently validated the robustness and applicability of AI-driven computational methods for target identification in both cancer and aging-related diseases.
Therefore, we leveraged the AI predictive power of the PandaOmics TargetID engine in order to rank the resulting target hypotheses and prioritize the most promising therapeutic gene targets.
We propose cyclic nucleotide gated channel subunit alpha 3 (CNGA3), glutamate dehydrogenase 1 (GLUD1) and sirtuin 1 (SIRT1) as potential novel dual-purpose therapeutic targets to treat aging and GBM.