
High school student researchers discover new brain tumor drug targets using AI
Three high school students – Andrea Olsen from Oslo, Norway; Zachary Harpaz of 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 April 26 in a journal Aging.
Three high school students – Andrea Olsen from Oslo, Norway; Zachary Harpaz of 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 April 26 in a journal Aging.
Olsen, a student at Sevenoaks School in Kent, England, began his internship at Insilico Medicine in 2021, after discovering a passion for neurobiology and technology. For the current paper, the fifth scientific paper he co-authored before turning eighteen, he and other researchers used PandaOmics to sift through datasets from the Gene Expression Omnibus repository maintained by the National Center for Biotechnology Information and find novel therapeutic targets involved to treat both of them. aging and glioblastoma multiforme.
Ren, a student in the International Division of Shanghai High School, has an interest in biology and biomarkers and joins them in the summer of 2022.
While there appears to be a clear link between aging and cancer, Olsen says their findings are more nuanced. “Sometimes, instead of aging, the body switches to cancer mechanisms, which is very interesting to discover.” He hypothesized that “the body tries to defend itself by switching back to the embryonic process of cell division.” GBM is caused by a genetic mutation that causes uncontrolled growth of glial cells, or cells that surround neurons in the brain. Even with existing therapies, the median survival of 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 an interest in biology as well. “I wanted to combine two of my favorite topics, computer science and biology, into the area of biology that I find most exciting – aging research,” said Harpaz. He founded generative AI drug discovery company Insilico Medicine whose founder and CEO, Alex Zhavoronkov, PhD, put him in touch with Olsen. The two young researchers started collaborating on the glioblastoma project and eventually presented their findings at the event Aging Research and Drug Discovery (ARDD) conference in Copenhagen, where they jointly launched the Youth Longevity Association (TYLA).
In this new paper, the three teenagers use PandaOmics to analyze their genes and identify three genes that are strongly correlated with aging and glioblastoma and could serve as potential therapeutic targets for new drugs.
“We selected overlapping genes to be highly correlated in 11 of 12 data sets, and we divided our data into young, middle-aged, and senior cohorts,” said Harpaz. “We mapped this on the importance of gene expression for survival.” After identifying two genetic targets for glioblastoma and aging – CNGA3 and GLUD1 – they cross-referenced their findings with previous findings from Insilico around genes that are strongly correlated with aging and identified a third target – SIRT1.
“I learned a lot about doing research projects,” said Ren, who helped review the three targets. “The PandaOmics platform really made this project accessible to me. As a high school sophomore, I do not have sufficient experience for advanced research and analysis, however, I was still able to navigate the PandaOmics platform after a short training period to process and compare glioblastoma datasets.”
The students said they wanted to continue their studies in AI and biology into college and advance GBM research from target discovery to drug development.
“The best way to take this research further is by using Insilico’s Chemistry42 software, where we can take the targets we identified through PandaOmics and generate small molecule, potential drugs, with these targets that have the potential to treat glioblastoma and aging at a higher level. tall. at the same time,” said Harpaz.
Prior to his internship at Insilico, Olsen said: “I never knew AI could be so helpful in discovering completely new therapeutic targets. For me, it was an amazing opportunity to get into the fields of research, aging, longevity and neuroscience. It really started my whole career.”
“I was very impressed by the commitment of these young researchers,” said Zhavoronkov. “I hope their work will inspire other young people passionate about science and technology to see how they can use AI tools to find new targets and treatments for aging and disease.”
About Insilico Drugs
Insilico Medicine, an end-to-end clinical-stage artificial intelligence (AI)-based drug discovery company, connects biology, chemistry, and clinical trial analysis using next-generation AI systems. The company has developed an AI platform that uses deep generative models, reinforcement learning, transformers and other modern machine learning techniques to find new targets and design new molecular structures with desired properties. Insilico Medicine provides breakthrough solutions for discovering and developing innovative drugs for cancer, fibrosis, immunity, central nervous system (CNS) and aging-related diseases.
For more information, visit www.insilico.com
Research methods
Data/statistical analysis
Article title
Identification of dual-purpose therapeutic targets involved in aging and glioblastoma multiforme using PandaOmics – an AI-enabled biological target discovery platform
Article Publication Date
26-Apr-2023