AI Startup Accelerates Disease Research Using Lab Integration

NewsAI Startup Accelerates Disease Research Using Lab Integration

In a world where neurological disorders affect more than a billion people globally, the pursuit of effective treatments is of paramount importance. These disorders range from the widely recognized Alzheimer’s and Parkinson’s diseases to numerous rare conditions that remain relatively unknown. BrainStorm Therapeutics, a pioneering startup based in San Diego, is at the forefront of developing innovative cures for these neurological conditions. By leveraging cutting-edge technologies such as artificial intelligence (AI) and organoids, they are revolutionizing the drug discovery process.

BrainStorm Therapeutics employs an innovative approach known as “lab in the loop.” This method involves the integration of AI-powered computational drug discovery with laboratory experiments using organoids. Organoids are small, three-dimensional models of brain cells that are derived from patient stem cells. By using this hybrid approach, BrainStorm aims to accelerate drug development by allowing clinical data and AI models to inform each other continuously.

Robert Fremeau, the founder and CEO of BrainStorm Therapeutics, emphasizes that the brain represents the final frontier in modern biology. With a background as a scientific director in neuroscience at Amgen and a faculty member at prestigious institutions like Duke University and the University of California, San Francisco, Fremeau is well-versed in the complexities of brain research. He believes that by combining organoid disease models with generative AI, it becomes possible to unravel the intricate biology underlying disease networks.

One of BrainStorm’s primary goals is to address the high failure rate of drug candidates during clinical trials for brain diseases, which currently exceeds 93%. This alarming statistic is largely due to the limitations of traditional preclinical models, such as those using rodents or two-dimensional cells, which struggle to predict human efficacy. By integrating human-derived brain organoids with AI-driven analysis, BrainStorm is developing a platform that more accurately reflects the complexity of human neurobiology, thereby enhancing the likelihood of clinical success.

Jun Yin, cofounder and chief technology officer at BrainStorm, highlights the potential of their platform to accelerate development timelines, reduce research and development costs, and significantly increase the probability of bringing effective therapies to patients. This innovative approach holds promise for making the development of treatments for both rare and common conditions faster and more economically viable.

BrainStorm Therapeutics’ AI models are powered by NVIDIA GPUs in the cloud, developed using the NVIDIA BioNeMo Framework. This framework consists of programming tools, libraries, and models designed for computational drug discovery. As a member of NVIDIA Inception, a global network of cutting-edge startups, BrainStorm is well-positioned to harness the power of AI and computational resources for drug development.

### Clinical Trial in a Dish

BrainStorm Therapeutics employs AI models to create gene maps of brain diseases, facilitating the identification of promising drug targets and clinical biomarkers. Organoids allow researchers to conduct high-throughput screening of thousands of drug molecules per day directly on human brain cells. This capability enables the testing of potential therapies’ effectiveness before initiating clinical trials.

Maya Gosztyla, the company’s cofounder and chief operating officer, explains that organoids can exhibit spontaneous brain waves, similar to those observed in human brains through electroencephalogram (EEG) scans. This allows BrainStorm to model complex brain activity in a smaller, controlled system, effectively conducting a “clinical trial in a dish” for studying brain diseases.

Currently, BrainStorm Therapeutics is using patient-derived organoids to advance drug discovery for Parkinson’s disease. This condition is linked to the loss of neurons responsible for producing dopamine, a neurotransmitter crucial for physical movement and cognition. By employing AI models to analyze the biological effects of genetic variants associated with Parkinson’s, BrainStorm aims to discover disease-modifying treatments that may slow, halt, or even reverse disease progression.

The BrainStorm team utilizes single-cell sequencing data from brain organoids to fine-tune foundation models available through the BioNeMo Framework, including the Geneformer model for gene expression analysis. These organoids are derived from patients with mutations in the GBA1 gene, the most common genetic risk factor for Parkinson’s disease. BrainStorm is also collaborating with the NVIDIA BioNeMo team to optimize open-source access to the Geneformer model.

### Accelerating Drug Discovery Research

With its proprietary platform, BrainStorm Therapeutics can replicate human brain biology and simulate how different treatments might work in a patient’s brain. This capability allows for rapid and cost-effective narrowing down of therapeutic options. Once AI models suggest potentially effective drugs, organoids are used to test these candidates before proceeding to human trials.

This innovative approach has already led to significant discoveries. For instance, BrainStorm found that Donepezil, a drug typically prescribed for Alzheimer’s disease, could also be effective in treating Rett syndrome, a rare genetic neurodevelopmental disorder. Within just nine months, the team progressed from organoid screening to applying for a phase 2 clinical trial of the drug in Rett patients. The U.S. Food and Drug Administration recently cleared this application.

BrainStorm also plans to develop multimodal AI models that integrate data from various sources, including cell sequencing, cell imaging, EEG scans, and more. This comprehensive approach is crucial for designing effective drugs and understanding diseases better.

As Yin points out, high-quality, multimodal input data is essential for developing the right drugs. AI models trained on such data can help identify more effective drug candidates and prognostic biomarkers for specific patients, ultimately enabling precision medicine.

Looking ahead, BrainStorm’s next project involves collaborating with the CURE5 Foundation to conduct an extensive repurposed drug screen for CDKL5 Deficiency Disorder, another rare genetic neurodevelopmental condition. This initiative underscores the transformative potential of rare disease research, turning it from a high-risk niche into a dynamic frontier.

According to Fremeau, integrating BrainStorm’s AI-powered organoid technology with NVIDIA’s accelerated computing resources and the BioNeMo platform is dramatically accelerating innovation while reducing costs. What once required a decade and billions of dollars can now be investigated with significantly leaner resources in a matter of months.

For those interested in exploring AI-accelerated drug discovery further, NVIDIA BioNeMo offers a valuable starting point. By continuing to push the boundaries of technology and biology, BrainStorm Therapeutics is paving the way for a brighter future in the treatment of neurological disorders.
For more Information, Refer to this article.

Neil S
Neil S
Neil is a highly qualified Technical Writer with an M.Sc(IT) degree and an impressive range of IT and Support certifications including MCSE, CCNA, ACA(Adobe Certified Associates), and PG Dip (IT). With over 10 years of hands-on experience as an IT support engineer across Windows, Mac, iOS, and Linux Server platforms, Neil possesses the expertise to create comprehensive and user-friendly documentation that simplifies complex technical concepts for a wide audience.
Watch & Subscribe Our YouTube Channel
YouTube Subscribe Button

Latest From Hawkdive

You May like these Related Articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.