{"id":3971,"date":"2025-04-22T14:42:28","date_gmt":"2025-04-22T14:42:28","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2025\/04\/22\/making-brain-waves-ai-startup-speeds-disease-research-with-lab-in-the-loop\/"},"modified":"2025-04-22T14:42:28","modified_gmt":"2025-04-22T14:42:28","slug":"making-brain-waves-ai-startup-speeds-disease-research-with-lab-in-the-loop","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2025\/04\/22\/making-brain-waves-ai-startup-speeds-disease-research-with-lab-in-the-loop\/","title":{"rendered":"Making Brain Waves: AI Startup Speeds Disease Research With Lab in the Loop"},"content":{"rendered":"
\n\t\t<\/span> <\/span> <\/span><\/span><\/p>\n

About 15% of the world\u2019s population<\/a> \u2014 over a billion people \u2014 are affected by neurological disorders, from commonly known diseases like Alzheimer\u2019s and Parkinson\u2019s to hundreds of lesser-known, rare conditions.<\/p>\n

BrainStorm Therapeutics<\/a>, a San Diego-based startup, is accelerating the development of cures for these conditions using AI-powered computational drug discovery paired with lab experiments using organoids: tiny, 3D bundles of brain cells created from patient-derived stem cells. This hybrid, iterative method, where clinical data and AI models inform one another to accelerate drug development, is known as lab in the loop.<\/p>\n

\u201cThe brain is the last frontier in modern biology,\u201d said BrainStorm\u2019s founder and CEO Robert Fremeau, who was previously a scientific director in neuroscience at Amgen and a faculty member at Duke University and the University of California, San Francisco. \u201cBy combining our organoid disease models with the power of generative AI, we now have the ability to start to unravel the underlying complex biology of disease networks.\u201d<\/p>\n

The company aims to lower the failure rate of drug candidates for brain diseases during clinical trials \u2014 currently over 93%<\/a> \u2014 and identify therapeutics that can be applied to multiple diseases. Achieving these goals would make it faster and more economically viable to develop treatments for rare and common conditions.<\/p>\n

\u201cThis alarmingly high clinical trial failure rate is mainly due to the inability of traditional preclinical models with rodents or 2D cells to predict human efficacy,\u201d said Jun Yin, cofounder and chief technology officer at BrainStorm. \u201cBy integrating human-derived brain organoids with AI-driven analysis, we\u2019re building a platform that better reflects the complexity of human neurobiology and improves the likelihood of clinical success.\u201d<\/p>\n

Fremeau and Yin believe that BrainStorm\u2019s platform has the potential to accelerate development timelines, reduce research and development costs, and significantly increase the probability of bringing effective therapies to patients.<\/p>\n

BrainStorm Therapeutics\u2019 AI models, which run on NVIDIA GPUs in the cloud<\/a>, were developed using the NVIDIA BioNeMo Framework<\/a>, a set of programming tools, libraries and models for computational drug discovery. The company is a member of NVIDIA Inception<\/a>, a global network of cutting-edge startups.<\/p>\n<\/p>\n

Clinical Trial in a Dish<\/b><\/h2>\n

BrainStorm Therapeutics uses AI models to develop gene maps of brain diseases, which they can use to identify promising targets for potential drugs and clinical biomarkers. Organoids allow them to screen thousands of drug molecules per day directly on human brain cells, enabling them to test the effectiveness of potential therapies before starting clinical trials.<\/p>\n

\u201cBrains have brain waves that can be picked up in a scan like an EEG, or electroencephalogram, which measures the electrical activity of neurons,\u201d said Maya Gosztyla, the company\u2019s cofounder and chief operating officer. \u201cOur organoids also have spontaneous brain waves, allowing us to model the complex activity that you would see in the human brain in this much smaller system. We treat it like a clinical trial in a dish for studying brain diseases.\u201d<\/p>\n

BrainStorm Therapeutics is currently using patient-derived organoids for its work on drug discovery for Parkinson\u2019s disease, a condition tied to the loss of neurons that produce dopamine, a neurotransmitter that helps with physical movement and cognition.<\/p>\n

\"\"<\/p>\n

\u201cIn Parkinson\u2019s disease, multiple genetic variants contribute to dysfunction across different cellular pathways, but they converge on a common outcome \u2014 the loss of dopamine neurons,\u201d Fremeau said. \u201cBy using AI models to map and analyze the biological effects of these variants, we can discover disease-modifying treatments that have the potential to slow, halt or even reverse the progression of Parkinson\u2019s.\u201d<\/p>\n

The BrainStorm team used single-cell sequencing data from brain organoids to fine-tune foundation models available through the BioNeMo Framework, including the Geneformer<\/a> model for gene expression analysis. The organoids were derived from patients with mutations in the GBA1 gene, the most common genetic risk factor for Parkinson\u2019s disease.<\/p>\n

BrainStorm is also collaborating with the NVIDIA BioNeMo team to help optimize open-source access to the Geneformer model.<\/p>\n

Accelerating Drug Discovery Research<\/b><\/h2>\n

With its proprietary platform, BrainStorm can mirror human brain biology and simulate how different treatments might work in a patient\u2019s brain.<\/p>\n

\u201cThis can be done thousands of times, much quicker and much cheaper than can be done in a wet lab \u2014 so we can narrow down therapeutic options very quickly,\u201d Gosztyla said. \u201cThen we can go in with organoids and test the subset of drugs the AI model thinks will be effective. Only after it gets through those steps will we actually test these drugs in humans.\u201d<\/p>\n

\"\"
View of an organoid using Fluorescence Imaging Plate Reader, or FLIPR \u2014 a technique used to study the effect of compounds on cells during drug screening.<\/figcaption><\/figure>\n

This technology led to the discovery that Donepezil, a drug prescribed for Alzheimer\u2019s disease, could also be effective in treating Rett syndrome, a rare genetic neurodevelopmental disorder. Within nine months, the BrainStorm team was able to go from organoid screening to applying for a phase 2 clinical trial of the drug in Rett patients. This application was recently cleared by the U.S. Food and Drug Administration.<\/p>\n

BrainStorm also plans to develop multimodal AI models that integrate data from cell sequencing, cell imaging, EEG scans and more.<\/p>\n

\u201cYou need high-quality, multimodal input data to design the right drugs,\u201d said Yin. \u201cAI models trained on this data will help us understand disease better, find more effective drug candidates and, eventually, find prognostic biomarkers for specific patients that enable the delivery of precision medicine.\u201d<\/p>\n

The company\u2019s next project is an initiative with the CURE5 Foundation<\/a> to conduct the most comprehensive repurposed drug screen to date for CDKL5 Deficiency Disorder, another rare genetic neurodevelopmental disorder.<\/p>\n

\u201cRare disease research is transforming from a high-risk niche to a dynamic frontier,\u201d said Fremeau. \u201cThe integration of BrainStorm\u2019s AI-powered organoid technology with NVIDIA accelerated computing resources and the NVIDIA BioNeMo platform is dramatically accelerating the pace of innovation while reducing the cost \u2014 so what once required a decade and billions of dollars can now be investigated with significantly leaner resources in a matter of months.\u201d<\/p>\n

Get started with <\/i>NVIDIA BioNeMo<\/i><\/a> for AI-accelerated drug discovery.<\/i><\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/brain-disease-ai-lab-in-the-loop\/<\/p>\n","protected":false},"author":0,"featured_media":3972,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3971"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=3971"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/3971\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/3972"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=3971"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=3971"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=3971"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}