Houston researchers create AI model to tap into how brain activity relates to illness

brainiac

BrainLM is now well-trained enough to use to fine-tune a specific task and to ask questions in other studies. Photo via Getty Images

Houston researchers are part of a team that has created an AI model intended to understand how brain activity relates to behavior and illness.

Scientists from Baylor College of Medicine worked with peers from Yale University, University of Southern California and Idaho State University to make Brain Language Model, or BrainLM. Their research was published as a conference paper at ICLR 2024, a meeting of some of deep learning’s greatest minds.

“For a long time we’ve known that brain activity is related to a person’s behavior and to a lot of illnesses like seizures or Parkinson’s,” Dr. Chadi Abdallah, associate professor in the Menninger Department of Psychiatry and Behavioral Sciences at Baylor and co-corresponding author of the paper, says in a press release. “Functional brain imaging or functional MRIs allow us to look at brain activity throughout the brain, but we previously couldn’t fully capture the dynamic of these activities in time and space using traditional data analytical tools.

"More recently, people started using machine learning to capture the brain complexity and how it relates it to specific illnesses, but that turned out to require enrolling and fully examining thousands of patients with a particular behavior or illness, a very expensive process,” Abdallah continues.

Using 80,000 brain scans, the team was able to train their model to figure out how brain activities related to one another. Over time, this created the BrainLM brain activity foundational model. BrainLM is now well-trained enough to use to fine-tune a specific task and to ask questions in other studies.

Abdallah said that using BrainLM will cut costs significantly for scientists developing treatments for brain disorders. In clinical trials, it can cost “hundreds of millions of dollars,” he said, to enroll numerous patients and treat them over a significant time period. By using BrainLM, researchers can enroll half the subjects because the AI can select the individuals most likely to benefit.

The team found that BrainLM performed successfully in many different samples. That included predicting depression, anxiety and PTSD severity better than other machine learning tools that do not use generative AI.

“We found that BrainLM is performing very well. It is predicting brain activity in a new sample that was hidden from it during the training as well as doing well with data from new scanners and new population,” Abdallah says. “These impressive results were achieved with scans from 40,000 subjects. We are now working on considerably increasing the training dataset. The stronger the model we can build, the more we can do to assist with patient care, such as developing new treatment for mental illnesses or guiding neurosurgery for seizures or DBS.”

For those suffering from neurological and mental health disorders, BrainLM could be a key to unlocking treatments that will make a life-changing difference.

This Houston startup has a game-changing technology for deep learning. Photo via Getty Images

Houston artificial intelligence startup raises $6M in seed funding

money moves

A computer science professor at Rice University has raised seed funding last month in order to grow his company that's focused on democratizing artificial intelligence tools.

ThirdAI, founded by Anshumali Shrivastava in April, raised $6 million in a seed funding round from three California-based VCs — Neotribe Ventures and Cervin Ventures, which co-led the round with support from Firebolt Ventures.

Shrivastava, CEO, co-founded the company with Tharun Medini, a recent Ph.D. who graduated under Shrivastava from Rice's Department of Electrical and Computer Engineering. Medini serves as the CTO of ThirdAI — pronounced "third eye." The startup is building the next generation of scalable and sustainable AI tools and deep learning systems.

"We are democratizing artificial intelligence through software innovations," says Shrivastava in a news release from Rice. "Our innovation would not only benefit current AI training by shifting to lower-cost CPUs, but it should also allow the 'unlocking' of AI training workloads on GPUs that were not previously feasible."

The technology ThirdAI is working with comes from 10 years of deep learning research and innovation. The company's technology has the potential to make computing 15-times faster.

"ThirdAI has developed a breakthrough approach to train deep learning models with a large number of parameters that run efficiently on general purpose CPUs. This technology has the potential to result in a gigantic leap forward in the accuracy of deep learning models," per and announcement from Cervin Ventures. "Our investment in ThirdAI was a no-brainer and we are fortunate to have had the opportunity to invest."

Anshumali Shrivastava is an associate professor of computer science at Rice University. Photo via rice.edu

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

Property Showcase

5 Houston scientists named winners of prestigious Hill Prizes 2026

prized research

Five Houston scientists were recognized for their "high-risk, high-reward ideas and innovations" by Lyda Hill Philanthropies and the Texas Academy of Medicine, Engineering, Science and Technology (TAMEST).

The 2026 Hill Prizes provide seed funding to top Texas researchers. This year's prizes were given out in seven categories, including biological sciences, engineering, medicine, physical sciences, public health and technology, and the new artificial intelligence award.

Each recipient’s institution or organization will receive $500,000 in direct funding from Dallas-based Lyda Hill Philanthropies. The organization has also committed to giving at least $1 million in discretionary research funding on an ad hoc basis for highly-ranked applicants who were not selected as recipients.

“It is with great pride that I congratulate this year’s Hill Prizes recipients. Their pioneering spirit and unwavering dedication to innovation are addressing some of the most pressing challenges of our time – from climate resilience and energy sustainability to medical breakthroughs and the future of artificial intelligence,” Lyda Hill, founder of Lyda Hill Philanthropies, said in a news release.

The 2026 Houston-area recipients include:

Biological Sciences: Susan M. Rosenberg, Baylor College of Medicine

Rosenberg and her team are developing ways to fight antibiotic resistance. The team will use the funding to screen a 14,000-compound drug library to identify additional candidates, study their mechanisms and test their ability to boost antibiotic effectiveness in animal models. The goal is to move toward clinical trials, beginning with veterans suffering from recurrent infections.

Medicine: Dr. Raghu Kalluri, The University of Texas MD Anderson Cancer Center

Kalluri is developing eye drops to treat age-related macular degeneration (AMD), the leading cause of vision loss globally. Kalluri will use the funding to accelerate studies and support testing for additional ocular conditions. He was also named to the National Academy of Inventors’ newest class of fellows last month.

Engineering: Naomi J. Halas, Rice University

Co-recipeints: Peter J. A. Nordlander and Hossein Robatjazi, Rice University

Halas and her team are working to advance light-driven technologies for sustainable ammonia synthesis. The team says it will use the funding to improve light-driven catalysts for converting nitrogen into ammonia, refine prototype reactors for practical deployment and partner with industry collaborators to advance larger-scale applications. Halas and Nordlander are co-founders of Syzygy Plasmonics, and Robatjazi serves as vice president of research for the company.

The other Texas-based recipients include:

  • Artificial Intelligence: Kristen Grauman, The University of Texas at Austin
  • Physical Sciences: Karen L. Wooley, Texas A&M University; Co-Recipient: Matthew Stone, Teysha Technologies
  • Public Health: Dr. Elizabeth C. Matsui, The University of Texas at Austin and Baylor College of Medicine
  • Technology: Kurt W. Swogger, Molecular Rebar Design LLC; Co-recipients: Clive Bosnyak, Molecular Rebar Design, and August Krupp, MR Rubber Business and Molecular Rebar Design LLC

Recipients will be recognized Feb. 2 during the TAMEST 2026 Annual Conference in San Antonio. They were determined by a committee of TAMEST members and endorsed by a committee of Texas Nobel and Breakthrough Prize Laureates and approved by the TAMEST Board of Directors.

“On behalf of TAMEST, we are honored to celebrate the 2026 Hill Prizes recipients. These outstanding innovators exemplify the excellence and ambition of Texas science and research,” Ganesh Thakur, TAMEST president and a distinguished professor at the University of Houston, added in the release. “Thanks to the visionary support of Lyda Hill Philanthropies, the Hill Prizes not only recognize transformative work but provide the resources to move bold ideas from the lab to life-changing solutions. We are proud to support their journeys and spotlight Texas as a global hub for scientific leadership.”

Investment bank opens new Houston office focused on energy sector

Investment bank Cohen & Co. Capital Markets has opened a Houston office to serve as the hub of its energy advisory business and has tapped investment banking veteran Rahul Jasuja as the office’s leader.

Jasuja joined Cohen & Co. Capital Markets, a subsidiary of financial services company Cohen & Co., as managing director, and head of energy and energy transition investment banking. Cohen’s capital markets arm closed $44 billion worth of deals last year.

Jasuja previously worked at energy-focused Houston investment bank Mast Capital Advisors, where he was managing director of investment banking. Before Mast Capital, Jasuja was director of energy investment banking in the Houston office of Wells Fargo Securities.

“Meeting rising [energy] demand will require disciplined capital allocation across traditional energy, sustainable fuels, and firm, dispatchable solutions such as nuclear and geothermal,” Jasuja said in a news release. “Houston remains the center of gravity where capital, operating expertise, and execution come together to make that transition investable.”

The Houston office will focus on four energy verticals:

  • Energy systems such as nuclear and geothermal
  • Energy supply chains
  • Energy-transition fuel and technology
  • Traditional energy
“We are making a committed investment in Houston because we believe the infrastructure powering AI, defense, and energy transition — from nuclear to rare-earth technology — represents the next secular cycle of value creation,” Jerry Serowik, head of Cohen & Co. Capital Markets, added in the release.

---

This article originally appeared on EnergyCaptialHTX.com.

MD Anderson makes AI partnership to advance precision oncology

AI Oncology

Few experts will disagree that data-driven medicine is one of the most certain ways forward for our health. However, actually adopting it comes at a steep curve. But what if using the technology were democratized?

This is the question that SOPHiA GENETICS has been seeking to answer since 2011 with its universal AI platform, SOPHiA DDM. The cloud-native system analyzes and interprets complex health care data across technologies and institutions, allowing hospitals and clinicians to gain clinically actionable insights faster and at scale.

The University of Texas MD Anderson Cancer Center has just announced its official collaboration with SOPHiA GENETICS to accelerate breakthroughs in precision oncology. Together, they are developing a novel sequencing oncology test, as well as creating several programs targeted at the research and development of additional technology.

That technology will allow the hospital to develop new ways to chart the growth and changes of tumors in real time, pick the best clinical trials and medications for patients and make genomic testing more reliable. Shashikant Kulkarni, deputy division head for Molecular Pathology, and Dr. J. Bryan, assistant professor, will lead the collaboration on MD Anderson’s end.

“Cancer research has evolved rapidly, and we have more health data available than ever before. Our collaboration with SOPHiA GENETICS reflects how our lab is evolving and integrating advanced analytics and AI to better interpret complex molecular information,” Dr. Donna Hansel, division head of Pathology and Laboratory Medicine at MD Anderson, said in a press release. “This collaboration will expand our ability to translate high-dimensional data into insights that can meaningfully advance research and precision oncology.”

SOPHiA GENETICS is based in Switzerland and France, and has its U.S. offices in Boston.

“This collaboration with MD Anderson amplifies our shared ambition to push the boundaries of what is possible in cancer research,” Dr. Philippe Menu, chief product officer and chief medical officer at SOPHiA GENETICS, added in the release. “With SOPHiA DDM as a unifying analytical layer, we are enabling new discoveries, accelerating breakthroughs in precision oncology and, most importantly, enabling patients around the globe to benefit from these innovations by bringing leading technologies to all geographies quickly and at scale.”

View All Listings