A new AI tool from a Baylor College of Medicine Lab could help better diagnose specific types of autism spectrum disorder, epilepsy and developmental delay disorders. Photo via Getty Images.

One of the hardest parts of any medical condition is waiting for answers. Speeding up an accurate diagnosis can be a doctor’s greatest mercy to a family. A team at Baylor College of Medicine has created technology that may do exactly that.

Led by Dr. Ryan S. Dhindsa, assistant professor of pathology and immunology at Baylor and principal investigator at the Jan and Dan Duncan Neurological Research Institute at Texas Children’s Hospital, the scientists have developed an artificial intelligence-based approach that will help doctors to identify genes tied to neurodevelopmental disorders. Their research was recently published the American Journal of Human Genetics.

According to its website, Dhindsa Lab uses “human genomics, human stem cell models, and computational biology to advance precision medicine.” The diagnoses that stem from the new computational tool could include specific types of autism spectrum disorder, epilepsy and developmental delay, disorders that often don’t come with a genetic diagnosis.

“Although researchers have made major strides identifying different genes associated with neurodevelopmental disorders, many patients with these conditions still do not receive a genetic diagnosis, indicating that there are many more genes waiting to be discovered,” Dhindsa said in a news release.

Typically, scientists must sequence the genes of many people with a diagnosis, as well as people not affected by the disorder, to find new genes associated with a particular disease or disorder. That takes time, money, and a little bit of luck. AI minimizes the need for all three, explains Dhindsa: “We used AI to find patterns among genes already linked to neurodevelopmental diseases and predict additional genes that might also be involved in these disorders.”

The models, made using patterns expressed at the single-cell level, are augmented with north of 300 additional biological features, including data on how intolerant genes are to mutations, whether they interact with other known disease-associated genes, and their functional roles in different biological pathways.

Dhindsa says that these models have exceptionally high predictive value.

“Top-ranked genes were up to two-fold or six-fold, depending on the mode of inheritance, more enriched for high-confidence neurodevelopmental disorder risk genes compared to genic intolerance metrics alone,” he said in the release. “Additionally, some top-ranking genes were 45 to 500 times more likely to be supported by the literature than lower-ranking genes.”

That means that the models may actually validate genes that haven’t yet been proven to be involved in neurodevelopmental conditions. Gene discovery done with the help of AI could possibly become the new normal for families seeking answers beyond umbrella terms like “autism spectrum disorder.”

“We hope that our models will accelerate gene discovery and patient diagnoses, and future studies will assess this possibility,” Dhindsa added.

Baylor Genetics has paired with Baylor’s department of molecular and human genetics to launch the Medical Genetics Multiomics Laboratory with a goal for the collaboration is to turn research into clinical diagnostics. Photo via Getty Images

This new Houston lab is translating genetics research into clinical diagnostics

DNA innovation

A new lab at Baylor College of Medicine is primed to do groundbreaking work in the field of genetics.

Baylor Genetics has paired with Baylor’s department of molecular and human genetics to launch the Medical Genetics Multiomics Laboratory (MGML). The goal for the collaboration is to turn research into clinical diagnostics.

MGML’s freshly launched first clinical test is Whole Transcriptomic RNA Sequencing (WT RNAseq). The new test builds upon the success of existing tests like whole exome sequencing (WES) and whole genome sequencing (WGS) currently on offer from Baylor Genetics by focusing on additional variants that could be missed by the other tests.

Baylor Genetics is offering WT RNAseq to the Undiagnosed Diseases Network (UDN) and its affiliated institutions. For more than a decade, the NIH-funded UDN has united clinical and research experts from across many fields and institutions to give answers to patients with rare genetic diseases. Since it became one of the first institutions to join the UDN in 2014, Baylor Genetics has been the UDN’s sequencing core, using WES, WGS and RNA sequencing to help diagnose patients. The additional offering of WT RNAseq could improve the diagnostic yield by as much as 17 percent.

“This agreement, and the MGML lab, bring to life our vision of innovation, allowing us to co-develop new tests, evaluate in terms of clinical utility, and offer commercially in either a research or clinical setting,” says Dr. Brendan Lee, professor, chair and Robert and Janice McNair Endowed Chair of Molecular and Human Genetics at Baylor College of Medicine, and scientific advisory and board of directors member at Baylor Genetics. “Baylor Genetics is turning around critical high-volume testing, but the challenge is also maintaining our innovative edge and our position as leaders in discovery and genomic health implementation. This agreement is a realization of the vision when Baylor Genetics was founded 10 years ago.”

The lab’s product offerings will continue to expand as it becomes commercially feasible to do so, and the new tests will be used both commercially and clinically.

Baylor Genetics combines the powers of Baylor College of Medicine, which has the NIH’s best-funded department of molecular and human genetics, and Japanese clinical diagnostic testing company H.U. Group Holdings.

Ad Placement 300x100
Ad Placement 300x600

CultureMap Emails are Awesome

Houston startups win NASA funding for space tech projects

fresh funding

Three Houston startups were granted awards from NASA this month to develop new technologies for the space agency.

The companies are among nearly 300 recipients that received a total agency investment of $44.85 million through the Small Business Innovation Research (SBIR) and Small Business Technology Transfer (STTR) Phase I grant programs, according to NASA.

Each selected company will receive $150,000 and, based on their progress, will be eligible to submit proposals for up to $850,000 in Phase II funding to develop prototypes.

The SBIR program lasts for six months and contracts small businesses. The Houston NASA 2025 SBIR awardees include:

Solidec Inc.

  • Principal investigator: Yang Xia
  • Proposal: Highly reliable and energy-efficient electrosynthesis of high-purity hydrogen peroxide from air and water in a nanobubble facilitated porous solid electrolyte reactor

Rarefied Studios LLC

  • Principal investigator: Kyle Higdon
  • Proposal: Plume impingement module for autonomous proximity operations

The STTR program contracts small businesses in partnership with a research institution and lasts for 13 months. The Houston NASA 2025 STTR awardees include:

Affekta LLC

  • Principal investigator: Hedinn Steingrimsson
  • Proposal: Verifiable success in handling unknown unknowns in space habitat simulations and a cyber-physical system

Solidec and Affekta have ties to Rice University.

Solidec extracts molecules from water and air, then transforms them into pure chemicals and fuels that are free of carbon emissions. It was co-founded by Rice professor Haotian Wang and and was an Innovation Fellow at Rice’s Liu Idea Lab for Innovation and Entrepreneurship. It was previouslt selected for Chevron Technology Ventures’ catalyst program, a Rice One Small Step grant, a U.S. Department of Energy grant, and the first cohort of the Activate Houston program.

Affekta, an AI course, AI assistance and e-learning platform, was a part of Rice's OwlSpark in 2023.

Houston energy tech startup Molecule closes series B funding round

Big Bang

Houston-based energy trading risk management (ETRM) software company Molecule has completed a successful series B round for an undisclosed amount, according to a July 16 release from the company.

The raise was led by Sundance Growth, a California-based software growth equity firm.

Sameer Soleja, founder and CEO of Molecule, said in the release that the funding will allow the company to "double down on product innovation, grow our team, and reach even more markets."

Molecule closed a $12 million Series A round in 2021, led by Houston-based Mercury Fund, and has since seen significant growth. The company, which was founded in 2012, has expanded its customer base across the U.S., U.K., Europe, Canada and South America, according to the release.

Additionally, it has launched two new modules of its software platform. Its Hive module, which debuted in 2022, enables clients to manage their energy portfolio and renewable credits together in one scalable platform. It also introduced Elektra, an add-on for the power market to its platform, which allows for complex power market trading.

"Four years ago, we committed to becoming the leading platform for energy trading," Soleja said in the release. "Today, our customers are managing complex power and renewable portfolios across multiple jurisdictions, all within Molecule.”

Molecule is also known for its data-as-a-lake platform, Bigbang, which enables energy ETRM and commodities trading and risk management (CTRM) customers to automatically import trade data from Molecule and then merge it with various sources to conduct queries and analysis.

“Molecule is doing something very few companies in energy tech have done: combining mission-critical depth with cloud-native, scalable technology,” Christian Stewart, Sundance Growth managing director, added in the statement.

“Sameer and his team have built a platform that’s not only powerful, but user-friendly—a rare combination in enterprise software. We’re thrilled to partner with Molecule as they continue to grow and transform the energy trading and risk management market.”

---

This article originally appeared on EnergyCapitalHTX.com.

Rice University professor earns $550k NSF award for wearable imaging tech​

science supported

Another Houston scientist has won one of the highly competitive National Science Foundation (NSF) CAREER Awards.

Lei Li, an assistant professor of electrical and computer engineering at Rice University, has received a $550,000, five-year grant to develop wearable, hospital-grade medical imaging technology capable of visualizing deep tissue function in real-time, according to the NSF. The CAREER grants are given to "early career faculty members who demonstrate the potential to serve as academic models and leaders in research and education."

“This is about giving people access to powerful diagnostic tools that were once confined to hospitals,” Li said in a news release from Rice. “If we can make imaging affordable, wearable and continuous, we can catch disease earlier and treat it more effectively.”

Li’s research focuses on photoacoustic imaging, which merges light and sound to produce high-resolution images of structures deep inside the body. It relies on pulses of laser light that are absorbed by tissue, leading to a rapid temperature rise. During this process, the heat causes the tissue to expand by a fraction, generating ultrasound waves that travel back to the surface and are detected and converted into an image. The process is known to yield more detailed images without dyes or contrast agents used in some traditional ultrasounds.

However, current photoacoustic systems tend to use a variety of sensors, making them bulky, expensive and impractical. Li and his team are taking a different approach.

Instead of using hundreds of separate sensors, Li and his researchers are developing a method that allows a single sensor to capture the same information via a specially designed encoder. The encoder assigns a unique spatiotemporal signature to each incoming sound wave. A reconstruction algorithm then interprets and decodes the signals.

These advances have the potential to lower the size, cost and power consumption of imaging systems. The researchers believe the device could be used in telemedicine, remote diagnostics and real-time disease monitoring. Li’s lab will also collaborate with clinicians to explore how the miniaturized technology could help monitor cancer treatment and other conditions.

“Reducing the number of detection channels from hundreds to one could shrink these devices from bench-top systems into compact, energy-efficient wearables,” Li said in the release. “That opens the door to continuous health monitoring in daily life—not just in hospitals.”

Amanda Marciel, the William Marsh Rice Trustee Chair of chemical and biomolecular engineering and an assistant professor at Rice, received an NSF CAREER Award last year. Read more here.