Collaborating Authors

San Diego County

Boffins build AI to identify genetic mutations • The Register


Machine learning techniques, such as deep learning, have proven surprisingly effective at identifying diseases like breast cancer. However, when it comes to identifying mutations at the genetic level, these models have come up short, according to researchers at the University of California San Diego (UCSD). In a paper published in the journal Nature Biotechnology this week, researchers at the university propose a new machine learning framework called DeepMosaic that uses a combination of image-based visualization and deep learning models to identify genetic mutations associated with diseases including cancer and disorders with genetic links, such as autism spectrum disorder. Using AI/ML to identify disease has been a hot topic in recent years. The problem, according to UCSD professor Joe Gleeson, is most of these models aren't well suited to identifying genetic mutations, called mosaic variants or mutations, because most of the software developed over the last two decades was trained on cancer samples. Because cancer cells divide so rapidly, they're relatively easy to spot for computer programs, he explained in an interview with The Register.

Meet DeepMosaic: A Computer Program that 'Learns' to Identify Mosaic Mutations Causing Disease - CBIRT


Scientists from the University of California San Diego School of Medicine and Rady Children's Institute for Genomic Medicine have developed a method for identifying mosaic mutations using deep learning. The process involves training a model to analyze large amounts of genomic data and recognize patterns associated with mosaic mutations. The researchers hope that this approach will help increase our understanding of the genetic basis of disease and lead to the development of more effective treatments. Genetic mutations can lead to a wide range of disorders that are often difficult to treat or understand. One type of mutation, called mosaic mutations, is particularly challenging to identify because it only affects a small percentage of cells.

New computer program 'learns' to identify mosaic mutations that cause disease


Genetic mutations cause hundreds of unsolved and untreatable disorders. Among them, DNA mutations in a small percentage of cells, called mosaic mutations, are extremely difficult to detect because they exist in a tiny percentage of the cells. Current DNA mutation software detectors, while scanning the 3 billion bases of the human genome, are not well suited to discern mosaic mutations hiding among normal DNA sequences. Often medical geneticists must review DNA sequences by eye to try to identify or confirm mosaic mutations--a time-consuming endeavor fraught with the possibility of error. Writing in the January 2, 2023, issue of Nature Biotechnology, researchers from the University of California San Diego School of Medicine and Rady Children's Institute for Genomic Medicine describe a method for teaching a computer how to spot mosaic mutations using an artificial intelligence approach termed "deep learning."

The Overlooked Upsides of Algorithms in the Workplace


Orly Lobel believes technology can make the world a better place--and she knows in 2022, that makes her a bit of a contrarian. Lobel, a law professor specializing in labor and employment at the University of San Diego in California, has studied how technology and the gig economy affects workers. That has made her familiar with the potential disruptions caused by tools like automated résumé screening and apps that use algorithms to assign work to people. Yet Lobel feels discussion about automation and AI is too stuck on the harms these systems create. In her book The Equality Machine: Harnessing Digital Technology for a Brighter, More Inclusive Future, Lobel encourages a sunnier view.

TuSimple Plans Layoffs WSJD - Technology

Self-driving trucking company TuSimple Holdings Inc. plans to cut potentially at least half of its workforce next week, people familiar with the matter said, as it scales back efforts to build and test autonomous truck-driving systems. A staff reduction of that size would likely affect at least 700 employees, the people said. As of June, TuSimple had 1,430 full-time employees globally. It has operations in San Diego, Arizona, Texas and China.

Startup Shield AI lands $60M to build artificial intelligence 'pilots' for military aircraft


Shield AI, a San Diego startup that's building artificial intelligence "pilots" for military aircraft and drones, has pulled in an additional $60 million in venture capital funding. The money is follow-on investment to a financing that Shield AI announced in June. It brings the total amount raised in the Series E round to $225 million -- made up of $150 million in equity and $75 million in debt. The additional capital came from the U.S. Innovative Technology Fund. Founded in 2015, Shield AI has raised just under $575 million since inception.

AI invents millions of materials that don't yet exist


Scientists have developed an artificial intelligence algorithm capable of predicting the structure and properties of more than 31 million materials that do not yet exist. The AI tool, named M3GNet, could lead to the discovery of new materials with exceptional properties, according to the team from the University of California San Diego who created it. M3GNet was able to populate a vast database of yet-to-be-synthesized materials instantaneously, which the engineers are already using in their hunt for more energy-dense electrodes for lithium-ion batteries used in everything from smartphones to electric cars. UC San Diego nanoengineering professor Shyue Ping Ong described M3GNet as "an AlphaFold for materials", referring to the breakthrough AI algorithm built by Google's DeepMind that can predict protein structures. "Similar to proteins, we need to know the structure of a material to predict its properties," said Professor Ong.

Breakthrough algorithm expands the exploration space for materials by orders of magnitude


Nanoengineers at the University of California San Diego's Jacobs School of Engineering have developed an AI algorithm that predicts the structure and dynamic properties of any material--whether existing or new--almost instantaneously. Known as M3GNet, the algorithm was used to develop, The project is explored in the Nov. 28 issue of the journal Nature Computational Science. The properties of a material are determined by the arrangement of its atoms. However, existing approaches to obtain that arrangement are either prohibitively expensive or ineffective for many elements.

Artificial Neural Networks Learn Better When They Spend Time Not Learning at All - Neuroscience News


Summary: "Off-line" periods during AI training mitigated "catastrophic forgetting" in artificial neural networks, mimicking the learning benefits sleep provides in the human brain. Depending on age, humans need 7 to 13 hours of sleep per 24 hours. During this time, a lot happens: Heart rate, breathing and metabolism ebb and flow; hormone levels adjust; the body relaxes. "The brain is very busy when we sleep, repeating what we have learned during the day," said Maxim Bazhenov, PhD, professor of medicine and a sleep researcher at University of California San Diego School of Medicine. "Sleep helps reorganize memories and presents them in the most efficient way."