Experts Matter. Find Yours.
Connect for media, speaking, professional opportunities & more.
UF team develops AI tool to make genetic research more comprehensive
University of Florida researchers are addressing a critical gap in medical genetic research — ensuring it better represents and benefits people of all backgrounds. Their work, led by Kiley Graim, Ph.D., an assistant professor in the Department of Computer & Information Science & Engineering, focuses on improving human health by addressing "ancestral bias" in genetic data, a problem that arises when most research is based on data from a single ancestral group. This bias limits advancements in precision medicine, Graim said, and leaves large portions of the global population underserved when it comes to disease treatment and prevention. To solve this, the team developed PhyloFrame, a machine-learning tool that uses artificial intelligence to account for ancestral diversity in genetic data. With funding support from the National Institutes of Health, the goal is to improve how diseases are predicted, diagnosed, and treated for everyone, regardless of their ancestry. A paper describing the PhyloFrame method and how it showed marked improvements in precision medicine outcomes was published Monday in Nature Communications. Graim, a member of the UF Health Cancer Center, said her inspiration to focus on ancestral bias in genomic data evolved from a conversation with a doctor who was frustrated by a study's limited relevance to his diverse patient population. This encounter led her to explore how AI could help bridge the gap in genetic research. “If our training data doesn’t match our real-world data, we have ways to deal with that using machine learning. They’re not perfect, but they can do a lot to address the issue.” —Kiley Graim, Ph.D., an assistant professor in the Department of Computer & Information Science & Engineering and a member of the UF Health Cancer Center “I thought to myself, ‘I can fix that problem,’” said Graim, whose research centers around machine learning and precision medicine and who is trained in population genomics. “If our training data doesn’t match our real-world data, we have ways to deal with that using machine learning. They’re not perfect, but they can do a lot to address the issue.” By leveraging data from population genomics database gnomAD, PhyloFrame integrates massive databases of healthy human genomes with the smaller datasets specific to diseases used to train precision medicine models. The models it creates are better equipped to handle diverse genetic backgrounds. For example, it can predict the differences between subtypes of diseases like breast cancer and suggest the best treatment for each patient, regardless of patient ancestry. Processing such massive amounts of data is no small feat. The team uses UF’s HiPerGator, one of the most powerful supercomputers in the country, to analyze genomic information from millions of people. For each person, that means processing 3 billion base pairs of DNA. “I didn’t think it would work as well as it did,” said Graim, noting that her doctoral student, Leslie Smith, contributed significantly to the study. “What started as a small project using a simple model to demonstrate the impact of incorporating population genomics data has evolved into securing funds to develop more sophisticated models and to refine how populations are defined.” What sets PhyloFrame apart is its ability to ensure predictions remain accurate across populations by considering genetic differences linked to ancestry. This is crucial because most current models are built using data that does not fully represent the world’s population. Much of the existing data comes from research hospitals and patients who trust the health care system. This means populations in small towns or those who distrust medical systems are often left out, making it harder to develop treatments that work well for everyone. She also estimated 97% of the sequenced samples are from people of European ancestry, due, largely, to national and state level funding and priorities, but also due to socioeconomic factors that snowball at different levels – insurance impacts whether people get treated, for example, which impacts how likely they are to be sequenced. “Some other countries, notably China and Japan, have recently been trying to close this gap, and so there is more data from these countries than there had been previously but still nothing like the European data," she said. “Poorer populations are generally excluded entirely.” Thus, diversity in training data is essential, Graim said. "We want these models to work for any patient, not just the ones in our studies," she said. “Having diverse training data makes models better for Europeans, too. Having the population genomics data helps prevent models from overfitting, which means that they'll work better for everyone, including Europeans.” Graim believes tools like PhyloFrame will eventually be used in the clinical setting, replacing traditional models to develop treatment plans tailored to individuals based on their genetic makeup. The team’s next steps include refining PhyloFrame and expanding its applications to more diseases. “My dream is to help advance precision medicine through this kind of machine learning method, so people can get diagnosed early and are treated with what works specifically for them and with the fewest side effects,” she said. “Getting the right treatment to the right person at the right time is what we’re striving for.” Graim’s project received funding from the UF College of Medicine Office of Research’s AI2 Datathon grant award, which is designed to help researchers and clinicians harness AI tools to improve human health.
Florida Tech Shark Biologist Stars in National Geographic Program on Shark Attacks
Toby Daly-Engel, the distinguished shark biologist and director of Florida Tech’s Shark Conservation Lab, is a featured expert on “When Sharks Attack…and Why,” an eight-episode program debuting this week as part of National Geographic’s SharkFest 2023. The series debuts July 6 at 9 p.m. Eastern on National Geographic with new episodes airing nightly through July 12. It is also now streaming on Disney+, Hulu and the National Geographic website. The series will air on Nat Geo Wild starting July 26 at 8 p.m. Eastern. As its name suggests, “When Sharks Attack…and Why” investigates shark encounters in America and around the world. “Many attacks are appearing in new and surprising places,” the network notes. Episodes explore incidents in New York, California, Hawaii, Indonesia, Australia and elsewhere. At Florida Tech, Daly-Engel conducts research using a combination of genomics, field ecology and modeling to study shark mating systems and habitat use, and the impacts of climate change on shark populations. On the program, she is our expert guide to anatomical and physiological aspects of sharks, many of which are unique to this species. We first meet Daly-Engel in Episode 1, New York Nightmare. Filmed in her lab, she talks viewers through key parts of a shark’s body using a small dogfish shark. She tells viewers that while a shark’s sense of smell is often touted, these apex predators also have powerful hearing, far better than humans. (In a later episode, she notes a shark’s vision in murky waters is about 10 times stronger than human vision in those conditions.) “I really enjoyed delving into the science behind shark-human interactions,” Daly-Engel said, “and busting the myths that make people afraid of the water.” Daly-Engel is no stranger to SharkFest. Last year she was featured in another SharkFest series, “Shark Attack File,” and she has been on SharkFest and Discovery’s Shark Week programing multiple times, including 2021 when she appeared on three programs across both networks. Looking to know more about shark encounters and attacks? Then let us help with your coverage and questions. Toby Daly-Engel is an assistant professor in the Department of Ocean Engineering and Marine Sciences department at Florida Tech. He's available to speak with media about this topic - simply click on his icon now to arrange an interview today.
• Has potential to help geneticists investigate vital issues such as antibacterial resistance • Will untangle the genetic components shared due to common ancestry from the ones shared due to evolution • The work is result of a four-year international collaboration. Aston University has worked with international partners to develop a software package to help scientists answer key questions about genetic factors associated with shared characteristics among different species. Called CALANGO (comparative analysis with annotation-based genomic components), it has the potential to help geneticists investigate vital issues such as antibacterial resistance and improvement of agricultural crops. This work CALANGO: a phylogeny-aware comparative genomics tool for discovering quantitative genotype-phenotype associations across species has been published in the journal Patterns. It is the result of a four year collaboration between Aston University, the Federal University of Minas Gerais in Brazil and other partners in Brazil, Norway and the US. Similarities between species may arise either from shared ancestry (homology) or from shared evolutionary pressures (convergent evolution). For example, ravens, pigeons and bats can all fly, but the first two are birds whereas bats are mammals. This means that the biology of flight in ravens and pigeons is likely to share genetic aspects due to their common ancestry. Both species are able to fly nowadays because their last common ancestor – an ancestor bird - was also a flying organism. In contrast, bats have the ability to fly via potentially different genes than the ones in birds, since the last common ancestor of birds and mammals was not a flying animal. Untangling the genetic components shared due to common ancestry from the ones shared due to common evolutionary pressures requires sophisticated statistical models that take common ancestry into account. So far, this has been an obstacle for scientists who want to understand the emergence of complex traits across different species, mainly due to the lack of proper frameworks to investigate these associations. The new software has been designed to effectively incorporate vast amounts of genomic, evolutionary and functional annotation data to explore the genetic mechanisms which underly similar characteristics between different species sharing common ancestors. Although the statistical models used in the tool are not new, it is the first time they have been combined to extract novel biological insights from genomic data. The technique has the potential to be applied to many different areas of research, allowing scientists to analyse massive amounts of open-source genetic data belonging to thousands of organisms in more depth. Dr Felipe Campelo from the Department of Computer Science in the College of Engineering and Physical Sciences at Aston University, said: “There are many exciting examples of how this tool can be applied to solve major problems facing us today. These include exploring the co-evolution of bacteria and bacteriophages and unveiling factors associated with plant size, with direct implications for both agriculture and ecology.” “Further potential applications include supporting the investigation of bacterial resistance to antibiotics, and of the yield of plant and animal species of economic importance.” The corresponding author of the study, Dr Francisco Pereira Lobo from the Department of Genetics, Ecology and Evolution at the Federal University of Minas Gerais in Brazil, said: “Most genetic and phenotypic variations occur between different species, rather than within them. Our newly developed tool allows the generation of testable hypotheses about genotype-phenotype associations across multiple species that enable the prioritisation of targets for later experimental characterization.” For more details about studying computer since at Aston University visit https://www.aston.ac.uk/eps/informatics-and-digital-engineering/computer-science
New research suggests model organisms may have evolved too far
A research team from Aston University and the Universities of Birmingham and Nottingham suggest model organisms evolved over 100 years may no longer be fit for purpose They found the bacterial strain Escherichia coli K-12 has been repeatedly cultured and mutated, resulting in many genetic changes The study has just been published in Microbial Genomics A research team from Aston University has found that the model organism used in laboratories for the past 100 years has evolved so extensively that it may no longer be fit for purpose. According to a new study, published in Microbial Genomics, the bacterial strain Escherichia coli K-12 has been repeatedly cultured and mutated, resulting in an organism that carries many genetic changes compared to the original isolated bacteria. The research team, from Aston University, and the Universities of Birmingham and Nottingham, made their discovery after re-examining the early preserved samples and looking at the base sequence of their DNA. They found a large number of differences at the DNA sequence level, and the differences are bigger when they examined currently used stocks that derived from the original samples. The work underscores the dangers of using one strain as a sole model. It also confirms that bacterial sequences evolve over short time scales and provides a fascinating insight into the first baby steps of molecular microbiology. Lead author Dr Doug Browning, of the School of Biosciences at Aston University, said: “The past 10 years have seen a massive amount of bacterial genome sequencing and the picture that is emerging is that bacterial genomes change very fast. This was unimaginable 100 years ago, and, of course, this is why folk back then were quick to adopt the K-12 strain as the model for everything.” The strain of bacteria in the study was originally isolated in 1922 from the faeces of a recuperating diptheria patient at Stanford University, in California. The strain was preserved and over time it, and many derivatives, were distributed to research laboratories around the world for use by researchers looking to understand the workings of living cells at the molecular level. While the number of genetic variations which have appeared in the intervening decades may sound alarm bells in some research areas, for others it may represent new research opportunities. Co-author Steve Busby, of the Institute of Microbiology and Infection at the University of Birmingham, said: “Actually the diversity that all this generates can add a new dimension to our understanding. It’s often true that things are seldom as they seem, and particularly so if you only study one strain.”