Bioinformatics | News

ICBR-Bioinformatics@ad.ufl.edu   ///  (352) 273-8049   ///    RRID: SCR_019120
The Latest Bioinformatics News

NEWS FEED

SynGatorTron™ to speed medical research, alleviate privacy worries

from UF Health

“Dr. Chatbot will see you now.”

The next generation of super-smart computers, tablets and cell phones may come equipped with artificial intelligence-generated medical chatbots that can interact with patients using human language and medical knowledge.

According to Yonghui Wu, Ph.D., director of natural language processing at the University of Florida Clinical and Translational Science Institute, the medical chatbot you interact with online will be able to use conversational language to communicate with and educate patients in much the same way we now interact with Apple’s chatbot, Siri, and Amazon’s Alexa.

The chatbot may also be culturally sensitive and matched to your age.

“It will be like having your own personal medical avatar,” Wu said.

Medical chatbots are just one of many possible applications to arise out of groundbreaking new AI tools developed by Wu and other researchers at UF and NVIDIA as part of a $100 million artificial intelligence public-private collaboration formed in 2020. Last year, they launched a clinical language AI model, GatorTron™. This AI tool enables computers to quickly access, read and interpret medical language in clinical notes and other unstructured narratives stored in real-world electronic health records. The model was trained on HiPerGator-AI, the university’s NVIDIA DGX SuperPOD system, which ranks among the world’s top 30 supercomputers.

The GatorTron™ model is expected to accelerate research and medical decision-making by extracting information and insights from massive amounts of clinical data with unprecedented speed and clarity. It will also lead to innovative AI tools and advanced, data-driven health research methods that were unimaginable even 10 or 15 years ago.

This year, the team is rolling out another model – SynGatorTron™ — with different capabilities. SynGatorTron™ can generate synthetic patient data untraceable to real patients. This synthetic data can then be used to train the next generation of medical AI systems to understand conversational language and medical terminology.

Most data-driven health research and health-related AI applications today rely on ‘de-identified’ patient data in electronic health records, from which patients’ private information such as name, address and birthdate, has been removed before it is used for research and development.

Removing patient data is time-consuming and labor-intensive. Automated de-identification systems can be used to generate large-scale machine de-identified data, but it’s not an ironclad solution.

According to Wu, even after all identifying patient information has been removed, there’s still a remote chance that someone could identify a patient by tracking data over time.

“Generating synthetic patient data is a safe way to preserve the knowledge of medical language but mitigate the risks of patient privacy,” Wu said.

Patient privacy isn’t the only barrier to training the next generation of AI models for research and other applications. The sheer volume of data required to train AI models can also stand in the way.

“There’s a finite amount of patient data available to us, and training AI computer models requires a tremendous amount of data,” said Duane Mitchell, M.D., Ph.D., director of the UF Clinical and Translational Science Institute and associate dean for clinical and translational sciences at the UF College of Medicine. “With SynGatorTron™, we can generate all the data we need.”

 


/// Read Full Article ///
Dr. Duane Mitchell is user in ICBR’s Bioinformatics, Cytometry, Electron Microscopy, Monoclonal Antibody, NextGen DNA Sequencing, Proteomics & Mass Spectrometry and Gene Expression & Genotyping core

Soltis named 2021-2022 Teacher/Scholar of the Year

Soltis named 2021-2022 Teacher/Scholar of the Year

from UF News
by Blake Trauschke

Pamela S. Soltis, a distinguished professor and curator at the Florida Museum of Natural History, has been selected as the 2021-2022 University of Florida Teacher/Scholar of the Year.

UF’s most prestigious and oldest faculty award, the recognition offers an honorarium of $6,000 in addition to other acknowledgements.  In selecting the winner, the Award Committee chooses a faculty member who demonstrates distinguished achievement in both teaching and scholarly activity as evidenced through scholarly research, creative writing, original works of art, etc., and visibility within and beyond the university.

Soltis, director of the UF Biodiversity Institute, is a botanist whose principal research focuses on plant diversity and evolution. She is widely known for her recognition of the importance of polyploidy — having more than two sets of chromosomes — evolution in flowering and seed plants. She joined UF in 2000.

She has more than 400 scientific publications, authored and edited nine books, and served as president for three scientific societies.

Soltis was a nominee for the National Medal of Science and won the Southeastern Universities Research Association’s 2018 Distinguished Scientist Award. Alongside her husband, Doug Soltis, who is also a distinguished professor at the university, Pam Soltis co-won the 2002 Dahlgren Prize in Botany from the Royal Physiographic Society of Sweden, the 2006 Asa Gray Award from the American Society of Plant Taxonomists, the 2010 Award of Merit from the Botanical Society of America, and the 2016 Darwin-Wallace Medal by the Linnean Society of London.

 


/// Read Full Article ///
Dr. Pam Soltis is a user in ICBR’s Cytometry, Monoclonal Antibody, NextGen DNA Sequencing and Gene Expression & Genotyping core.

New COVID test can quickly detect variants

New COVID test can quickly detect variants

from UF News

University of Florida researchers have invented a test that can determine within 10-15 minutes whether patients test positive for COVID and, if so, which of the five known variants of concern they have.

The research, published Saturday in The Lancet’s eBioMedicine, involves the use of a simple heating device and a cellphone. The team also used a new form of CRISPR — a means of finding and targeting a specific section of genetic material inside a cell — to quickly and effectively diagnose COVID and learn which variant of concern is in a patient sample: alpha, beta, gamma, delta, or omicron.

The finding could provide policymakers with vital information about when to require masking and prepare hospitals for a wave of infections. It could also allow patients and family members to prevent or treat a particular variant more effectively.

“For the medical and research community, knowing which variants are emerging is extremely important,” said corresponding author Piyush Jain, an assistant professor and a Shah Rising Star Professor in the Department of Chemical Engineering. “If an especially serious variant like delta or a genetically similar variant, such as deltacron, arises in the future, work like this discovery will help us track it earlier.”

The team, including professors Marco Salemi, Rhoel Dinglasan, John Lednicky and their lab members from the Emerging Pathogens Institute, made the findings in collaboration with two bioscience engineering companies registered in the Czech Republic. The companies helped the researchers engineer a prototype that could function at home, in a clinic, or in the field.

Current processes for determining COVID variants take several days to perform, which is why patients typically don’t learn which variant they have.

Advancing on recently published work, including by Long Nguyen, a PhD candidate and the first author of the study, the UF team is the first to investigate the new heat-loving CRISPR technology, which manages to combine speed, accuracy, and variant identification by amplifying and detecting coronavirus genetic material in one step.

 


/// Read Full Article ///
Dr. Piyush Jain is a user in ICBR’s Cytometry and Monoclonal Antibody cores.
Dr. Rhoel Dinglasan is a user in ICBR’s Cytometry, Electron Microscopy, Monoclonal Antibody, NextGen DNA Sequencing, and Gene Expression & Genotyping cores.
Dr. Marco Salemi is a user in ICBR’s Bioinformatics, Cytometry, NextGen DNA Sequencing and Gene Expression & Genotyping cores.
Dr. John Lednicky is a current user in UF | ICBR’s  Electron Microscopy and Gene Expression & Genotyping cores.

Viruses Don’t Just Make You Sick. They Affect Your Gut Bacteria, Too, Study Finds

from UF/IFAS

Norovirus is a food-borne virus that causes food poisoning in millions of people each year. A new study from the University of Florida shows this virus also alters the bacteria that live in our gut, providing new clues about the human microbiome’s role in our health.

“A lot of research has shown that intestinal viruses use gut bacteria to increase their infectiousness. However, no one has looked at what happens to the bacteria themselves during this process, which is what we investigated in this study,” said Melissa Jones, senior author of the study and an assistant professor in the UF/IFAS department of microbiology and cell science.

The researchers observed this virus-bacteria interaction in two ways: They introduce human norovirus to common human gut bacteria strains in a controlled lab environment; and they infected mice with the mouse version of norovirus and analyzed the bacteria in the droppings.

bacteria before and after norovirus introduction

Bacteria before (left) and after (right) introduction of norovirus. Photo courtesy of Melissa Jones.

The researchers found that in both scenarios, gut bacteria experienced changes in gene expression —which genes are turned on or off. They also saw the bacteria’s surface became wrinkled and sprouted new webby appendages. It is not yet clear how long these changes last. Following these changes, the microbes increased their production of outer membrane vesicles, nano-sized packets of molecules bacteria use to communicate with each other and with human cells, Jones explained.

However, the message contained in these vesicles is still a mystery. They may help gut bacteria and the human body better respond to the virus to stop infection. Or, they could be part of a stress response in bacteria that helps norovirus cause further disruption in our gut.

If the latter is true, it may help explain why norovirus in particular is so good at infecting people, Jones said.

“Norovirus has been called the perfect human pathogen because it gets in the body, usually through contaminated food, and makes lots and lots of copies of itself under the radar of our immune system. Then, as anyone who has gotten norovirus knows all too well, it spreads itself widely to other people through all the bodily fluids we lose while sick,” Jones said. “Our future research may show how gut bacteria are part of this very efficient process.”

 


/// Read Full Article ///

 

Dr. Melissa Jones is a current user in UF | ICBR’s Cytometry, Electron Microscopy, Gene Expression & Genotyping, NextGen DNA Sequencing and Proteomics & Mass Spectrometry
Chanel Mosby-Haundrup is a current user in UF | ICBR’s Cytometry, Electron Microscopy, Gene Expression & Genotyping, and NextGen DNA Sequencing
Sutonuka Bhar is a current user in UF | ICBR’s Cytometry, Electron Microscopy, and Proteomics & Mass Spectrometry
Matthew Phillips is a current user in UF | ICBR’s Bioinformatics and Cytometry
Dr. Mariola Edelmann is a current user in UF | ICBR’s Cytometry, Electron Microscopy, and Proteomics & Mass Spectrometry

Hot Tumors: The Turbo Engine That Immunotherapy Needed

by Maja Aganovic
UF Innovate

Immunotherapy is a hot topic of conversation when it comes to cancer treatment. Pediatric oncologist Dr. Elias Sayour and his team have found a way to make a hot tumor, their way to make immunotherapy, an alternative to chemotherapy, more effective.

“I spend the bulk of my time doing research, 80 percent of my time trying to develop new therapies for childhood cancer,” said Sayour, an associate professor of neurosurgery and pediatrics and principal investigator of the RNA Engineering Laboratory within the University of Florida Brain Tumor Immunotherapy Program. “What we do to take care of children with cancer is largely provide medicines called chemotherapy.

“These are medicines that can work against cancer, but they also can cause a lot of toxicity. And they don’t protect you after they’re out of the bloodstream.”

His team, which includes Hector Mendez-GomesSadeem QdaisatDuane Mitchell, and Brandon Wummer – is trying to develop immunotherapy, which holds that your own body should be able to sense foreign cancer cells and tumors in the body to attack them as if they were a virus or other pathogen. A beautiful concept, but with limited efficacy; immunotherapy has demonstrated only a 15-20 percent effective rate.

“Cancer has evolved to prevent immune recognition,” explained Sayour. His team recently received the 2021 Invention of the Year award from UF Innovate | Tech Licensing for their intratumoral Type 1 interferons that sensitize response to checkpoint inhibitors.

Making immune checkpoint inhibitors more effective

The body has natural immune checkpoints that regulate the immune system in an attack against pathogens so the body doesn’t attack healthy host cells. However, these immune checkpoints can also protect cancers from the body’s natural immune defense.

Sayour began his journey by asking the question “Why are some cancers really good at turning off the immune system?”

Immune Checkpoint Inhibitors are a subset of immunotherapy. They are drugs that work by blocking the body’s natural immune checkpoints and are approved for a variety of cancer types, including skin and lung cancer. Sayour and his team sought to improve on this form of therapy.

When cancers successfully escape immune recognition, they sever the communication line to the immune system. Sayour and his team theorized that if they could determine which communication line was severed, they might be able to reverse the process.

 


/// Read Full Article ///
Dr. Elias Sayour and Dr. Hector Mendez-Gomes are current users in UF | ICBR’s Cytometry, Electron Microscopy, Gene Expression & Genotyping, NextGen DNA Sequencing and Proteomics & Mass Spectrometry cores.
Dr. Sadeem Qdaisat is a current user in UF | ICBR’s Cytometry core.
Dr. Duane Mitchell is a current user in UF | ICBR’s Bioinformatics, Cytometry, Electron Microscopy, Gene Expression & Genotyping, Monoclonal Antibody, NextGen DNA Sequencing and Proteomics & Mass Spectrometry cores.

 

UF Researcher Dr. Marco Salemi Utilizes ICBR Genomics Expertise to Understand COVID19 Epidemiology

By Steven Madore, Ph.D.

In recent years, public health emergencies caused by epidemics have led to the use of genome sequencing to identify and characterize viral pathogens. Rapid acquisition of high quality viral genomic sequences is critical for understanding viral pathogen origin, transmission and epidemiological spread. Ultimately deciphering the molecular characteristics of viruses accelerates the development of diagnostic assays and vaccine development and drug design and is important in understanding the role of evolutionary variants in viral spread through the affected population.

This virus contains a single molecule of RNA that contains the genetic information to produce new progeny in infected cells. To determine the viral genome “code” viral (more…)

UF | ICBR Scientists Contribute to Clinical Trial Testing Novel Treatment for Canine Atopic Dermatitis

 

Atopic dermatitis, or AD, is a common chronic inflammatory skin disease affecting dogs, causing defects of the skin barrier and modifications of the normal cutaneous microflora. While multiple treatment options are available, there is a growing interest in the use of alternative natural ingredient products. In human AD reports show the potential benefits of topical applications of heat-killed beneficial bacteria, with some studies demonstrating the efficacy of rapidly killed beneficial lactobacilli in ameliorating clinical symptoms. A recent clinical trial led by Dr. Domenico Santoro and Clinical Trail Coordinator Lana Fagman from the UF Small Animal Clinical Sciences, College of Veterinary Medicine, and performed in collaboration with UF | ICBR scientists Drs. Yanping Zhang and Yu Fahong, investigated the efficacy of a spray version of a veterinary product containing heat killed lactobacilli (L. rhamnosus and L. reuteri) marketed as an adjuvant therapy for allergic dogs on the clinical signs of canine AD. This spray was applied once a day for 28 days on ten privately owned, mildly affected, dogs and clinical symptoms and skin microbiota analyzed. (more…)

UF Researchers to Use AI to Predict How Hurricanes Spread Invasive Plants

Courtesy of UF/IFAS
Written by Brad Buck

Scientists project hurricane intensity and frequency will increase with climate change. That leads researchers to want to better predict how storms will disperse and establish nonnative plant invaders.

Knowing where invasive plants spread will always be useful. But it may become especially handy soon as the National Hurricane Center is considering moving the official start of the Atlantic hurricane season two weeks earlier, starting it May 15, instead of June 1. Tropical Storm Arthur formed May 16 last year, marking six straight years a named storm formed before June 1. (more…)