Further development of this novel technology could result in new, more sensitive assays for clinical laboratories to use in the effort to improve antimicrobial stewardship in hospitals
Researchers at McMaster University in Ontario, Canada, have used artificial intelligence (AI) to identify a potential antibiotic that neutralizes the drug-resistant bacteria Acinetobacter baumannii, an antibiotic resistant pathogen commonly found in many hospitals. This will be of interest to clinical laboratory managers and microbiologists involved in identifying strains of bacteria to determine if they are antimicrobial-resistant (AMR) superbugs.
Using machine learning, the scientists screened thousands molecules to look for those that inhibited the growth of this specific pathogen. And they succeeded.
“We trained a neural network with this growth inhibition dataset and performed in silico predictions for structurally new molecules with activity against A. baumannii,” the researchers wrote in their published study.
They discovered that the molecule abaucin inhibited the growth of the antibiotic-resistant pathogen in vitro.
This shows how machine learning and AI technologies are giving biomedical researchers tools to identify new therapeutic drugs that are effective against drug-resistant strains of bacteria. This same research can be expected to lead to new clinical laboratory assays that determine if superbugs can be attacked by specific therapeutic drugs.
“When I think about AI in general, I think of these models as things that are just going to help us do the thing we’re going to do better,” Jonathan Stokes, PhD, Assistant Professor of Biomedicine and Biochemistry at McMaster University in Ontario, Canada, and lead author of the study, told USA Today. Clinical laboratory scientists and microbiologists will be encouraged by the McMaster University scientists’ findings. (Photo copyright: McMaster University.)
McMaster Study Details
Jonathan Stokes, PhD, head of the Stokes Laboratory at McMaster University, is Assistant Professor of Biomedicine/Biochemistry at McMaster and lead author of the study. Stokes’ team worked with researchers from the Broad Institute of MIT and Harvard to explore the effectiveness of AI in combating superbugs, USA Today reported.
“This work highlights the utility of machine learning in antibiotic discovery and describes a promising lead with targeted activity against a challenging Gram-negative pathogen,” the researchers wrote in Nature Chemical Biology.
Stokes Lab utilized the high-throughput drug screening technique, spending weeks growing and exposing Acinetobacter baumannii to more than 7,500 agents of drugs and active ingredients of drugs. When 480 compounds were uncovered that blocked the growth of bacteria, this information was then provided to a computer that was trained to run an AI algorithm, CNN reported.
“Once we had our [machine learning] model trained, what we could do then is start showing that model brand-new pictures of chemicals that it had never seen, right? And based on what it had learned during training, it would predict for us whether those molecules were antibacterial or not,” Stokes told CNN.
The model spent hours screening more than 6,000 molecules. It then narrowed the search to 240 chemicals, which were tested in the lab. The scientists pared down the results to the nine most effective inhibitors of bacteria. They then eliminated those that were either related to existing antibiotics or might be considered dangerous.
The researchers found one compound—RS102895 (abaucin)—which, according to Stokes, was likely created to treat diabetes, CNN reported. The scientists discovered that the compound prevented bacterial components from making their way from inside a cell to the cell’s surface.
“It’s a rather interesting mechanism and one that is not observed amongst clinical antibiotics so far as I know,” Stokes told CNN.
Because of the effectiveness of the antibiotic during testing on mice skin, the researchers believe this method may be useful for creating antibiotics custom made to battle additional drug resistant pathogens, CNN noted.
Defeating a ‘Professional Pathogen’
Acinetobacter baumannii (A. baumannii)—the focus of Stoke’s study—is often found on hospital counters and doorknobs and has a sneaky way of using other organisms’ DNA to resist antibiotic treatment, according to CNN.
“It’s what we call in the laboratory a professional pathogen,” Stokes told CNN.
A. baumannii causes infections in the urinary tract, lungs, and blood and typically wreaks havoc to vulnerable patients on breathing machines, in intensive care units, or undergoing surgery, USA Today reported.
A. baumannii is resistant to carbapenem, a potent antibiotic. The Centers for Disease Control and Prevention (CDC) reported that in 2017 the bacteria infected 8,500 people in hospitals, 700 of those infections being fatal.
Further, in its 2019 “Antibiotic Resistance Threats in the United States” report, the CDC stated that one out of every four patients infected with the bacteria died within one month of their diagnosis. The federal agency deemed the bacteria “of greatest need” for new antibiotics.
Thus, finding a way to defeat this particularly nasty bacteria could save many lives.
Implications of Study Findings on Development of new Antibiotics
The Stokes Laboratory study findings show promise. If more antibiotics worked so precisely, it’s possible bacteria would not have a chance to become resistant in the first place, CNN reported.
Next steps in Stokes’ research include optimizing the chemical structure and testing in larger animals or humans, USA Today reported.
“It’s important to remember [that] when we’re trying to develop a drug, it doesn’t just have to kill the bacterium,” Stokes noted. “It also has to be well tolerated in humans and it has to get to the infection site and stay at the infection site long enough to elicit an effect,” USA Today reported.
Stokes’ study is a prime example of how AI can make a big impact in clinical laboratory diagnostics and treatment.
“We know broad-spectrum antibiotics are suboptimal and that pathogens have the ability to evolve and adjust to every trick we throw at them … AI methods afford us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it at a reduced cost. This is an important avenue of exploration for new antibiotic drugs,” Stokes told CNN.
Clinical laboratory managers and microbiologists may want to keep an open-mind about the use of AI in drug development. More research is needed to give substance to the McMaster University study’s findings. But the positive results may lead to methods for fine tuning existing antibiotics to better combat antimicrobial-resistant bacteria, USA Today reported.
How Automated Tools Increase Collected Revenue, Produce More Claims, and Require Less Labor: Unleashing the Power of AI and Machine Learning in Coding/Billing/Collections by Dean Paluch...
Two studies show the accuracy of perception-based systems in detecting disease biomarkers without needing molecular recognition elements, such as antibodies
Researchers from multiple academic and research institutions have collaborated to develop a non-conventional machine learning-based technology for identifying and measuring biomarkers to detect ovarian cancer without the need for molecular identification elements, such as antibodies.
Traditional clinical laboratory methods for detecting biomarkers of specific diseases require a “molecular recognition molecule,” such as an antibody, to match with each disease’s biomarker. However, according to a Lehigh University news release, for ovarian cancer “there’s not a single biomarker—or analyte—that indicates the presence of cancer.
“When multiple analytes need to be measured in a given sample, which can increase the accuracy of a test, more antibodies are required, which increases the cost of the test and the turnaround time,” the news release noted.
Unveiled in two sequential studies, the new method for detecting ovarian cancer uses machine learning to examine spectral signatures of carbon nanotubes to detect and recognize the disease biomarkers in a very non-conventional fashion.
“Carbon nanotubes have interesting electronic properties,” said Daniel Heller, PhD (above), in the Lehigh University news release. “If you shoot light at them, they emit a different color of light, and that light’s color and intensity can change based on what’s sticking to the nanotube. We were able to harness the complexity of so many potential binding interactions by using a range of nanotubes with various wrappings. And that gave us a range of different sensors that could all detect slightly different things, and it turned out they responded differently to different proteins.” This method differs greatly from traditional clinical laboratory methods for identifying disease biomarkers. (Photo copyright: Memorial Sloan-Kettering Cancer Center.)
Perception-based Nanosensor Array for Detecting Disease
In the Science Advances paper, the researchers described their development of “a perception-based platform based on an optical nanosensor array that leverages machine learning algorithms to detect multiple protein biomarkers in biofluids.
“Perception-based machine learning (ML) platforms, modeled after the complex olfactory system, can isolate individual signals through an array of relatively nonspecific receptors. Each receptor captures certain features, and the overall ensemble response is analyzed by the neural network in our brain, resulting in perception,” the researchers wrote.
“This work demonstrates the potential of perception-based systems for the development of multiplexed sensors of disease biomarkers without the need for specific molecular recognition elements,” the researchers concluded.
In the Nature Biomedical Engineering paper, the researchers described a fined-tuned toolset that could accurately differentiate ovarian cancer biomarkers from biomarkers in individuals who are cancer-free.
“Here we show that a ‘disease fingerprint’—acquired via machine learning from the spectra of near-infrared fluorescence emissions of an array of carbon nanotubes functionalized with quantum defects—detects high-grade serous ovarian carcinoma in serum samples from symptomatic individuals with 87% sensitivity at 98% specificity (compared with 84% sensitivity at 98% specificity for the current best [clinical laboratory] screening test, which uses measurements of cancer antigen 125 and transvaginal ultrasonography,” the researchers wrote.
“We demonstrated that a perception-based nanosensor platform could detect ovarian cancer biomarkers using machine learning,” said Yoona Yang, PhD, a postdoctoral research associate in Lehigh’s Department of Chemical and Biomolecular Engineering and co-first author of the Science Advances article, in the news release.
How Perception-based Machine Learning Platforms Work
According to Yang, perception-based sensing functions like the human brain.
“The system consists of a sensing array that captures a certain feature of the analytes in a specific way, and then the ensemble response from the array is analyzed by the computational perceptive model. It can detect various analytes at once, which makes it much more efficient,” Yang said.
“SWCNTs have unique optical properties and sensitivity that make them valuable as sensor materials. SWCNTS emit near-infrared photoluminescence with distinct narrow emission bands that are exquisitely sensitive to the local environment,” the researchers wrote in Science Advances.
“Carbon nanotubes have interesting electronic properties,” said Daniel Heller, PhD, Head of the Cancer Nanotechnology Laboratory at Memorial Sloan Kettering Cancer Center and Associate Professor in the Department of Pharmacology at Weill Cornell Medicine of Cornell University, in the Lehigh University news release.
“If you shoot light at them, they emit a different color of light, and that light’s color and intensity can change based on what’s sticking to the nanotube. We were able to harness the complexity of so many potential binding interactions by using a range of nanotubes with various wrappings. And that gave us a range of different sensors that could all detect slightly different things, and it turned out they responded differently to different proteins,” he added.
The researchers put their technology to practical test in the second study. The wanted to learn if it could differentiate symptomatic patients with high-grade ovarian cancer from cancer-free individuals.
The research team used 269 serum samples. This time, nanotubes were bound with a specific molecule providing “an extra signal in terms of data and richer data from every nanotube-DNA combination,” said Anand Jagota PhD, Professor, Bioengineering and Chemical and Biomolecular Engineering, Lehigh University, in the news release.
This year, 19,880 women will be diagnosed with ovarian cancer and 12,810 will die from the disease, according to American Cancer Society data. While more research and clinical trials are needed, the above studies are compelling and suggest the possibility that one day clinical laboratories may detect ovarian cancer faster and more accurately than with current methods.
Screening and analysis of ocean samples also identified a possible missing link in how the RNA viruses evolved
An international team of scientists has used genetic screening and machine learning techniques to identify more than 5,500 previously unknown species of marine RNA viruses and is proposing five new phyla (biological groups) of viruses. The latter would double the number of RNA virus phyla to 10, one of which may be a missing link in the early evolution of the microbes.
Though the newly-discovered viruses are not currently associated with human disease—and therefore do not drive any current medical laboratory testing—for virologists and other microbiologists, “a fuller catalog of these organisms is now available to advance scientific understanding of how viruses evolve,” said Dark Daily Editor-in-Chief Robert Michel.
“While scientists have cataloged hundreds of thousands of DNA viruses in their natural ecosystems, RNA viruses have been relatively unstudied,” wrote four microbiologists from Ohio State University (OSU) who participated in the study in an article they penned for The Conversation.
The OSU study authors included:
Ahmed Zayed, PhD, research scientist, Dept. of Microbiology, OSU.
Matthew Sullivan, PhD, Professor of Microbiology and Director of the Center of Microbiome Science at OSU.
“RNA viruses are clearly important in our world, but we usually only study a tiny slice of them—the few hundred that harm humans, plants and animals,” explained Matthew Sullivan, PhD (above), Director, Center of Microbiome Science, in an OSU news story. Sullivan led the OSU research team. “We wanted to systematically study them on a very big scale and explore an environment no one had looked at deeply, and we got lucky because virtually every species was new, and many were really new,” he added. (Photo copyright: University of Ohio.)
RNA versus DNA Viruses
In contrast to the better-understood DNA virus, an RNA virus contains RNA instead of DNA as its genetic material, according to Samanthi Udayangani, PhD, in an article she penned for Difference Between. Examples of RNA viruses include:
One major difference, she explains, is that RNA viruses mutate at a higher rate than do DNA viruses.
The OSU scientists identified the new species by analyzing a database of RNA sequences from plankton collected during a series of ocean expeditions aboard a French schooner owned by the Tara Ocean Foundation.
“Plankton are any aquatic organisms that are too small to swim against the current,” the authors explained in The Conversation. “They’re a vital part of ocean food webs and are common hosts for RNA viruses.”
The team’s screening process focused on the RNA-dependent RNA polymerase (RdRp) gene, “which has evolved for billions of years in RNA viruses, and is absent from other viruses or cells,” according to the OSU news story.
“RdRp is supposed to be one of the most ancient genes—it existed before there was a need for DNA,” Zayed said.
The RdRp gene “codes for a particular protein that allows a virus to replicate its genetic material. It is the only protein that all RNA viruses share because it plays an essential role in how they propagate themselves. Each RNA virus, however, has small differences in the gene that codes for the protein that can help distinguish one type of virus from another,” the study authors explained.
The screening “ultimately identified over 44,000 genes that code for the virus protein,” they wrote.
Identifying Five New Phyla
The researchers then turned to machine learning to organize the sequences and identify their evolutionary connections based on similarities in the RdRp genes.
“The more similar two genes were, the more likely viruses with those genes were closely related,” they wrote.
The technique classified many of the sequences within the five previously known phyla of RNA viruses:
But the researchers also identified five new phyla—including two dubbed “Taraviricota” and “Arctiviricota”—that “were particularly abundant across vast oceanic regions,” they wrote. Taraviricota is named after the Tara expeditions and Arctiviricota gets its name from the Arctic Ocean.
They speculated that Taraviricota “might be the missing link in the evolution of RNA viruses that researchers have long sought, connecting two different known branches of RNA viruses that diverged in how they replicate.”
In addition to the five new phyla, the researchers are proposing at least 11 new classes of RNA viruses, according to the OSU story. The scientists plan to issue a formal proposal to the International Committee on Taxonomy of Viruses (ICTV), the body responsible for classification and naming of viruses.
Studying RNA Viruses Outside of Disease Environments
“As the COVID-19 pandemic has shown, RNA viruses can cause deadly diseases. But RNA viruses also play a vital role in ecosystems because they can infect a wide array of organisms, including microbes that influence environments and food webs at the chemical level,” wrote the four study authors in The Conversation. “Mapping out where in the world these RNA viruses live can help clarify how they affect the organisms driving many of the ecological processes that run our planet. Our study also provides improved tools that can help researchers catalog new viruses as genetic databases grow.”
This remarkable study, which was partially funded by the US National Science Foundation, will be most intriguing to virologists and microbiologists. However, clinical laboratories also should be interested in the fact that the catalog of known viruses has just expanded by 5,500 types of RNA viruses.
