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.
CDC’s findings are a setback for the national effort to encourage hospitals and their clinical laboratories to reduce the number of nosocomial infections and practice better antimicrobial stewardship
Nosocomial infections—also known as hospital-acquired infections—increased during the COVID-19 pandemic. That’s according to a Centers for Disease Control and Prevention (CDC) report that showed increases in several HAIs, including a 14% jump in Methicillin-resistant Staphylococcus aureus (MRSA) from 2020 to 2021.
Clinical laboratory testing is part of a concerted effort in the US to reduce HAIs in acute care hospitals. Additionally, diagnostic testing is vital to antimicrobial stewardship, which is designed to help physicians prescribe to patients only those antibiotics that are appropriate and reduce the chance for antimicrobial resistance (AMR).
So, it’s disturbing to see a setback in both HAIs and antimicrobial stewardship in the wake of the COVID-19 pandemic. Burda called the CDC’s findings a “regression” that “gives new meaning to the term long COVID.”
“I think, without any proof, doctors, nurses, medical technicians, and other clinicians who provide direct patient care regressed in terms of infection control best practices,” wrote healthcare journalist David Burda in his column for 4Sight Health. Clinical laboratories that processed COVID-19 tests during the pandemic can attest to the burnout. (Photo copyright: 4Sight Health.)
CDC Report Reveals Increase in Hospital Acquired Infections
The CDC used standardized infection ratios (SIRs) in its report to detail changes in nosocomial infections. CDC calculates SIRs by dividing the number of observed infections by the number of predicted infections.
“In 2021, the nation and the world continued to experience unprecedented challenges due to the COVID-19 pandemic, which impacted surveillance for and incidence of HAIs,” the CDC explained in its report.
“Compared to pre-pandemic years, hospitals across the nation experienced higher than usual hospitalizations and shortages in healthcare personnel and equipment, which may have resulted in deterioration in multiple patient safety metrics since the beginning of the pandemic,” the CDC added.
In his 4Sight Health article, Burda noted that physicians and other care providers may have “regressed” in their infection control practices due to severe pressures during the COVID-19 pandemic. “I also think the traveling nurse and temporary staff situation had something to do with it. Who has time to learn or follow the infection control policies and protocols at every hospital when you’re moving from one hospital to the next every few weeks?” he added.
The CDC explored HAIs in acute care hospitals, critical access hospitals, inpatient rehabilitation facilities, and long-term acute care hospitals. According to the federal agency’s report, at acute care hospitals, increases in nosocomial infections from 2020 to 2021 include the following:
27 states performed better on at least two types of infection.
30 states performed worse on at least two infection types.
In response to the CDC’s report, the American Hospital Association (AHA) wrote, “In acute care hospitals, the increases seen in some HAIs in 2021 contrast with the success in reducing these infections prior to the pandemic. Despite the challenges of the COVID-19 pandemic, acute care hospitals performed significantly better than the 2015 national baseline in preventing CLABSI, CAUTI, SSIs following colon surgeries, and C. difficile infections.”
The AHA recommended that hospitals “continue to reinforce prevention practices and review HAI surveillance data to identify areas for improvement.”
Dangers of Antimicrobial Resistance
According to CDC data, in the US there are 2.8 million antimicrobial infections each year, and more than 35,000 people die as a result. Dark Daily has reported extensively on the growing danger of antibiotic resistance and outlined the importance of clinical laboratory involvement in hospital antimicrobial stewardship programs.
In “During Pandemic, Clinical Laboratories Should Be Alert for Drug Resistant Infections That Pose High Risk to COVID-19 Patients,” we covered a study conducted at the University of Minnesota which highlighted the continuing need for microbiologists and clinical laboratories to stay alert for COVID-19 patients with drug-resistant infections following a CDC report on 941 confirmed and probable Candida auris cases that had been reported in 13 states, with an additional 1,830 patients that had been found to be colonized with the multidrug-resistant fungus.
The Joint Commission’s expansion of antibiotic stewardship standards, which went into effect on January 1, 2023, could help hospitals reduce nosocomial infections and fight antimicrobial resistance.
Pew conducted research related to the requirements and found “significant room for improvement in adoption and implementation of stewardship practices” in acute care hospitals, Hyun wrote.
Allocate financial resources for staffing and IT to support the antimicrobial stewardship program.
Implement evidence-based guidelines to improve antibiotic use for infections such as urinary tract c. diff. community-acquired pneumonia.
Evaluate the program using evidenced-based criteria.
“New antibiotic stewardship standards should help limit the emergence and spread of new drug-resistant superbugs,” Hyun noted.
Clinical Laboratories Need to Deepen Involvement
By testing patients and quickly reporting results to physicians, hospital-based and independent medical laboratories play an important role in appropriate antibiotic use and elimination of HAIs.
Heightened involvement by microbiologists and other medical laboratory professionals is key to success in light of recent setbacks in elimination of HAIs and antimicrobial resistance due to the SARS-CoV-2 outbreak.
This research indicates consumers could increase their demand for clinical laboratory testing for genetic risk factors associated with addiction
Rutgers University researchers recently published a study of hundreds of college students that suggests there could be high future consumer demand for genetic testing related to addiction risk. What is significant is that the college students surveyed are members of Generation Z, people born between the mid-1990s and early 2010s.
Zoomers grew up knowing about the human genome, and they are likely aware of new genetic insights, new gene therapies, and new clinical laboratory tests that analyze genomic data to diagnose disease and/or identify the individual’s predisposition to certain genetic conditions.
Thus, consumer demand among Gen Z for clinical laboratories to provide such tests in the future could drive a new class of diagnostic testing that would generate a new revenue stream for clinical laboratories, while also enabling labs to deliver a value-added service to healthcare consumers and their physicians.
“Overall, the [study] results strongly encourage the notion that real genetic risk scores may prove helpful in preventing and treating alcohol addiction,” Danielle Dick, PhD, Director of the Rutgers Addiction Research Center and lead author of the study, told Neuroscience News. The results of the Rutgers study could lead to increased demand for clinical laboratory tests to determine addiction risk. (Photo copyright: Rutgers University.)
Methodology Used in Rutgers Study
To complete their study, the Rutgers researchers surveyed 325 college students and asked how they would react to learning about genetic test results indicating their risk for alcohol use disorder. The researchers found that despite the complexity of the genetic factors underlying addiction, respondents understood the connection between genetic risk and the likelihood of developing alcoholism. And most respondents indicated they would take precautions if they learned that they were at high risk.
The research “paves the way for studies using real genetic data and for integrating genetic information into prevention and intervention efforts,” the study’s lead author, Danielle Dick, PhD, Director of the Rutgers Addiction Research Center (RARC), Greg Brown Endowed Chair in Neuroscience, and Professor, Robert Wood Johnson Medical School/Psychiatry, told Neuroscience News.
The story notes that most genes associated with addiction have only been discovered recently. Commercial genetic testing services do not provide information about addiction risk, “so very few people have ever received genuine information about their genetic tendency toward addiction,” Neuroscience News noted.
The researchers obtained their data as part of a trial that sought to evaluate “the efficacy of educational information on understanding of polygenic risk scores for alcohol use disorder,” they wrote in the American Journal of Medical Genetics.
After recruiting the study participants, the researchers randomly assigned them to one of three groups:
A control group of 109 students that received no educational information.
A group of 105 students who were directed to a website with educational information about alcohol use disorder, “including a definition, consequences, and ways to reduce risk,” the researchers wrote.
A group of 111 students who were directed to a website with the same information about alcoholism, in addition to information about the role of genetics in addiction risk. This included information about “genetic variation, risk variants, how polygenic scores are created, and how they can be interpreted,” the researchers noted.
In all three groups, the survey asked respondents to imagine three hypothetical scenarios: that they had 1) a below-average genetic risk of developing alcoholism, 2) an average risk, and 3) an above-average risk.
For each level of risk, they answered a series of questions “that assessed psychological distress, perceived chance of developing alcohol use disorder, and intentions related to seeking additional information, talking to a healthcare provider, and drinking behavior,” the researchers wrote.
Results of the Rutgers Study of Genetic Risk for Alcohol Use Disorder
The researchers found that exposure to educational information had a minimal impact on the responses, which were generally consistent across all three groups.
With higher levels of risk for alcohol use disorder, respondents were more likely to indicate psychological distress, more likely to seek additional information, more likely to talk to a healthcare provider, and more likely to change drinking behaviors.
And “as the level of genetic risk increased, the perceived chance of developing alcohol use disorder significantly increased,” the researchers wrote.
Does Learning of Risk Alter Behavior?
Citing previous research, Dick said that addiction risk is roughly half determined by genetic factors, “but there’s no single addiction gene that’s either present or absent,” Dick told Neuroscience News. “Instead, there are thousands of interacting genes, so each person’s genetic risk falls somewhere on a continuum.”
The risk is distributed on a bell curve, she said, and most people fall in the middle. But despite this complexity, “study participants formed relatively accurate impressions of the risk for addiction associated with various genetic results.”
The researchers appeared to be most encouraged that the respondents indicated a willingness to take precautionary measures if they learned they had a high genetic risk of developing alcoholism.
“There was a hope that compelling information about elevated genetic risk would get people to change behavior, but we haven’t seen that happen for other aspects of health,” Dick said. “Initial studies suggest that receiving genetic feedback for heart disease, lung cancer, and diabetes does not get people to change their behavior. Getting people to alter their behavior is hard.”
Future Rutgers studies will investigate understanding of risk scores in other populations, Neuroscience News reported.
As demand for genetic tests increases, so does the call for clinical laboratories to process and analyze the data, and work with ordering physicians to explain test results to patients
According to a 23andMe press release announcing the results of two national surveys, “most people and doctors agree that genetic testing offers promise for more personalized healthcare.” This is positive for clinical laboratories that provide genetic testing. These two surveys indicate a growing understanding among physicians and healthcare consumers of genetic testing’s value to effective precision medicine.
The surveys were conducted by Medscape, an online resource of medical information owned by WebMD, and Material, an international firm that partners with companies to provide strategy, insights, design, and technology, according to its website. Direct-to-consumer (DTC) genetic testing company 23andMe commissioned the surveys.
The researchers found that 75% of patients in the US said, “they’d be more likely to follow a doctor’s advice if they knew their genetic profile was used to personalize their care.”
The survey also revealed that:
92% of doctors in the US say genetics is an important part of a patient’s complete health picture.
66% of doctors say genetic testing could help lead to better outcomes for patients.
“I am excited about a future where genetic information becomes the foundation of personalized health,” said Anne Wojcicki, 23andMe co-founder and CEO, in a press release. “And that future may help alleviate some issues already affecting the population.” Recent surveys commissioned by 23andMe that indicate both physicians and patients are becoming more accepting of genetic tests are good news for clinical laboratories that perform genetic testing. (Photo copyright: TechCrunch/Wikimedia Commons.)
Filling a Need for Personalized Healthcare
Elective genetic testing is not only becoming more popular with doctors and patients, it may also fill a key precision medicine need in the population. According to the researchers, “more than half of people surveyed (55%) said they don’t feel healthy today, and 63% said they don’t feel in control of their health. And while most people surveyed (62%) said they wanted advice from their doctors that was tailored to them personally, few, only about 36%, said that’s what they were getting,” the press release noted.
Clearly, demand for a pathway to more personalized healthcare exists in the market. Thus, companies that offer elective genetic testing are looking to fill that need.
Genetic testing kits from companies such as 23andMe and Ancestry have become increasingly popular over the past few years. People often turn to these DTC companies to learn about their heritage, but they also allow healthcare consumers to take part in elective genetic testing without needing a referral from a doctor.
Before the popularity of these DTC tests, most genetic testing only took place when ordered by a healthcare provider. But that may be changing. According to a study conducted by Global Markets Insights (GMI), the size of the DTC genetic testing market “surpassed USD $3 billion in 2022 and is predicted to expand at over 11.5% CAGR [compound annual growth rate] from 2023-2032.”
GMI also predicted that “rising prevalence of genetic disorders will accelerate [genetic testing] industry growth.”
Problems and Opportunities in Genetic Testing
As consumer demand for elective genetic testing has increased, certain issues and opportunities have arisen as well.
In an article she penned for STAT titled, “Why the Rise of DNA Testing Is Creating Challenges—and An Opportunity,” physician/scientist Noura Abul-Husn MD, PhD, Vice President of Genomic Health at 23andMe, wrote, “This rapid growth has created what some might see as a big problem and others might see as an opportunity.” Abul-Husn is also Associate Professor of Medicine and Genetics, and Clinical Director of the Institute for Genomic Health, at the Icahn School of Medicine at Mount Sinai.
“The problem? There hasn’t been a corresponding increase in genetics education and training healthcare providers about it, meaning that many people are reaching out to healthcare providers who are ill-prepared to incorporate genetic test results into clinical practice,” she wrote.
“The opportunity? Results from genetic testing can help healthcare providers engage with their patients on a deeper level about personal health risks, promoting health, and preventing disease,” she added.
Growing Need for Processing and Analyzing Genomic Tests
A YouGov survey of 1,000 adults between February 9 and February 12, 2022, showed that two of every 10 Americans have taken a DTC genetic test. But it seems healthcare professionals currently lack the training to incorporate genetic test results into their patients’ care. This may present an opportunity for the genetic testing industry to meet the demand of its consumers.
The growing popularity of elective genetic testing will also increase demand for clinical laboratories to process and analyze these types of tests. And that will drive increased revenue and job opportunities in those labs.
Another factor that is positive about the increased acceptance and interest in genetic testing by doctors and consumers is that this creates a demand by employees for their company health plan to cover genetic tests. Each year, going forward, employers will recognize that their employees want genetic tests and so will take steps to make such tests a covered benefit within the health plan. That is also a positive market factor for those medical laboratories offering genetic testing.
It seems clear that elective genetic testing offers individuals the opportunity to work with their physicians to design personalized treatments based on their unique conditions. And it gives the healthcare industry—including clinical laboratories—the opportunity to expand services and branch out. The future of precision medicine may lie within our genes.
Research shows face-to-face genetics counseling overcomes barriers to proceeding with genetic testing and increases chances of catching cancer early
Research funded by the Prostate Cancer Foundation (PCF) has found that when patients receive in-person genetics counseling instead of virtual telehealth consultation, they are more likely to complete full germline genetic testing.
Clinical laboratory professionals have long been aware, at least anecdotally, that when physicians hand medical laboratory test orders to patients, a high percentage do not follow through and provide blood specimens for testing.
According to a PCF press release, with an on-site genetics counseling program “genetic testing occurs at the time of the consult,” whereas “with the telegenetics model, testing kits are mailed to the veteran’s home to be completed later, which can be a significant barrier, particularly for veterans with unstable housing. Researchers also explain that a face-to-face interaction with a trusted healthcare provider may be a better forum for having psychosocially complex genetic counseling discussions than telemedicine.”
This insight may be useful for genetic testing labs that can arrange for personal counseling of patients whose physician has recommended a complete full germline genetic test. Those labs would likely see a higher proportion of genetic test referrals convert into actual tests because more patients would decide to proceed.
“Without a doubt, telemedicine has many benefits, but this research shows that when it comes to genetic counseling and testing, in-person consults are most impactful,” Howard R. Soule, PhD, PCF Executive Vice President and Chief Science Officer, said in the press release.
Prostate Cancer Foundation Executive Vice President and Chief Science Officer Howard R. Soule, PhD said in-person counseling for genetic testing is more effective than a telehealth consult. Clinical laboratories are familiar with the problem of patients not following through on doctors’ orders for lab testing. (Photo copyright: Prostate Cancer Foundation.)
Germline genetic testing identifies inherited mutations that may be linked to cancer. In at-risk individuals, it plays a role in secondary screening, and it is also an element in treating prostate and other cancers.
The patients in the study were referred for cancer genetics services between October 1, 2020, and February 28, 2022, the JCO Oncology Practice paper noted. About two-thirds (65%) were referred due to a personal history of cancer and 26% due to family history of cancer. More than half self-identified as Black.
Among the 238 patients, 130 received telehealth genetic counseling compared with 108 who were counseled onsite. A total of 117 patients in the study underwent the genetic testing.
The researchers found that among all patients in the study, those who received on-site counseling had a 3.2-fold higher likelihood of completing the genetic testing compared with the telehealth service. Among the patients who self-identified as Black, the likelihood was 4.8-fold higher. The study also found that those who received on-site counseling were less likely to miss follow-up care.
The study noted some demographic differences between the two groups: Veterans seen onsite had a median age of 71 and 92% were male. Among those who received telegenetics counselling, the median age was 57 and 58% were male.
Barriers to Genetic Testing
“Barriers to genetic testing—such as lack of access to cancer genetic services and an overall shortage of genetics service providers, both within and outside of the VA—translate to missed opportunities to diagnose cancer earlier, identify at risk family members, and offer precision oncology treatment,” the press release states.
Citing previous studies, the researchers noted that barriers to completion of genetic testing “have been magnified among racial minorities, even in cases for which there is a clear indication for testing, or if the testing is provided free of cost.”
One goal of the study, the researchers wrote, was to determine if on-site consultation could help overcome those barriers.
These consultations “can be complex encounters, and for patients with active cancer, they occur during a stressful period of their care,” the researchers wrote. The consults should include “the benefits and limitations of testing, different types of test results, and the risk of psychological impact of test results.”
Possible Explanations for Genetic Test Completion Rates
The researchers pointed to several possible explanations for the differences in testing rates. The on-site genetics nurse “has flexibility to see patients in the same physical space as their oncology follow-up or treatment visits.” The study found that this led to better attendance at appointments.
In addition, those patients received testing during the consultation. However, patients who underwent genetics counselling received their testing kits by mail. “This time delay allows for multiple intervening factors that could affect the completion of genetic testing,” the researchers wrote.
The researchers also suggested that patients may be more inclined to trust providers with whom they have face-to-face interactions.
“Our findings suggest that the presence of an on-site genetics service can potentially mitigate [racial] disparities, while effectively increasing the proportion of completed [genetic tests] for patients regardless of racial or ethnic background,” they wrote.
“Although telegenetics has greatly expanded access to genetics evaluations, it is possible that a face-to-face interaction with a provider onsite may be a better method for delivery of genetics consultations, given the inherent complexity in these encounters, particularly in the veteran population,” the researchers noted in JCO Oncology Practice. “It is imperative to optimize these interactions and facilitate genetics services follow-up, as the ultimate results from testing—if indicated—have profound implications on matters that are important to patients.”
Though the PCF study is confined to genetic testing and does not encompass all clinical laboratory testing, those with experience in medical laboratories know a high percentage of patients do not complete doctor-ordered lab tests.
“Going as far back as the 1990s, there has been recognition among pathologists and clinical laboratory managers that, as a rule of thumb, for every 100 lab test orders a doctor hands to patients, only 60% of those patients come in and provide a blood specimen,” said Robert Michel, Editor-in-Chief of Dark Daily and its sister publication The Dark Report. “To my knowledge, there’s never been a published study about this aspect of clinical laboratory testing that has appeared in a peer-reviewed medical journal.
“Over the years, fear of needles was believed to be one reason why some patients accept a lab test order from their physician but do not take the next step of providing a specimen to a clinical lab,” Michel added. “Today, with high-deductible health plans and expensive genetic tests, cost would be another reason why patients might decline to go forward with lab tests ordered by their physicians.”
New study shows how artificial neural networks are leading to improved microscopic capabilities and precision that could help researchers better understand causes of tumors
Pathologists, microbiologists, and clinical laboratory scientists engaged in research into cellular activity will be interested to learn that advances in artificial intelligence (AI) are leading to new opportunities for future research studies to observe and capture—in real time—biological processes in living cells/samples.
“EPFL biophysicists have now found a way to automate microscope control for imaging biological events in detail while limiting stress on the sample, all with the help of artificial neural networks. Their technique works for bacterial cell division, and for mitochondrial division,” according to Phys.org.
Even better, the EPFL scientists are making the control framework available as an open-source software plug-in for the microscope control program Micro-Manager. This enables clinical laboratories to integrate artificial intelligence into existing microscope control software, Phys.org noted.
“An intelligent microscope is kind of like a self-driving car. It needs to process certain types of information, subtle patterns that it then responds to by changing its behavior,” Suliana Manley, PhD, biophysicist and a professor in the Laboratory of Experimental Biophysics at the École Polytechnique Fédérale de Lausanne, told Phys.org. Clinical laboratories and anatomic pathology groups may want to explore the capabilities of this intelligent microscope technology. (Photo copyright: EPFL.)
EPFL Study Breakdown
Suliana Manley, PhD, biophysicist, professor, and head of the Laboratory of Experimental Biophysics at the EPFL, is the principal investigator of the “Intelligent microscope” study. She has spent her career focusing on the development of high-resolution optical instruments and the organization and dynamics of proteins.
Manley and her team learned how to detect mitochondrial divisions in bacteria such as Caulobacter Crescentus. These divisions can occur once every few minutes, but last only seconds. Their infrequency and ability to occur anywhere within the mitochondrial network makes them difficult to spot and photograph, Physics World noted.
To overcome this barrier, the EPFL team trained the neural network to look for mitochondrial constrictions—the shape change in mitochondria that leads to division—and combined that data with observations of the protein DRP1, the presence of which is required for spontaneous divisions to occur, Phys.org reported.
“A common goal of fluorescence microscopy is to collect data on specific biological events. Yet, the event-specific content that can be collected from a sample is limited, especially for rare or stochastic processes,” wrote the EPFL scientists in their Nature Methods paper. “We developed an event-driven acquisition framework, in which neural-network-based recognition of specific biological events triggers real-time control in an instant structured illumination microscope … we capture mitochondrial and bacterial divisions at imaging rates that match their dynamic timescales, while extending overall imaging durations. Because event-driven acquisition allows the microscope to respond specifically to complex biological events, it acquires data enriched in relevant content.”
Manley’s intelligent fluorescent microscope responds more rapidly than human control can achieve. When the microscope senses constrictions and DRP1 protein levels are high, it switches into high-speed image capture mode and gathers multiple images with minute detail. Conversely, when both constrictions and protein are low, the microscope goes into low-speed imaging mode, which preserves the integrity of the sample by avoiding excessive exposure to light, Phys.org noted.
Automating microscope control limits the stress placed on samples, increasing the likelihood of more accurate results. It also allows microscope control for imaging biological events in detail, as it eliminates human error that naturally occurs from trying to keep up with events in real time, Phys.org reported.
“Using a neural network, we can detect much more subtle events and use them to drive changes in acquisition speed,” Manley told Phys.org. “The potential of intelligent microscopy includes measuring what standard acquisitions would miss. We capture more events, measure smaller constrictions, and can follow each division in greater detail.”
What’s Next for EPFL?
Manley and her EPFL team plan to continue working with neural networks to detect different events and bring about different hardware responses.
“For example, we envision harnessing optogenetic perturbations to modulate transcription at key moments in cell differentiation,” she told Physics World. “We also think of using event detection as a means of data compression, selecting for storage or analysis the pieces of data that are most relevant to a given study.”
As research continues in bacterial cell division, there will be a point where the technology enables researchers to observe cell activity and what conditions cause abnormal (tumor) cells to be created. That would be the first step to then investigating ways to stop the cellular process that creates abnormal cells.
It should not surprise pathologists and clinical laboratory managers that researchers and technology developers are exploring ways to “turbocharge” classic light microscopy. Advances in image analysis, combined with machine learning algorithms, are making it possible to tease new insights from the images viewed with a standard microscope.
