Genetic engineers at the lab used the new tool to generate a catalog of 71 million possible missense variants, classifying 89% as either benign or pathogenic
Genetic engineers continue to use artificial intelligence (AI) and deep learning to develop research tools that have implications for clinical laboratories. The latest development involves Google’s DeepMind artificial intelligence lab which has created an AI tool that, they say, can predict whether a single-letter substitution in DNA—known as a missense variant (aka, missense mutation)—is likely to cause disease.
The Google engineers used their new model—dubbed AlphaMissense—to generate a catalog of 71 million possible missense variants. They were able to classify 89% as likely to be either benign or pathogenic mutations. That compares with just 0.1% that have been classified using conventional methods, according to the DeepMind engineers.
This is yet another example of how Google is investing to develop solutions for healthcare and medical care. In this case, DeepMind might find genetic sequences that are associated with disease or health conditions. In turn, these genetic sequences could eventually become biomarkers that clinical laboratories could use to help physicians make earlier, more accurate diagnoses and allow faster interventions that improve patient care.
“AI tools that can accurately predict the effect of variants have the power to accelerate research across fields from molecular biology to clinical and statistical genetics,” wrote Google DeepMind engineers Jun Cheng, PhD (left), and Žiga Avsec, PhD (right), in a blog post describing the new tool. Clinical laboratories benefit from the diagnostic biomarkers generated by this type of research. (Photo copyrights: LinkedIn.)
AI’s Effect on Genetic Research
Genetic experiments to identify which mutations cause disease are both costly and time-consuming, Google DeepMind engineers Jun Cheng, PhD, and Žiga Avsec, PhD, wrote in a blog post. However, artificial intelligence sped up that process considerably.
“By using AI predictions, researchers can get a preview of results for thousands of proteins at a time, which can help to prioritize resources and accelerate more complex studies,” they noted.
Of all possible 71 million variants, approximately 6%, or four million, have already been seen in humans, they wrote, noting that the average person carries more than 9,000. Most are benign, “but others are pathogenic and can severely disrupt protein function,” causing diseases such as cystic fibrosis, sickle-cell anemia, and cancer.
“A missense variant is a single letter substitution in DNA that results in a different amino acid within a protein,” Cheng and Avsec wrote in the blog post. “If you think of DNA as a language, switching one letter can change a word and alter the meaning of a sentence altogether. In this case, a substitution changes which amino acid is translated, which can affect the function of a protein.”
In the Google DeepMind study, AlphaMissense predicted that 57% of the 71 million variants are “likely benign,” 32% are “likely pathogenic,” and 11% are “uncertain.”
The AlphaMissense model is adapted from an earlier model called AlphaFold which uses amino acid genetic sequences to predict the structure of proteins.
“AlphaMissense was fed data on DNA from humans and closely related primates to learn which missense mutations are common, and therefore probably benign, and which are rare and potentially harmful,” The Guardian reported. “At the same time, the program familiarized itself with the ‘language’ of proteins by studying millions of protein sequences and learning what a ‘healthy’ protein looks like.”
The model assigned each variant a score between 0 and 1 to rate the likelihood of pathogenicity [the potential for a pathogen to cause disease]. “The continuous score allows users to choose a threshold for classifying variants as pathogenic or benign that matches their accuracy requirements,” Avsec and Cheng wrote in their blog post.
However, they also acknowledged that it doesn’t indicate exactly how the variation causes disease.
The engineers cautioned that the predictions in the catalog are not intended for clinical use. Instead, they “should be interpreted with other sources of evidence.” However, “this work has the potential to improve the diagnosis of rare genetic disorders, and help discover new disease-causing genes,” they noted.
Genomics England Sees a Helpful Tool
BBC noted that AlphaMissense has been tested by Genomics England, which works with the UK’s National Health Service. “The new tool is really bringing a new perspective to the data,” Ellen Thomas, PhD, Genomics England’s Deputy Chief Medical Officer, told the BBC. “It will help clinical scientists make sense of genetic data so that it is useful for patients and for their clinical teams.”
AlphaMissense is “a big step forward,” Ewan Birney, PhD, Deputy Director General of the European Molecular Biology Laboratory (EMBL) told the BBC. “It will help clinical researchers prioritize where to look to find areas that could cause disease.”
Other experts, however, who spoke with MIT Technology Review were less enthusiastic.
Heidi Rehm, PhD, co-director of the Program in Medical and Population Genetics at the Broad Institute, suggested that the DeepMind engineers overstated the certainty of the model’s predictions. She told the publication that she was “disappointed” that they labeled the variants as benign or pathogenic.
“The models are improving, but none are perfect, and they still don’t get you to pathogenic or not,” she said.
“Typically, experts don’t declare a mutation pathogenic until they have real-world data from patients, evidence of inheritance patterns in families, and lab tests—information that’s shared through public websites of variants such as ClinVar,” the MIT article noted.
Is AlphaMissense a Biosecurity Risk?
Although DeepMind has released its catalog of variations, MIT Technology Review notes that the lab isn’t releasing the entire AI model due to what it describes as a “biosecurity risk.”
The concern is that “bad actors” could try using it on non-human species, DeepMind said. But one anonymous expert described the restrictions “as a transparent effort to stop others from quickly deploying the model for their own uses,” the MIT article noted.
And so, genetics research takes a huge step forward thanks to Google DeepMind, artificial intelligence, and deep learning. Clinical laboratories and pathologists may soon have useful new tools that help healthcare provider diagnose diseases. Time will tell. But the developments are certain worth watching.
Researchers find declining antibody levels in SARS-CoV-2 patients are offset by T cells and B cells that remain behind to fight off reinfection
Questions remain regarding how long antibodies produced by a COVID-19 vaccine or natural infection will provide ongoing protection against SARS-CoV-2. However, a new study showing COVID-19 immunity may be “robust” and “long lasting” may signal important news for clinical laboratories and in vitro diagnostics companies developing serological tests for the coronavirus disease.
The LJI research team analyzed blood samples from 188 COVID-19 patients, 7% of whom had been hospitalized. They measured not only virus-specific antibodies in the blood stream, but also memory B cell infections, T helper cells, and cytotoxic (killer) T cells.
While antibodies eventually disappear from the blood stream, T cells and B cells appear to remain to fight future reinfection.
“As far as we know, this is the largest study ever for any acute infection that has measured all four of those components of immune memory,” Crotty said in a La Jolla Institute news release.
The LJI researchers found that virus-specific antibodies remained in the blood stream months after infection while spike-specific memory B cells—which could trigger an accelerated and robust antibody-mediated immune response in the event of reinfection—actually increased in the body after six months. In addition, COVID-19 survivors had an army of T cells ready to halt reinfection.
“Our data show immune memory in at least three immunological compartments was measurable in ~95% of subjects five to eight months post symptom onset, indicating that durable immunity against secondary COVID-19 disease is a possibility in most individuals,” the study concludes. The small percentage of the population found not to have long-lasting immunity following COVID-19 infection could be vaccinated in an effort to stop reinfection from occurring on the way to achieving herd immunity, the LJI researchers maintained.
Do COVID-19 Vaccines Create Equal Immunity Against Reinfection?
Whether COVID-19 vaccinations will provide the same immune response as an active infection has yet to be determined, but indications are protection may be equally strong.
“It is possible that immune memory will be similarly long lasting similar following vaccination, but we will have to wait until the data come in to be able to tell for sure,”
LJI Research Professor Daniela Weiskopf, PhD, said in the LJI statement. “Several months ago, our studies showed that natural infection induced a strong response, and this study now shows that the response lasts. The vaccine studies are at the initial stages, and so far, have been associated with strong protection. We are hopeful that a similar pattern of responses lasting over time will also emerge for the vaccine-induced responses.”
The study’s authors cautioned that people previously diagnosed with COVID-19 should not assume they have protective immunity from reinfection, the Washington Post noted. In fact, according to the LJI news release, researchers saw a “100-fold range in the magnitude of immune memory.”
Alessandro Sette, Doctor of Biological Sciences (above), an Italian immunologist, Professor at the Center for Autoimmunity and Inflammation/Center for Infectious Disease and Vaccine Research at La Jolla Institute for Immunology, and co-author of the study, told the Washington Post that people should act responsibly. “If I had COVID, I would still not throw away my masks, I would not go to rave parties … It’s like driving a car where you know you have 90% probability that the brakes work.” (Photo copyright: La Jolla Institute for Immunology.)
Previous Studies Found Little Natural Immunity Against SARS-CoV-2 Reinfection
The Scientist reported that several widely publicized previous studies raised concerns that immunity from natural infection was fleeting, perhaps dwindling in weeks or months. And a United Kingdom study published in Nature Microbiology found that COVID-19 generated “only a transient neutralizing antibody response that rapidly wanes” in patients who exhibited milder infection.
Daniel M. Davis, PhD, Professor of Immunology at the University of Manchester, says more research is needed before scientists can know for certain how long COVID-19 immunity lasts after natural infection.
“Overall, these results are interesting and provocative, but more research is needed, following large numbers of people over time. Only then, will we clearly know how many people produce antibodies when infected with coronavirus, and for how long,” Davis told Newsweek.
While additional peer-reviewed studies on the body’s immune response to COVID-19 will be needed, this latest study from the La Jolla Institute for Immunity may help guide clinical laboratories and in vitro diagnostic companies that are developing serological antibody tests for COVID-19 and lead to more definitive answers as to how long antibodies confer protective immunity.
The St. Louis-based in vitro diagnostics (IVD) developer is making PrecivityAD available to physicians while awaiting FDA clearance for the non-invasive test
Clinical laboratories have long awaited a test for Alzheimer’s disease and the wait may soon be over. The first blood test to aid physicians and clinical laboratories in the diagnosis of patients with memory and cognitive issues has been released by C₂N Diagnostics of St. Louis. The test measures biomarkers associated with amyloid plaques in the brain—the pathological hallmark of Alzheimer’s.
In a news release, PrecivityAD describes the laboratory-developed test (LDT) as “a highly sensitive blood test using mass spectrometry and is performed in C₂N’s CLIA-certified laboratory. While the test by itself cannot diagnose Alzheimer’s disease … the test is an important new tool for physicians to aid in the evaluation process.”
PrecivityAD provides physicians with an Amyloid Probability Score (APS) for each patient. For example:
A low APS (0-36) is consistent with a negative amyloid PET scan result and, thus, has a low likelihood of amyloid plaques, an indication other causes of cognitive symptoms should be investigated.
An intermediate APS (37-57) does not distinguish between the presence or absence of amyloid plaques and indicates further diagnostic evaluation may be needed to assess the underlying cause(s) for the patient’s cognitive symptoms.
A high APS (58-100) is consistent with a positive amyloid positron-emission tomography (PET) scan result and, thus, a high likelihood of amyloid plaques. Presence of amyloid plaques is consistent with an Alzheimer’s disease diagnosis in someone who has cognitive decline, but alone is insufficient for a final diagnosis.
The $1,250 test is not currently covered by health insurance or Medicare. However, C₂N Diagnostics has pledged to offer discounts to patients based on income levels.
Jeff Cummings, MD, ScD (above) Research Professor, Department of Brain Health, University of Nevada, Las Vegas, said in a C₂N Diagnostics press release, “A blood test for Alzheimer’s is a game changer.” While there is no cure for Alzheimer’s, a non-invasive blood test can help providers diagnose patients when their symptoms are mild and often misdiagnosed. “Advances in Alzheimer’s diagnostics are key to more effective identification, diagnosis, and clinical trial recruitment,” he added. Currently, brain changes caused by the disease are most commonly identified through PET scans. (Photo copyright: University of Nevada Las Vegas.)
Additional Research Requested
While C₂N’s PrecivityAD is the first test of its kind to reach the commercial market, it has not received US Food and Drug Administration (FDA) clearance, nor has the company published detailed data on the test’s accuracy. However, the PrecivityAD website says the laboratory-developed test “correctly identified brain amyloid plaque status (as determined by quantitative PET scans) in 86%” of 686 patients, all of whom were older than 60 years of age with subjective cognitive impairment or dementia.
But some Alzheimer’s advocacy groups are tempering their enthusiasm about the breakthrough. Eliezer Masliah, MD, Director of the Division of Neuroscience, National Institute on Aging, told the Associated Press (AP), “I would be cautious about interpreting any of these things,” he said of the company’s claims. “We’re encouraged, we’re interested, we’re funding this work, but we want to see results.”
Heather Snyder, PhD, Vice President, Medical and Scientific Relations at the Alzheimer’s Association told the AP her organization will not endorse a test without FDA clearance. The Alzheimer’s Association also would like to see the test studied in larger and diverse populations. “It’s not quite clear how accurate or generalizable the results are,” she said.
Braunstein defended the decision to make the test for Alzheimer’s immediately available to physicians, asking in the AP article, “Should we be holding that technology back when it could have a big impact on patient care?”
Howard Fillit, MD, Founding Executive Director and Chief Science Officer of the Alzheimer’s Drug Discovery Foundation (ADDF), maintains the first-of-its-kind blood test is an important milestone in Alzheimer’s research. ADDF invested in C₂N’s development of the test.
“Investing in biomarker research has been a core goal for the ADDF because having reliable, accessible, and affordable biomarkers for Alzheimer’s diagnosis is step one in finding drugs to prevent, slow, and even cure the disease,” Fillit said in an ADDF news release.
C₂N is also developing a Brain Health Panel to detect multiple blood-based markers for Alzheimer’s disease that will aid in better disease staging, treatment monitoring, and differential diagnosis.
Second Alzheimer’s Test in Development
Soon medical laboratories may have two different in vitro diagnostic tests for Alzheimer’s disease. On December 2, Fujirebio Diagnostics filed for FDA 510(k) premarket clearance for its Lumipulse G β-Amyloid Ratio (1-42/1-40) test, which looks for biomarkers found in cerebral spinal fluid.
“Accurate and earlier intervention will also facilitate the development of new drug therapies, which are urgently needed as the prevalence of Alzheimer’s disease increases with a rapidly aging population globally,” Fujirebio Diagnostics President and CEO Monte Wiltse said in a news release.
The Lumipulse G β-Amyloid test, which is intended for use in patients aged 50 and over presenting with cognitive impairment, has received CE-marking for use in the European Union.
Clinical laboratory managers will want to keep a close eye on rapidly evolving developments in testing for Alzheimer’s disease. It is the sixth leading cause of death in the United States and any clinical laboratory test that could produce an early and accurate diagnosis of Alzheimer’s Disease would become a valuable tool for physicians who treat patients with the symptoms of Alzheimer’s.
The AI protein-structure-prediction system may ‘revolutionize life sciences by enabling researchers to better understand disease,’ researchers say
Genomics leaders watched with enthusiasm as artificial intelligence (AI) accelerated discoveries that led to new clinical laboratory diagnostic tests and advanced the evolution of personalized medicine. Now Google’s London-based DeepMind has taken that a quantum step further by demonstrating its AI can predict the shape of proteins to within the width of one atom and model three-dimensional (3D) structures of proteins that scientist have been trying to map accurately for 50 years.
Pathologists and clinical laboratory professionals know that it is estimated that there are around 30,000 human genes. But the human proteome has a much larger number of unique proteins. The total number is still uncertain because scientists continue to identify new human proteins. For this reason, more knowledge of the human protein is expected to trigger an expanding number of new assays that can be used by medical laboratories for diagnostic, therapeutic, and patient-monitoring purposes.
DeepMind’s AI tool is called AlphaFold and the protein-structure-prediction system will enable scientists to quickly move from knowing a protein’s DNA sequence to determining its 3D shape without time-consuming experimentation. It “is expected to accelerate research into a host of illnesses, including COVID-19,” BBC News reported.
This protein-folding breakthrough not only answers one of biology’s biggest mysteries, but also has the potential to revolutionize life sciences by enabling researchers to better understand disease processes and design personalized therapies that target specific proteins.
In November, DeepMind’s AlphaFold won the 14th Community Wide Experiment on Critical Assessment of Techniques for Protein Structure Prediction (CASP14), a biennial competition in which entrants receive amino acid sequences for about 100 proteins whose 3D structures are unknown. By comparing the computational predictions with the lab results, each CASP14 competitor received a global distance test (GDT) score. Scores above 90 out of 100 are considered equal to experimental methods. AlphaFold produced models for about two-thirds of the CASP14 target proteins with GDT scores above 90, a CASP14 press release states.
According to MIT Technology Review, DeepMind’s discovery is significant. That’s because its speed at predicting the structure of proteins is unprecedented and it matched the accuracy of several techniques used in clinical laboratories, including:
Unlike the laboratory techniques, which, MIT noted, are “expensive and slow” and “can take hundreds of thousands of dollars and years of trial and error for each protein,” AlphaFold can predict a protein’s shape in a few days.
“AlphaFold is a once in a generation advance, predicting protein structures with incredible speed and precision,” Arthur D. Levinson, PhD, Founder and CEO of Calico Life Sciences, said in a DeepMind blogpost. “This leap forward demonstrates how computational methods are poised to transform research in biology and hold much promise for accelerating the drug discovery process.”
Science reported that AlphaFold, which scored a median of 87—25 points above the next best predictions—did so well that CASP14 organizers worried DeepMind may have been somehow cheated. To validate the results, they asked AlphaFold to complete a “special challenge”—modeling a membrane protein from an ancient species of microbes called archaea, which they had been unable to model satisfactorily using X-ray crystallography. AlphaFold returned a detailed image of a three-part protein with two long helical arms in the middle. “It’s almost perfect,” Andrei Lupas, PhD, Director at the Max Planck Institute for Developmental Biology, told Science. “They could not possibly have cheated on this. I don’t know how they do it.” (Graphic copyright: DeepMind/Nature.)
“Even tiny rearrangements of these vital molecules can have catastrophic effects on our health, so one of the most efficient ways to understand disease and find new treatments is to study the proteins involved,” Moult said in the CASP14 press release. “There are tens of thousands of human proteins and many billions in other species, including bacteria and viruses, but working out the shape of just one requires expensive equipment and can take years.”
Science reported that the 3D structures of only 170,000 proteins have been solved, leaving roughly 200 million proteins that have yet to be modeled. Therefore, AlphaFold will help researchers in the fields of genomics, microbiomics, proteomics, and other omics understand the structure of protein complexes.
“Being able to investigate the shape of proteins quickly and accurately has the potential to revolutionize life sciences,” Andriy Kryshtafovych, PhD, Project Scientist at University of California, Davis, Genome Center, said in the press release. “Now that the problem has been largely solved for single proteins, the way is open for development of new methods for determining the shape of protein complexes—collections of proteins that work together to form much of the machinery of life, and for other applications.”
Clinical laboratories play a major role in the study of human biology. This breakthrough in genomics research and new insights into proteomics may provide opportunities for medical labs to develop new diagnostic tools and assays that better identify proteins of interest for diagnostic and therapeutic purposes.
Genomics experts say this is a sign that clinical laboratory genetics testing is maturing into a powerful tool for population health
Faced with lagging sales and employee layoffs, genomics companies in the genealogy DNA testing market are shifting their focus to the healthcare aspects of the consumer genomics data they’ve compiled and aggregated.
Recent analysis of the sales of genetic tests from Ancestry and 23andMe show the market is definitely cooling, and the analysts speculate that—independent of the consequences of the COVID-19 pandemic on consumer behavior—the two clinical laboratory genetic testing companies may already have done testing for the majority of consumers who want to buy these tests.
“I think the consumer market is going to become more integrated into the healthcare experience,” Joe Grzymski, PhD, told GenomeWeb. “Whether that occurs through your primary care doctor, your large integrated health network, or your payor, I think there will be profound changes in society’s tolerance for using genetics for prevention.”
In February, Ancestry, the largest company in the home DNA testing space, announced it was laying off 6% of its workforce or approximately 100 people, across different departments due to a decline in sales, CNBC reported. Several weeks earlier, 23andMe, the second largest company in this market, also announced it was laying off about 100 people or 14% of its workforce due to declining sales.
“I wasn’t surprised by the news,” said Linda Avey, a 23andMe co-founder who is now co-founder and Chief Executive Officer at Precisely Inc., a genomics company headquartered in San Francisco. She was commenting to GenomeWeb on the recent restructuring at her former company. “The level of expensive advertising has been insane here in the US. Those [customer acquisition costs] are not a sustainable model.”
CNBC surmised that the lull in at-home genetic testing is due mainly to:
A drought of early adopters. Individuals who were interested in the testing for genealogical and health reasons, and who believed in the value of the tests, have already purchased the product.
Privacy concerns. Some potential customers may have reservations about having their DNA information collected and stored in a database due to concerns about how that data is safeguarded and its potential uses by outside companies, law enforcement, and governments.
COVID-19 May or May Not Be a Factor in Declining DNA Testing Sales
The COVID-19 pandemic may be playing a role in the decline in sales of at-home DNA testing kits. However, there are indications that the market was cooling before the virus occurred.
An article in MIT Technology Review reported that 26 million people had purchased at-home DNA testing kits by the beginning of 2019. The article also estimated that if the market continued at that pace, 100 million people were expected to purchase the tests by the end of 2020.
However, data released by research firm Second Measure, a company that analyzes credit and debit card purchases, may show a different story, reported Vox. The data showed a general decline in test kit sales in 2019. Ancestry’s sales were down 38% and 23andMe’s sales were down 54% in November 2019 compared to November 2018. The downward trend continued in December with Ancestry sales declining 15% and 23andMe sales declining 48% when compared to December 2018.
Second Measure, however, compiled data from the two companies’ websites only. They did not include testing kits that may have been purchased through other sources such as Amazon, or at brick and mortar locations.
Nevertheless, the measures being taken by genomics companies to shore up their market indicates the Second Measure data is accurate or very close.
Rise of Population-level Genomics
This decline in genealogical sales seems to be behind DNA-testing companies shifting focus to the healthcare aspects of consumer genomics. Companies like 23andMe and Ancestry are looking into developing health reports based on their customers’ data that can ascertain an individual’s risk for certain health conditions, or how they may react to prescription medications.
“We are seeing the next wave of maturity of the genetics market,” Othman Laraki, co-founder and CEO of Color Genomics, told CNBC. “If expensive diagnostic testing was genomics’ equivalent of mainframe computers, direct to consumer ancestry genetics was the hobbyist use. While the early adopter wave is petering out, we are seeing the real market (the equivalent of a PC in every home and a phone in every pocket), which is population-level use of genetics, taking hold.” (Photo copyright: San Francisco Business Times.)
For some genomics companies like 23andMe, the at-home DNA testing market was never specifically about selling testing kits. Rather, these companies envisioned a market where consumers would pay to have their DNA analyzed to obtain data on their ancestry and health, and in turn the testing companies would sell the aggregated consumer data to other organizations, such as pharmaceutical companies.
“Remember that 23andMe was never in the consumer genomics business, they were in the data aggregation business,” Spencer Wells, PhD, founder and Executive Director of the Insitome Institute, a US-based 501(c)3 nonprofit think tank focused on key areas in the field of personal genomics, told GenomeWeb. “They created a database that should in principle allow them to do what they promised, which is to improve people’s health through genomic testing.”
Even with clinical laboratory testing currently focused on COVID-19 testing, there remains an opportunity to sequence large numbers of people through at-home DNA testing and then incorporate those findings into the practice of medicine. The hope is that sales will again accelerate once consumers feel there is a compelling need for the tests.
Pathologists and clinical laboratory managers will want to watch to see if the companies that grew big by selling ancestry and genealogy tests to consumers will start to send sales reps into physicians’ offices to offer genetic tests that would be useful in diagnosing and treating patients.
