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.
DeepMind hopes its unrivaled collection of data, enabled by artificial intelligence, may advance development of precision medicines, new medical laboratory tests, and therapeutic treatments
‘Tis the season for giving, and one United Kingdom-based artificial intelligence (AI) research laboratory is making a sizeable gift. After using AI and machine learning to create “the most comprehensive map of human proteins,” in existence, DeepMind, a subsidiary of Alphabet Inc. (NASDAQ:GOOGL), parent company of Google, plans to give away for free its database of millions of protein structure predictions to the global scientific community and to all of humanity, The Verge reported.
Pathologists and clinical laboratory scientists developing proteomic assays understand the significance of this gesture. They know how difficult and expensive it is to determine protein structures using sequencing of amino acids. That’s because the various types of amino acids in use cause the [DNA] string to “fold.” Thus, the availability of this data may accelerate the development of more diagnostic tests based on proteomics.
“For decades, scientists have been trying to find a method to reliably determine a protein’s structure just from its sequence of amino acids. Attraction and repulsion between the 20 different types of amino acids cause the string to fold in a feat of ‘spontaneous origami,’ forming the intricate curls, loops, and pleats of a protein’s 3D structure. This grand scientific challenge is known as the protein-folding problem,” a DeepMind statement noted.
Enter DeepMind’s AlphaFold AI platform to help iron things out. “Experimental techniques for determining structures are painstakingly laborious and time consuming (sometimes taking years and millions of dollars). Our latest version [of AlphaFold] can now predict the shape of a protein, at scale and in minutes, down to atomic accuracy. This is a significant breakthrough and highlights the impact AI can have on science,” DeepMind stated.
Release of Data Will Be ‘Transformative’
In July, DeepMind announced it would begin releasing data from its AlphaFold Protein Structure Database which contains “predictions for the structure of some 350,000 proteins across 20 different organisms,” The Verge reported, adding, “Most significantly, the release includes predictions for 98% of all human proteins, around 20,000 different structures, which are collectively known as the human proteome. By the end of the year, DeepMind hopes to release predictions for 100 million protein structures.”
According to Edith Heard, PhD, Director General of the European Molecular Biology Laboratory (EMBL), the open release of such a dataset will be “transformative for our understanding of how life works,” The Verge reported.
“I see this as the culmination of the entire 10-year-plus lifetime of DeepMind,” company CEO and co-founder Demis Hassabis (above), told The Verge. “From the beginning, this is what we set out to do: to make breakthroughs in AI, test that on games like Go and Atari, [and] apply that to real-world problems, to see if we can accelerate scientific breakthroughs and use those to benefit humanity.” The release of DeepMind’s entire protein prediction database will certainly do that. Clinical laboratory scientists worldwide will have free access to use it in developing new precision medicine treatments based on proteomics. (Photo copyright: BBC.)
Free Data about Proteins Will Accelerate Research on Diseases, Treatments
Research into how protein folds and, thereby, functions could have implications to fighting diseases and developing new medicines, according to DeepMind.
“This will be one of the most important datasets since the mapping of the human genome,” said Ewan Birney, PhD, Deputy Director General of the EMBL, in the DeepMind statement. EMBL worked with DeepMind on the dataset.
DeepMind protein prediction data are already being used by scientists in medical research. “Anyone can use it for anything. They just need to credit the people involved in the citation,” said Demis Hassabis, DeepMind CEO and Co-founder, in The Verge.
In a blog article, Hassabis listed several projects and organizations already using AlphaFold. They include:
“As researchers seek cures for diseases and pursue solutions to other big problems facing humankind—including antibiotic resistance, microplastic pollution, and climate change—they will benefit from fresh insights in the structure of proteins,” Hassabis wrote.
Because of the deep financial backing that Alphabet/Google can offer, it is reasonable to predict that DeepMind will make progress with its AI technology that regularly adds capabilities and accuracy, allowing AlphaFold to be effective for many uses.
This will be particularly true for the development of new diagnostic assays that will give clinical laboratories better tools for diagnosing disease earlier and more accurately.
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.
Clinical laboratories and pathology groups may eventually use these devices to detect minute quantities of biomarkers
IBM has regularly declared its interest in being a player in the field of healthcare big data. Now comes news that the information technology giant wants to develop lab-on-a-chip (LOC) technology that can handle different types of clinical laboratory and anatomic pathology tests.
As reported in Nature Nanotechnology, researchers at IBM are working with a team from Mount Sinai Health System. Together, they created a lab-on-a-chip device capable of separating biomolecules as small as 20nm in length from urine, saliva, or blood samples without the need for specialized clinical laboratory equipment. The technology is called nanoDLD.
Current testing of this lab-on-a-chip focuses on exosomes and cancer research. However, researchers note that the asymmetric pillar array on their silicon chip can also separate DNA, viruses, and protein complexes. With further development, they hope to separate particles down to 10nm in length. This would allow isolation of specific proteins. (more…)
