(Press-News.org) Antibodies are not only produced by our immune cells to fight viruses and other pathogens in the body. For a few decades now, medicine has also been using antibodies produced by biotechnology as drugs. This is because antibodies are extremely good at binding specifically to molecular structures according to the lock-and-key principle. Their use ranges from oncology to the treatment of autoimmune diseases and neurodegenerative conditions.
However, developing such antibody drugs is anything but simple. The basic requirement is for an antibody to bind to its target molecule in an optimal way. At the same time, an antibody drug must fulfil a host of additional criteria. For example, it should not trigger an immune response in the body, it should be efficient to produce using biotechnology, and it should remain stable over a long period of time.
Once scientists have found an antibody that binds to the desired molecular target structure, the development process is far from over. Rather, this marks the start of a phase in which researchers use bioengineering to try to improve the antibody's properties. Scientists led by Sai Reddy, a professor at the Department of Biosystems Science and Engineering at ETH Zurich in Basel, have now developed a machine learning method that supports this optimisation phase, helping to develop more effective antibody drugs.
Robots can't manage more than a few thousand
When researchers optimise an entire antibody molecule in its therapeutic form (i.e. not just a fragment of an antibody), it used to start with an antibody lead candidate that binds reasonably well to the desired target structure. Then researchers randomly mutate the gene that carries the blueprint for the antibody in order to produce a few thousand related antibody candidates in the lab. The next step is to search among them to find the ones that bind best to the target structure. "With automated processes, you can test a few thousand therapeutic candidates in a lab. But it is not really feasible to screen any more than that," Reddy says. Typically, the best dozen antibodies from this screening move on to the next step and are tested for how well they meet additional criteria. "Ultimately, this approach lets you identify the best antibody from a group of a few thousand," he says.
Candidate pool massively increased by machine learning
Reddy and his colleagues are now using machine learning to increase the initial set of antibodies to be tested to several million. "The more candidates there are to choose from, the greater the chance of finding one that really meets all the criteria needed for drug development," Reddy says.
The ETH researchers provided the proof of concept for their new method using Roche's antibody cancer drug Herceptin, which has been on the market for 20 years. "But we weren't looking to make suggestions for how to improve it - you can't just retroactively change an approved drug," Reddy explains. "Our reason for choosing this antibody is because it is well known in the scientific community and because its structure is published in open-access databases."
Computer predictions
Starting out from the DNA sequence of the Herceptin antibody, the ETH researchers created about 40,000 related antibodies using a CRISPR mutation method they developed a few years ago. Experiments showed that 10,000 of them bound well to the target protein in question, a specific cell surface protein. The scientists used the DNA sequences of these 40,000 antibodies to train a machine learning algorithm.
They then applied the trained algorithm to search a database of 70 million potential antibody DNA sequences. For these 70 million candidates, the algorithm predicted how well the corresponding antibodies would bind to the target protein, resulting in a list of millions of sequences expected to bind.
Using further computer models, the scientists predicted how well these millions of sequences would meet the additional criteria for drug development (tolerance, production, physical properties). This reduced the number of candidate sequences to 8,000.
Improved antibodies found
From the list of optimised candidate sequences on their computer, the scientists selected 55 sequences from which to produce antibodies in the lab and characterise their properties. Subsequent experiments showed that several of them bound even better to the target protein than Herceptin itself, as well as being easier to produce and more stable than Herceptin. "One new variant may even be better tolerated in the body than Herceptin," says Reddy. "It is known that Herceptin triggers a weak immune response, but this is typically not a problem in this case." However, it is a problem for many other antibodies and is necessary to prevent for drug development.
The ETH scientists are now applying their artificial intelligence method to optimise antibody drugs that are in clinical development. To this end, they recently founded the ETH spin-off deepCDR Biologics, which partners with both early stage and established biotech and pharmaceutical companies for antibody drug development.
INFORMATION:
COVID-19 has been associated with increases in opioid overdose deaths, which may be in part because the pandemic limited access to buprenorphine, a treatment used for opioid dependency, according to a new study led by Princeton University researchers.
The researchers found that Americans who were already taking opioids did not experience disruptions in their supply. Patients who were not previously taking opioids for pain management were less likely to receive a new prescription in the first months of the pandemic, but prescriptions for new patients soon bounced back to previous levels.
At the same time, fewer ...
A number of SARS-CoV-2 variants have emerged from immunocompromised hosts, research has identified. It is thought that variants of concern - including B.1.1.7, a variant first identified in Kent - were a result of long-term infection in people with a weakened immune system.
Persistent infections in immunocompromised people could cause the virus to mutate more frequently because the person's immune system cannot clear the virus as quickly as the immune system of a healthy person.
Authors Professor Wendy Barclay, Dr Thomas Peacock, Professor Julian Hiscox and Rebekah Penrice-Randal explain the importance of monitoring genetic changes in SARS-CoV-2 for future control of the virus: ...
Besides enabling more potent smartphones and higher download speeds while riding the subway, cutting-edge technologies like artificial intelligence, robotics, and wireless communications are on the verge of revolutionizing well-established industrial fields. A remarkable example is "smart agriculture," which has seen a tremendous increase in the use of drones for various tasks, especially in Japan.
Drones, or "unmanned aerial vehicles" (UAVs), have been the focus of extensive research for agricultural applications. For example, they can take aerial images of a field and, through subsequent image processing, identify problems in specific areas of the crop fields. Another notable use case for UAVs that has been quickly gaining traction is the spraying of pesticides. In ...
The extreme summer drought of 2018 was a special situation for both nature and scientists. It was very hard on the forest. At the same time, it offered researchers from the Universities of Basel (Switzerland) and Würzburg (Germany) the opportunity to study the reaction of trees to this climatic phenomenon.
Research in the treetops
"The summer of 2018 was hotter and drier than in any other year since weather records began," says ecophysiologist Professor Bernhard Schuldt from the University of Wuerzburg. Together with Dr Matthias Arend and Professor Ansgar Kahmen from the University of Basel, he was significantly involved in the study, which is published in the scientific journal PNAS. "A unique opportunity arose for us to study the influence of ...
A new paper in the Review of Economic Studies indicates that disease can alter the social networks and economic growth of countries for generations, even after the disease itself is eradicated.
Social networks are an important determinant of a country's growth as they affect the diffusion of ideas and the rate of technological progress. But social networks also diffuse diseases that can rapidly spread and dampen growth.
As ideas and germs diffuse through the same human interactions, the network structure of a country ultimately depends on its epidemiological environment. In countries with low prevalence of infectious diseases, high diffusion networks ...
An estimated 334,000 COVID-19 cases are attributable to meatpacking plants, resulting in $11.2 billion in economic damage, according to a new study led by a researcher at the University of California, Davis. The study was published in the journal Food Policy.
It found that beef- and pork-processing plants more than doubled per capita infection rates in counties that had them. Chicken-processing plants increased transmission rates by 20 percent. The study looked specifically at large meatpacking plants generating more than 10 million pounds per month.
Conservative estimate
Researchers said both the economic impact ...
LAWRENCE -- How did the first humans migrate to populate North America? It's one of the great scientific puzzles of our day, especially because forbidding glaciers covered most of Canada, Alaska and Pacific Northwest during the Last Glacial Maximum (LGM). These glaciers limited human movements between northern ice-free areas, like the Beringia Land Bridge, and southern ice-free areas, like the continental United States.
Now, research from the University of Kansas into the whole genomes of the American pine marten and Pacific pine marten -- weasel-like mammals that range today from Alaska to the American Southwest -- could shed light ...
Philadelphia, April 15, 2021 - A new study shows that markers of fear recall differ between men and women, but in a hormone-dependent manner.
Aberrant fear-memory processing in the brain is thought to underlie anxiety disorders, which affect hundreds of millions of people worldwide. The neurobiological mechanisms underlying these disorders remain poorly understood, but recent studies suggest that neural oscillations in the prefrontal cortex can reflect the strength of fear recall activity, providing a physiological measure.
Women suffer from anxiety disorders at twice the rate of men and indeed ...
Researchers in Sweden have developed a more eco-friendly way to remove heavy metals, dyes and other pollutants from water. The answer lies in filtering wastewater with a gel material taken from plant cellulose and spiked with small carbon dots produced in a microwave oven.
Reporting in the journal Sustainable Marials and Technologies, researchers from KTH Royal Institute of Technology, in collaboration with Politecnico di Torino, engineered a more sustainable technique for producing hydrogel composites, a type of material that is wteidely studied for wastewater decontamination.
Minna Hakkarainen, who leads ...
PITTSBURGH, April 15, 2021 - Oncologists faced with treating older women with breast cancer often must decide if the treatment may be more detrimental than the cancer. A study published today in JAMA Network Open by researchers at UPMC Hillman Cancer Center and the University of Pittsburgh School of Medicine sheds new light on this choice and suggests the rate of cancer recurrence or survival may be no different in treated vs. untreated elderly patients diagnosed in the early stages of the cancer diagnosed most commonly in women.
"As a breast surgeon, I want to give my patients the best chance of survival with the best quality ...
