The Shiny–and Potentially Dangerous—New Tool for Predicting Human Behavior

Studies of twins have played an important role in determining that genetic differences play a role in the development of differences in behavior.
[Editor's Note: This essay is in response to our current Big Question, which we posed to experts with different perspectives: "How should DNA tests for intelligence be used, if at all, by parents and educators?"]
Imagine a world in which pregnant women could go to the doctor and obtain a simple inexpensive genetic test of their unborn child that would allow them to predict how tall he or she would eventually be. The test might also tell them the child's risk for high blood pressure or heart disease.
Can we use DNA not to understand, but to predict who is going to be intelligent or extraverted or mentally ill?
Even more remarkable -- and more dangerous -- the test might predict how intelligent the child would be, or how far he or she could be expected to go in school. Or heading further out, it might predict whether he or she will be an alcoholic or a teetotaler, or straight or gay, or… you get the idea. Is this really possible? If it is, would it be a good idea? Answering these questions requires some background in a scientific field called behavior genetics.
Differences in human behavior -- intelligence, personality, mental illness, pretty much everything -- are related to genetic differences among people. Scientists have known this for 150 years, ever since Darwin's half-cousin Francis Galton first applied Shakespeare's phrase, "Nature and Nurture" to the scientific investigation of human differences. We knew about the heritability of behavior before Mendel's laws of genetics had been re-discovered at the end of the last century, and long before the structure of DNA was discovered in the 1950s. How could discoveries about genetics be made before a science of genetics even existed?
The answer is that scientists developed clever research designs that allowed them to make inferences about genetics in the absence of biological knowledge about DNA. The best-known is the twin study: identical twins are essentially clones, sharing 100 percent of their DNA, while fraternal twins are essentially siblings, sharing half. To the extent that identical twins are more similar for some trait than fraternal twins, one can infer that heredity is playing a role. Adoption studies are even more straightforward. Is the personality of an adopted child more like the biological parents she has never seen, or the adoptive parents who raised her?
Twin and adoption studies played an important role in establishing beyond any reasonable doubt that genetic differences play a role in the development of differences in behavior, but they told us very little about how the genetics of behavior actually worked. When the human genome was finally sequenced in the early 2000s, and it became easier and cheaper to obtain actual DNA from large samples of people, scientists anticipated that we would soon find the genes for intelligence, mental illness, and all the other behaviors that were known to be "heritable" in a general way.
But to everyone's amazement, the genes weren't there. It turned out that there are thousands of genes related to any given behavior, so many that they can't be counted, and each one of them has such a tiny effect that it can't be tied to meaningful biological processes. The whole scientific enterprise of understanding the genetics of behavior seemed ready to collapse, until it was rescued -- sort of -- by a new method called polygenic scores, PGS for short. Polygenic scores abandon the old task of finding the genes for complex human behavior, replacing it with black-box prediction: can we use DNA not to understand, but to predict who is going to be intelligent or extraverted or mentally ill?
Prediction from observing parents works better, and is far easier and cheaper, than anything we can do with DNA.
PGS are the shiny new toy of human genetics. From a technological standpoint they are truly amazing, and they are useful for some scientific applications that don't involve making decisions about individual people. We can obtain DNA from thousands of people, estimate the tiny relationships between individual bits of DNA and any outcome we want — height or weight or cardiac disease or IQ — and then add all those tiny effects together into a single bell-shaped score that can predict the outcome of interest. In theory, we could do this from the moment of conception.
Polygenic scores for height already work pretty well. Physicians are debating whether the PGS for heart disease are robust enough to be used in the clinic. For some behavioral traits-- the most data exist for educational attainment -- they work well enough to be scientifically interesting, if not practically useful. For traits like personality or sexual orientation, the prediction is statistically significant but nowhere close to practically meaningful. No one knows how much better any of these predictions are likely to get.
Without a doubt, PGS are an amazing feat of genomic technology, but the task they accomplish is something scientists have been able to do for a long time, and in fact it is something that our grandparents could have done pretty well. PGS are basically a new way to predict a trait in an individual by using the same trait in the individual's parents — a way of observing that the acorn doesn't fall far from the tree.
The children of tall people tend to be tall. Children of excellent athletes are athletic; children of smart people are smart; children of people with heart disease are at risk, themselves. Not every time, of course, but that is how imperfect prediction works: children of tall parents vary in their height like anyone else, but on average they are taller than the rest of us. Prediction from observing parents works better, and is far easier and cheaper, than anything we can do with DNA.
But wait a minute. Prediction from parents isn't strictly genetic. Smart parents not only pass on their genes to their kids, but they also raise them. Smart families are privileged in thousands of ways — they make more money and can send their kids to better schools. The same is true for PGS.
The ability of a genetic score to predict educational attainment depends not only on examining the relationship between certain genes and how far people go in school, but also on every personal and social characteristic that helps or hinders education: wealth, status, discrimination, you name it. The bottom line is that for any kind of prediction of human behavior, separation of genetic from environmental prediction is very difficult; ultimately it isn't possible.
Still, experts are already discussing how to use PGS to make predictions for children, and even for embryos.
This is a reminder that we really have no idea why either parents or PGS predict as well or as poorly as they do. It is easy to imagine that a PGS for educational attainment works because it is summarizing genes that code for efficient neurological development, bigger brains, and swifter problem solving, but we really don't know that. PGS could work because they are associated with being rich, or being motivated, or having light skin. It's the same for predicting from parents. We just don't know.
Still, experts are already discussing how to use PGS to make predictions for children, and even for embryos.
For example, maybe couples could fertilize multiple embryos in vitro, test their DNA, and select the one with the "best" PGS on some trait. This would be a bad idea for a lot of reasons. Such scores aren't effective enough to be very useful to parents, and to the extent they are effective, it is very difficult to know what other traits might be selected for when parents try to prioritize intelligence or attractiveness. People will no doubt try it anyway, and as a matter of reproductive freedom I can't think of any way to stop them. Fortunately, the practice probably won't have any great impact one way or another.
That brings us to the ethics of PGS, particularly in the schools. Imagine that when a child enrolls in a public school, an IQ test is given to her biological parents. Children with low-IQ parents are statistically more likely to have low IQs themselves, so they could be assigned to less demanding classrooms or vocational programs. Hopefully we agree that this would be unethical, but let's think through why.
First of all, it would be unethical because we don't know why the parents have low IQs, or why their IQs predict their children's. The parents could be from a marginalized ethnic group, recognizable by their skin color and passed on genetically to their children, so discriminating based on a parent's IQ would just be a proxy for discriminating based on skin color. Such a system would be no more than a social scientific gloss on an old-fashioned program for perpetuating economic and cognitive privilege via the educational system.
People deserve to be judged on the basis of their own behavior, not a genetic test.
Assigning children to classrooms based on genetic testing would be no different, although it would have the slight ethical advantage of being less effective. The PGS for educational attainment could reflect brain-efficiency, but it could also depend on skin color, or economic advantage, or personality, or literally anything that is related in any way to economic success. Privileging kids with higher genetic scores would be no different than privileging children with smart parents. If schools really believe that a psychological trait like IQ is important for school placement, the sensible thing is to administer the children an actual IQ test – not a genetic test.
IQ testing has its own issues, of course, but at least it involves making decisions about individuals based on their own observable characteristics, rather than on characteristics of their parents or their genome. If decisions must be made, if resources must be apportioned, people deserve to be judged on the basis of their own behavior, the content of their character. Since it can't be denied that people differ in all sorts of relevant ways, this is what it means for all people to be created equal.
[Editor's Note: Read another perspective in the series here.]
Scientists find enzymes in nature that could replace toxic chemicals
Basecamp Research is using portable labs like this one to gather samples from ecosystems around the world.
Some 900 miles off the coast of Portugal, nine major islands rise from the mid-Atlantic. Verdant and volcanic, the Azores archipelago hosts a wealth of biodiversity that keeps field research scientist, Marlon Clark, returning for more. “You’ve got this really interesting biogeography out there,” says Clark. “There’s real separation between the continents, but there’s this inter-island dispersal of plants and seeds and animals.”
It’s a visual paradise by any standard, but on a microscopic level, there’s even more to see. The Azores’ nutrient-rich volcanic rock — and its network of lagoons, cave systems, and thermal springs — is home to a vast array of microorganisms found in a variety of microclimates with different elevations and temperatures.
Clark works for Basecamp Research, a biotech company headquartered in London, and his job is to collect samples from ecosystems around the world. By extracting DNA from soil, water, plants, microbes and other organisms, Basecamp is building an extensive database of the Earth’s proteins. While DNA itself isn’t a protein, the information stored in DNA is used to create proteins, so extracting, sequencing, and annotating DNA allows for the discovery of unique protein sequences.
Using what they’re finding in the middle of the Atlantic and beyond, Basecamp’s detailed database is constantly growing. The outputs could be essential for cleaning up the damage done by toxic chemicals and finding alternatives to these chemicals.
Catalysts for change
Proteins provide structure and function in all living organisms. Some of these functional proteins are enzymes, which quite literally make things happen.
“Industrial chemistry is heavily polluting, especially the chemistry done in pharmaceutical drug development. Biocatalysis is providing advantages, both to make more complex drugs and to be more sustainable, reducing the pollution and toxicity of conventional chemistry," says Ahir Pushpanath, who heads partnerships for Basecamp.
“Enzymes are perfectly evolved catalysts,” says Ahir Pushpanath, a partnerships lead at Basecamp. ”Enzymes are essentially just a polymer, and polymers are made up of amino acids, which are nature’s building blocks.” He suggests thinking about it like Legos — if you have a bunch of Lego pieces and use them to build a structure that performs a function, “that’s basically how an enzyme works. In nature, these monuments have evolved to do life’s chemistry. If we didn’t have enzymes, we wouldn’t be alive.”
In our own bodies, enzymes catalyze everything from vision to digesting food to regrowing muscles, and these same types of enzymes are necessary in the pharmaceutical, agrochemical and fine chemical industries. But industrial conditions differ from those inside our bodies. So, when scientists need certain chemical reactions to create a particular product or substance, they make their own catalysts in their labs — generally through the use of petroleum and heavy metals.
These petrochemicals are effective and cost-efficient, but they’re wasteful and often hazardous. With growing concerns around sustainability and long-term public health, it's essential to find alternative solutions to toxic chemicals. “Industrial chemistry is heavily polluting, especially the chemistry done in pharmaceutical drug development,” Pushpanath says.
Basecamp is trying to replace lab-created catalysts with enzymes found in the wild. This concept is called biocatalysis, and in theory, all scientists have to do is find the right enzymes for their specific need. Yet, historically, researchers have struggled to find enzymes to replace petrochemicals. When they can’t identify a suitable match, they turn to what Pushpanath describes as “long, iterative, resource-intensive, directed evolution” in the laboratory to coax a protein into industrial adaptation. But the latest scientific advances have enabled these discoveries in nature instead.
Marlon Clark, a research scientist at Basecamp Research, looks for novel biochemistries in the Azores.
Glen Gowers
Enzyme hunters
Whether it’s Clark and a colleague setting off on an expedition, or a local, on-the-ground partner gathering and processing samples, there’s a lot to be learned from each collection. “Microbial genomes contain complete sets of information that define an organism — much like how letters are a code allowing us to form words, sentences, pages, and books that contain complex but digestible knowledge,” Clark says. He thinks of the environmental samples as biological libraries, filled with thousands of species, strains, and sequence variants. “It’s our job to glean genetic information from these samples.”
“We can actually dream up new proteins using generative AI," Pushpanath says.
Basecamp researchers manage this feat by sequencing the DNA and then assembling the information into a comprehensible structure. “We’re building the ‘stories’ of the biota,” Clark says. The more varied the samples, the more valuable insights his team gains into the characteristics of different organisms and their interactions with the environment. Sequencing allows scientists to examine the order of nucleotides — the organic molecules that form DNA — to identify genetic makeups and find changes within genomes. The process used to be too expensive, but the cost of sequencing has dropped from $10,000 a decade ago to as low as $100. Notably, biocatalysis isn’t a new concept — there have been waves of interest in using natural enzymes in catalysis for over a century, Pushpanath says. “But the technology just wasn’t there to make it cost effective,” he explains. “Sequencing has been the biggest boon.”
AI is probably the second biggest boon.
“We can actually dream up new proteins using generative AI,” Pushpanath says, which means that biocataylsis now has real potential to scale.
Glen Gowers, the co-founder of Basecamp, compares the company’s AI approach to that of social networks and streaming services. Consider how these platforms suggest connecting with the friends of your friends, or how watching one comedy film from the 1990s leads to a suggestion of three more.
“They’re thinking about data as networks of relationships as opposed to lists of items,” says Gowers. “By doing the same, we’re able to link the metadata of the proteins — by their relationships to each other, the environments in which they’re found, the way those proteins might look similar in sequence and structure, their surrounding genome context — really, this just comes down to creating a searchable network of proteins.”
On an Azores island, this volcanic opening may harbor organisms that can help scientists identify enzymes for biocatalysis to replace toxic chemicals.
Emma Bolton
Uwe Bornscheuer, professor at the Institute of Biochemistry at the University of Greifswald, and co-founder of Enzymicals, another biocatalysis company, says that the development of machine learning is a critical component of this work. “It’s a very hot topic, because the challenge in protein engineering is to predict which mutation at which position in the protein will make an enzyme suitable for certain applications,” Bornscheuer explains. These predictions are difficult for humans to make at all, let alone quickly. “It is clear that machine learning is a key technology.”
Benefiting from nature’s bounty
Biodiversity commonly refers to plants and animals, but the term extends to all life, including microbial life, and some regions of the world are more biodiverse than others. Building relationships with global partners is another key element to Basecamp’s success. Doing so in accordance with the access and benefit sharing principles set forth by the Nagoya Protocol — an international agreement that seeks to ensure the benefits of using genetic resources are distributed in a fair and equitable way — is part of the company's ethos. “There's a lot of potential for us, and there’s a lot of potential for our partners to have exactly the same impact in building and discovering commercially relevant proteins and biochemistries from nature,” Clark says.
Bornscheuer points out that Basecamp is not the first company of its kind. A former San Diego company called Diversa went public in 2000 with similar work. “At that time, the Nagoya Protocol was not around, but Diversa also wanted to ensure that if a certain enzyme or microorganism from Costa Rica, for example, were used in an industrial process, then people in Costa Rica would somehow profit from this.”
An eventual merger turned Diversa into Verenium Corporation, which is now a part of the chemical producer BASF, but it laid important groundwork for modern companies like Basecamp to continue to scale with today’s technologies.
“To collect natural diversity is the key to identifying new catalysts for use in new applications,” Bornscheuer says. “Natural diversity is immense, and over the past 20 years we have gained the advantages that sequencing is no longer a cost or time factor.”
This has allowed Basecamp to rapidly grow its database, outperforming Universal Protein Resource or UniProt, which is the public repository of protein sequences most commonly used by researchers. Basecamp’s database is three times larger, totaling about 900 million sequences. (UniProt isn’t compliant with the Nagoya Protocol, because, as a public database, it doesn’t provide traceability of protein sequences. Some scientists, however, argue that Nagoya compliance hinders progress.)
“Eventually, this work will reduce chemical processes. We’ll have cleaner processes, more sustainable processes," says Uwe Bornscheuer, a professor at the University of Greifswald.
With so much information available, Basecamp’s AI has been trained on “the true dictionary of protein sequence life,” Pushpanath says, which makes it possible to design sequences for particular applications. “Through deep learning approaches, we’re able to find protein sequences directly from our database, without the need for further laboratory-directed evolution.”
Recently, a major chemical company was searching for a specific transaminase — an enzyme that catalyzes a transfer of amino groups. “They had already spent a year-and-a-half and nearly two million dollars to evolve a public-database enzyme, and still had not reached their goal,” Pushpanath says. “We used our AI approaches on our novel database to yield 10 candidates within a week, which, when validated by the client, achieved the desired target even better than their best-evolved candidate.”
Basecamp’s other huge potential is in bioremediation, where natural enzymes can help to undo the damage caused by toxic chemicals. “Biocatalysis impacts both sides,” says Gowers. “It reduces the usage of chemicals to make products, and at the same time, where contamination sites do exist from chemical spills, enzymes are also there to kind of mop those up.”
So far, Basecamp's round-the-world sampling has covered 50 percent of the 14 major biomes, or regions of the planet that can be distinguished by their flora, fauna, and climate, as defined by the World Wildlife Fund. The other half remains to be catalogued — a key milestone for understanding our planet’s protein diversity, Pushpanath notes.
There’s still a long road ahead to fully replace petrochemicals with natural enzymes, but biocatalysis is on an upward trajectory. "Eventually, this work will reduce chemical processes,” Bornscheuer says. “We’ll have cleaner processes, more sustainable processes.”
Small changes in how a person talks could reveal Alzheimer’s earlier
In an initial study, Canary analyzed speech recordings with AI and identified early stage Alzheimer’s with 96 percent accuracy.
Dave Arnold retired in his 60s and began spending time volunteering in local schools. But then he started misplacing items, forgetting appointments and losing his sense of direction. Eventually he was diagnosed with early stage Alzheimer’s.
“Hearing the diagnosis made me very emotional and tearful,” he said. “I immediately thought of all my mom had experienced.” His mother suffered with the condition for years before passing away. Over the last year, Arnold has worked for the Alzheimer’s Association as one of its early stage advisors, sharing his insights to help others in the initial stages of the disease.
Arnold was diagnosed sooner than many others. It's important to find out early, when interventions can make the most difference. One promising avenue is looking at how people talk. Research has shown that Alzheimer’s affects a part of the brain that controls speech, resulting in small changes before people show other signs of the disease.
Now, Canary Speech, a company based in Utah, is using AI to examine elements like the pitch of a person’s voice and their pauses. In an initial study, Canary analyzed speech recordings with AI and identified early stage Alzheimer’s with 96 percent accuracy.
Developing the AI model
Canary Speech’s CEO, Henry O’Connell, met cofounder Jeff Adams about 40 years before they started the company. Back when they first crossed paths, they were both living in Bethesda, Maryland; O’Connell was a research fellow at the National Institutes of Health studying rare neurological diseases, while Adams was working to decode spy messages. Later on, Adams would specialize in building mathematical models to analyze speech and sound as a team leader in developing Amazon's Alexa.
It wasn't until 2015 that they decided to make use of the fit between their backgrounds. ““We established Canary Speech in 2017 to build a product that could be used in multiple languages in clinical environments,” O'Connell says.
The need is growing. About 55 million people worldwide currently live with Alzheimer’s, a number that is expected to double by 2050. Some scientists think the disease results from a buildup of plaque in the brain. It causes mild memory loss at first and, over time, this issue get worse while other symptoms, such as disorientation and hallucinations, can develop. Treatment to manage the disease is more effective in the earlier stages, but detection is difficult since mild symptoms are often attributed to the normal aging process.
O’Connell and Adams specialize in the complex ways that Alzheimer’s effects how people speak. Using AI, their mathematical model analyzes 15 million data points every minute, focusing on certain features of speech such as pitch, pauses and elongation of words. It also pays attention to how the vibrations of vocal cords change in different stages of the disease.
To create their model, the team used a type of machine learning called deep neural nets, which looks at multiple layers of data - in this case, the multiple features of a person’s speech patterns.
“Deep neural nets allow us to look at much, much larger data sets built out of millions of elements,” O’Connell explained. “Through machine learning and AI, we’ve identified features that are very sensitive to an Alzheimer’s patient versus [people without the disease] and also very sensitive to mild cognitive impairment, early stage and moderate Alzheimer's.” Based on their learnings, Canary is able to classify the disease stage very quickly, O’Connell said.
“When we’re listening to sublanguage elements, we’re really analyzing the direct result of changes in the brain in the physical body,” O’Connell said. “The brain controls your vocal cords: how fast they vibrate, the expansion of them, the contraction.” These factors, along with where people put their tongues when talking, function subconsciously and result in subtle changes in the sounds of speech.
Further testing is needed
In an initial trial, Canary analyzed speech recordings from phone calls to a large U.S. health insurer. They looked at the audio recordings of 651 policyholders who had early stage Alzheimer’s and 1018 who did not have the condition, aiming for a representative sample of age, gender and race. They used this data to create their first diagnostic model and found that it was 96 percent accurate in identifying Alzheimer’s.
Christian Herff, an assistant professor of neuroscience at Maastricht University in the Netherlands, praised this approach while adding that further testing is needed to assess its effectiveness.
“I think the general idea of identifying increased risk for cognitive impairment based on speech characteristics is very feasible, particularly when change in a user’s voice is monitored, for example, by recording speech every year,” Herff said. He noted that this can only be a first indication, not a full diagnosis. The accuracy still needs to be validated in studies that follows individuals over a period of time, he said.
Toby Walsh, a professor of artificial intelligence at the University of New South Wales, also thinks Canary’s tool has potential but highlights that Canary could diagnose some people who don’t really have the disease. “This is an interesting and promising application of AI,” he said, “but these tools need to be used carefully. Imagine the anxiety of being misdiagnosed with Alzheimer’s.”
As with many other AI tools, privacy and bias are additional issues to monitor closely, Walsh said.
Other languages
A related issue is that not everyone is fluent in English. Mahnaz Arvaneh, a senior lecturer in automatic control and systems engineering at the University of Sheffield, said this could be a blind spot.
“The system may not be very accurate for those who have English as their second language as their speaking patterns would be different, and any issue might be because of language deficiency rather than cognitive issues,” Arvaneh said.
The team is expanding to multiple languages starting with Japanese and Spanish. The elements of the model that make up the algorithm are very similar, but they need to be validated and retrained in a different language, which will require access to more data.
Recently, Canary analyzed the phone calls of 233 Japanese patients who had mild cognitive impairment and 704 healthy people. Using an English model they were able to identify the Japanese patients who had mild cognitive impairment with 78 percent accuracy. They also developed a model in Japanese that was 45 percent accurate, and they’re continuing to train it with more data.
The future
Canary is using their model to look at other diseases like Huntington’s and Parkinson’s. They’re also collaborating with pharmaceuticals to validate potential therapies for Alzheimer’s. By looking at speech patterns over time, Canary can get an indication of how well these drugs are working.
Dave Arnold and his wife dance at his nephew’s wedding in Rochester, New York, ten years ago, before his Alzheimer's diagnosis.
Dave Arnold
Ultimately, they want to integrate their tool into everyday life. “We want it to be used in a smartphone, or a teleconference call so that individuals could be examined in their home,” O’Connell said. “We could follow them over time and work with clinical teams and hospitals to improve the evaluation of patients and contribute towards an accurate diagnosis.”
Arnold, the patient with early stage Alzheimer’s, sees great promise. “The process of getting a diagnosis is already filled with so much anxiety,” he said. “Anything that can be done to make it easier and less stressful would be a good thing, as long as it’s proven accurate.”