22 Aug Applied Ethics of Polygenic Scores – Director’s Cut
(Longer version of article published at: https://leapsmag.com/the-shiny-and-potentially-dangerous-new-tool-for-predicting-human-behavior/) Posted here with permission)
Imagine a world in which pregnant parents 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. 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, so I will start there.
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 nineteen fifties. 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% 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 were 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? PGS are the shiny new toy of human genetics, and from a technological standpoint they are truly amazing. We can obtain DNA from hundreds and 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.
Without a doubt, PGS are an amazing feat of genomic technology, but I will suggest that 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 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. But in fact, PGS and prediction from parents are alike in this as well. First of all, prediction from parents is more genetic than you might think. For most traits, prediction works nearly as well from parents to adopted-away children as it does in genetically related families. You can see that this would be true for height, but to a surprising degree it is true for behavioral traits as well. The personalities of biological parents predict the personalities of adopted-away children much better than the personalities of the adoptive parents who raised them.
And even though they are based on DNA, PGS aren’t strictly genetic, either. This is a little complicated to explain. Consider the PGS for educational attainment. Your parents each have a score based on their DNA, and you inherit a random half from each parent. That means you don’t inherit half of each of your mother’s and father’s PGS. In studies that include both parents and children, you can ask how well children’s educational attainment is predicted by the DNA they didn’t inherit from their mother and father. The answer is, pretty well: for educational attainment, uninherited DNA predicts about half as well as the PGS actually inherited by the children. Therefore, some of the reasons your PGS predicts your educational attainment have nothing to do with anything going on in your genes: it is because of characteristics of your parents, presumably including being rich or educationally oriented. The bottom line is that for any kind of prediction of human behavior, separation of genetic from environmental prediction is very difficult and ultimately not possible.
A limitation of prediction from parents is that we would wind up making the same prediction for all of a couple’s children. We can predict that the children of tall parents will be tall, but we can’t predict which of several children will be taller. Because each new child is dealt a new random 50% of each parent’s DNA, we can use PGS to make differential predictions for a couple’s children. But when we do this, the PGS work less than half as well as they do when predicting across different families, especially for behavioral traits like educational attainment and intelligence.
All of the above 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.
The comparison between PGS and parent prediction is important because the best way to understand the practicality and ethics of using PGS in the real world is to imagine doing the same thing with parental prediction. The practicality is the easy part. It seems so magical to predict a child’s height or IQ from her DNA, but in practically any situation you can imagine it would be far easier, cheaper, and more effective to predict from parents’ heights or IQs. In the situations for which parental phenotypes might not be available—orphans or sperm banks—predicting from DNA might be interesting if it were robust (it isn’t now, except for height) and ethical (see below).
The most common speculation about practical uses of PGS involves differential prediction within families. 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. Within-family PGS aren’t effective enough to be very useful to parents, and to the extent they were effective, it is very difficult to know what else might be selected for when parents tried to select for children who were smart or attractive. 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. Try this: when a child enrolls in a public school, administer an IQ test 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 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.
Assigning children to classrooms based on GPS 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 PGS 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 IQ 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. In a world in which 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.