Genomics, Medicine, and Pseudoscience

I've moved to Substack. Come join me there.

noreply@blogger.com (Steven Salzberg) — Sun, 09 Feb 2025 21:48:00 +0000

Hello readers,

After blogging on this site since 2007, and at Forbes since 2010, I've moved all of my content over to Substack, at https://stevensalzberg.substack.com/. This includes every one of the 488 articles on this site, including over 300 that also appeared (simultaneously) at Forbes. You'll see all the articles in my Archive there, and from now on, any new articles I write will only appear on Substack.

If you're interested, you can subscribe (for free) to my Substack page, and you'll get a notice each time a new article appears. You won't get any other email or spam from the site. We've had a good run on Blogger, but it's time to move on.

I'll post links to new articles on Twitter (@stevensalzberg1), Facebook, and BlueSky (@stevensalzberg.bsky.social).

I hope you'll check out my articles on the new site!

–Steven Salzberg

RFK Jr. is not a serious person. Don't take him seriously.

noreply@blogger.com (Steven Salzberg) — Fri, 29 Nov 2024 18:52:00 +0000

Well, president-elect Trump has announced that he will nominate Robert F. Kennedy Jr. to be the Secretary of Health and Human Services (HHS), putting him in charge of most of the nation's public health and medical research.

I can't say strongly enough how unqualified RFK Jr. is for this job. He isn't qualified to come anywhere within a thousand miles of any medical or science-related issue, much less to be in charge of health policy for the whole country. Virtually everything RFK says about science is wrong–actually, it's worse than that, because he speaks with such absolutely certainty, despite being wrong, that he convinces people to take actions that end up hurting themselves. To a normal person, someone not accustomed to lying so boldly, these claims can be convincing.

Since Trump's announcement of the nomination, I've been seeing columns in major media outlets (I'm looking at you, New York Times and Washington Post) saying things like "hey, some of RFK's ideas aren't entirely wrong."

Just. Stop. Even a broken clock is right twice a day. Don't take RFK Jr., or his nomination, seriously.

I don't want to try to list all of RFK's mistaken views, which would require a book-length column, but here are a few. Just last year he said, on the Lix Fridman podcast, that "there’s no vaccine that is safe and effective," and that the polio vaccine did more harm than good. (Both of those statements are wildly wrong.) In 2005, he wrote a long essay for Rolling Stone and Salon which claimed that thimerosal-containing vaccines cause autism (they don't), and that the government knew about it and had been covering it up:

“The story of how government health agencies colluded with Big Pharma to hide the risks of thimerosal from the public is a chilling case study of institutional arrogance, power and greed.” [quote from RFK Jr.]

The article was full of dramatic claims like this one. The only problem was, all of them were false. Rolling Stone and Salon eventually retracted the article and deleted it from their websites.

In 2019, Kennedy visited the island nation of Samoa to spread his anti-vaccine message, sponsored in part by his anti-vaccine organization, Children's Health Defense. (The name is highly misleading.) Vaccination rates plummeted, and just a few months later a tragic measles outbreak began, causing 83 deaths and 1,867 hospitalizations. Kennedy published an article afterwards calling it a "mild measles outbreak," and in the same article claims (falsely) that vaccines themselves, rather than measles, caused the deaths.

RFK Jr. is someone who never admits he was wrong, even (or especially) when his mistakes cause the deaths of innocent children. Instead, his conspiracy-addled brain blames someone else.

And that's only a tiny sample of RFK's misinformation. He also loves raw milk, which I wrote about in 2014 and again in 2023. Raw milk sometimes contains nasty bacteria and viruses, but fortunately Louis Pasteur solved this problem in the 1860s, when he invented what we now call pasteurization. As I pointed out in my 2023 piece, bacteria just love raw milk. And you know what else is in raw milk but not pasteurized milk? Cow poop. Just don't tell this to RFK Jr.

By writing columns saying "RFK Jr. has some good ideas" (which I won't link to, since that's just feeding the beast), media organizations are falling into a trap: they're taking RFK seriously. I'd like to ask these journalists: if Trump nominated a first-grader instead, would you write similar stories? Maybe something like "hey, this nominee has some good ideas about nutrition!"

Don't do it. This nomination deserves ridicule and scorn, nothing more.

I've written multiple columns (both on this site and at Forbes, my former site) warning about RFK Jr. and his dangerous anti-vaccine craziness, starting with this 2014 piece where I called him out for his efforts to lobby Congress against vaccines. His primary obsession then–and he still has this obsession–was the mistaken notion that thimerosal, a harmless preservative that isn't even used in vaccines today, causes autism. This claim has been thoroughly debunked in multiple studies.

In 2017, I wrote about "Trump's lovefest with anti-vaxxer RFK Jr." – a lovefest that apparently still continues, seven years later. That column was about Trump's promise to put RFK in charge of a commission on vaccines. Fortunately, that vaccine commission never happened, but today we face a much more dangerous threat, if RFK Jr. is confirmed as Secretary of HHS.

I've also pointed out that Kennedy is one of the "Disinformation Dozen," a group of twelve people who, as reported by the Center for Countering Digital Hate, was responsible for 65% of all the anti-vaccine disinformation online. And earlier this year I asked how he could possibly be so arrogant as to think he's qualified to be President, given that his only claims to fame are his name, which he inherited, and his anti-vaccine notoriety.

My problem with RFK Jr. is not just that he is wrong about vaccines, although that is the most immediate threat to public health. But he's also an idealogue, someone who holds onto his mistaken ideas despite mountains of contradictory evidence, and someone who simply makes up things to "prove" his points.

And in that quote from him above, where he uses the phrase "institutional arrogance," highlights another danger: RFK Jr. is the one who is arrogant. He believes that he can substitute his own unsubstantiated beliefs for the knowledge of genuine experts, and why? Because he's a Kennedy, a man who has lived a life of great privilege, getting into Harvard as a "legacy" despite being expelled from prep school over his drug use, all the while pretending to be fighting against the system. He is too arrogant to listen to others, or to admit his mistakes.

So no, I cannot take this nomination seriously. Children will die if RFK Jr. is put in charge of HHS. There are tens of thousands of people who are far, far more qualified than Kennedy, and I hope the Senate will refuse to confirm him. I'm not optimistic, but I hope a few Senators will look at the man's record and treat him with the scorn he deserves.

Political pollsters are pretending they know what's happening. They don't.

noreply@blogger.com (Steven Salzberg) — Mon, 21 Oct 2024 11:30:00 +0000

This week I have to explain a little statistics, because the political news media have failed so badly.

If you’re like me, you’re probably exhausted with all the so-called news stories about the latest U.S. presidential polls. After each poll, which seems to be a daily occurrence as the election draws near, news outlets report the results on their front pages with breathless excitement. The race is changing! Harris is pulling ahead! Trump is catching up! Swing states are swingier than ever!

To cite just one example, CNN just reported that “Polls show Harris’ numbers in Pennsylvania have shifted over the past month.” This story included a video featuring polling expert Harry Enten, who stated “there has never been a race this close in the polling since 1972!” OMG! (The “OMG” is from me, not Enten.)

Okay, now let’s get to reality (with a small dose of statistics).

A poll is nothing more than a tiny sample of voters’ opinions. A poll might ask, say, 1000 people who they plan to vote for, and then report the results. If you ask a truly representative sample of people, a poll can give you a pretty good idea of how the candidates stand.

The problem is, this is really hard to do accurately, and it’s become much harder since everyone switched to cell phones. Decades ago, pollsters would phone people, and those people would answer the phone. Not any more: many people won’t answer a call from a number they don’t know, and people who do answer might have a bias towards one party or the other.

So pollsters compile some numbers and then adjust them (more on that below), and then report the results with a “margin of error,” which goes something like this. Suppose that a poll finds Trump leading in Nebraska by 18%, with a margin of error of 4%. That means that he might be leading by anywhere from 14% to 22% – and that’s just one pollster’s guess. He might be leading by 30%, or even losing, if you ask a different pollster.

But a 4% margin means that if you run the poll again and again, the results will swing back and forth, randomly, in a pretty wide range.

That’s exactly what’s happening in Pennsylvania. The voters are split, but every poll shows a slightly different result, because that’s what random sampling does. It’s not news!

So let me give you some actual data. Let’s look at Pennsylvania because it seems to be the closest Presidential race, according to the polls. Here are the actual margins of victory from the past 9 elections - real numbers, not polls:

2020: Biden (D) won by 1.2%
2016: Trump (R) by 0.7%
2012: Obama (D) by 5.4%
2008: Obama (D) by 10.3%
2004: GW Bush (R) by 2.5%
2000: Gore (D) by 4.2%
1996: Clinton (D) by 9.2%
1992: Clinton (D) by 9.1%
1988: GHW Bush (R) by 2.3%

Clearly, Pennsylvania has been closely divided in recent years. Suppose the race this year will eventually be won, by either candidate, by less than 2%, as happened in 2016 and 2020. Then what would we expect polls to show us? Given their typical 4% margin of error, we’d expect polls to show a race that flips back and forth from one poll to another, even if no one is changing their mind.

And that, I argue, is just what we’re seeing. The polls aren’t accurate enough, statistically speaking, to tell us anything other than “we don’t know who will win Pennsylvania.” But the media reports each one as if it’s a revelation.

Now back to those “adjustments” that pollsters make. In 2016 and 2020, the polls were off by quite a lot. In 2016, as everyone knows, pollsters were highly confident that Hillary Clinton would win, and they were wrong. They were almost as confident that Joe Biden would win in 2020, and they were right–but the race was closer than they predicted, and their estimates were once again off. In the 2022 midterm elections, though, they were wrong again, but in the opposite direction, and Democrats did better than forecast.

Did they over-correct after 2020, and is that why they predicted much bigger Republican gains in 2022? And have they fixed that now, so that polls this year will be spot on? Who knows?

The thing is, it’s very hard to figure out who will actually show up to vote, and who might answer the phone when a pollster calls, and whether they’re even telling the truth. So pollsters make statistical adjustments based on past experience, weighing some voters more than others. In general, they don’t tell the public precisely how they do this.

Are these adjustments accurate? Well, here’s the kicker: we won’t know until after the election! But one thing is almost certainly true: the changing polls are overstating the number of people who are changing their mind.

So I have a suggestion to the media: stop reporting every poll as if it’s news. Instead, tell us where the candidates stand on issues that really matter: support for Ukraine, support for Israel, health care policy, immigration, respect for the rule of law, stuff like that. I know, crazy stuff, right?

I realize that my plea will fall on deaf ears. It’s so much easier for The Washington Post, CNN, The New York Times, Fox News, and others to write about and talk about polls, and pretend these are actual news. It’s also lazy.

Don't tell me they found Tyrannosaurus rex meat again!

noreply@blogger.com (Steven Salzberg) — Tue, 24 Sep 2024 11:30:00 +0000

It seems that some scientists are still claiming they can find bits of dinosaur meat clinging to the fossilized bones of ancient dinosaurs. Don’t sharpen your dinner knives yet.

I thought this story, which first appeared in 2007, had died long ago, but it has just reappeared. Before I get to that, though, let me explain the original claims. Back in the late 2000’s, a couple of paleontologists managed to publish two articles in the journal Science claiming they had found traces of original dinosaur proteins in 68-million-year-old Tyrannosaurus rex fossils, and in an even older 80-million-year-old fossil from another dinosaur, a hadrosaur.

This would have been shocking news if it was true, but alas, it wasn’t (even if Jurassic Park fans wished otherwise). Organic material survives only a very short time after an animal dies, usually just a few years. Bones and teeth can last far longer, though. Scientists have extracted DNA from the bones of Neandertals and cave bears that are over 50,000 years old, which is pretty extraordinary.

But 68 million years is far, far longer than 50,000 years. Those fossils are one thousand times older than bones from Neandertals.

But maybe proteins can last longer than DNA? Well, perhaps, but not that long. The oldest known protein fragment, which was preserved in an exceptionally cold environment, is about 3 million years old. The T. rex fossils studied in the Science paper were found in a warm climate, where any proteins must have degraded far more quickly.

I wrote about this way back in 2008, expressing my disappointment with the journal and explaining some of the problems. Nature ran a news story about the controversy as well.

But wait, you’re probably thinking, that T. rex study was published in a prestigious journal, so how can it be wrong? Well, what seemed to happen was this: one of the editors at Science back in 2007 simply believed the study, or maybe he just wanted to believe it, so he ignored the reviewers. How do I know this? Well, when the first paper appeared, in 2007, two of the scientific reviewers, both experts in the field, contacted me to tell me that they had both recommended rejecting the paper, but the editor went ahead with publication anyway. (They contacted me because I had published papers in Science before, and they wanted my advice on what they could do.)

My guess is that the Science editor wanted to get headlines along the lines of “T. rex tasted like chicken.” (To explain: the tiny fragments of protein that the first paper found appeared to be similar to proteins from birds.) The editor got exactly that, in stories that ran in the Washington Post, the New York Times, Smithsonian Mazazine, and elsewhere back in 2007 and 2008.

After the original T. rex paper appeared, at least two letters were sent to Science explaining why it was wrong. Science published them as a “technical comments,” which weren’t nearly as prominent as the original paper.

That letters gave far more plausible explanations for the data from the paper: first, one letter explained that it was very likely that the tiny, tiny trace of chicken-like protein was simply contamination from a modern bird, maybe as benign as someone’s turkey sandwich. That letter also pointed out that the supposed T. rex protein appeared to be modern in origin, because it lacked the signs of aging that an ancient protein fragment should have. (The details are very technical; follow the link if you want to learn more.) The other letter pointed out errors in the statistical analysis, pointing out that the result could easily be a statistical artifact.

A later paper, published independently, re-analyzed the T. rex data itself and found that the sample appeared to contain “common laboratory contaminants, soil bacteria, and bird-like hemoglobin and collagen.” In other words, no ancient proteins at all.

I should note that the experiments used to detect the dinosaur proteins, using a technology called mass spectrometry, are notoriously plagued by contaminants. Even a tiny trace of a modern bird in the mass spectrometry lab (e.g., someone eating a turkey sandwich) is liable to produce a few protein fragments that show up in the experiment. Scientists at the time pointed out that the very same lab had done experiments using ostrich bones around the same time as the dinosaur fossils.

And if that wasn’t enough, yet another published paper argued that the “soft matter” found in some fossils by the paleontologists was likely to be a bacterial biofilm. Fossils, I should explain, are highly porous, and it’s easy to imagine how bacterial could infiltrate them over the millenia.

In fact, you don’t have to imagine that at all: another scientific paper from 2019, published in the journal eLife, described finding “an abundant microbial community” in dinosaur fossils.

All of this skepticism did not deter the original scientists. It was less than two years before they’d published a second report (also in Science, with the same editor) claiming that they’d found similar proteins in another, even older dinosaur fossil, an 80-million-year-old hadrosaur.

And yes, the paleontologists continued to insist that they found “soft matter” that must have originated from the original dinosaurs. Dinosaur meat! The highly regarded CBS news program 60 Minutes was so impressed that they aired an entire segment on this finding:

Alas, there’s just no way that fossils contain any soft matter from 62 million years ago. It was likely just bacteria. But we can’t let that get in the way of a good story.

So how long can animal proteins survive? In temperate regions (such as those where the T. rex fossils were found), most organic matter decays in a few decades. If the animal happens to die in a very cold place, and its body is encased in ice, it seems that some organic material can survive up to one million years, and possibly even longer. Cool! (Pun intended.)

But the T. rex fossils from the original Science study were found in temperate climates. They were not frozen in deep permafrost or ice, and the original organic material was almost certainly long gone many millions of years ago.

I thought this story was dead, but apparently I was wrong: a small cadre of scientists continues to believe that dinosaur fossils–which are made entirely of stone, not bones–contain detectable traces of the original dinosaur proteins. Unbeknownst to me (because I wasn’t following it), another paper appeared in 2017 that claimed to find signs of dinosaur proteins in a 195-million-year-old fossil, more than twice as old as the previously reported claims.

Astounding, if true. And just this month, a chemistry professor at MIT reported that he has the explanation for how these proteins survived so long. This finding, though, is more about how the chemical bonds in collagen–the protein that bones are built upon–are exceptionally stable. That’s interesting, but it doesn’t at all prove that collagen can last for nearly 200 million years.

So count me as deeply skeptical. The science of dinosaur “meat” has from the beginning been fraught with wishful thinking. Multiple papers appeared refuting the original claims, and none of those were effectively rebutted; it seems they were just ignored by scientists who preferred a more fanciful story. I wish it were otherwise, but fossilized bones from Tyrannosaurus rex and other dinosaurs lost any traces of the original organic material eons ago.

The Hayflick Limit: why humans can't live forever

noreply@blogger.com (Steven Salzberg) — Wed, 21 Aug 2024 11:30:00 +0000

A scientific legend, Leonard Hayflick, passed away at the beginning of August. Most non-scientists probably don’t recognize his name, but he made a remarkable discovery in the early 1960s. Back then, while doing experiments on human cells, he and a colleague, Paul Moorhead, discovered that our cells can only divide a limited number of times.

This discovery, although made at the level of an individual cell, has a dramatic implication: humans cannot live forever.

What Hayflick discovered was that after 40 to 60 rounds of splitting in two, cells simply won’t divide any more. At that point, they enter a phase called senescence, and they eventually die. The number of divisions that a cell can go through is now known as the “Hayflick limit.”

Prior to Hayflick’s experiments, many scientists believed that cells could divide forever. After all, every cell in our body comes from one original cell, and that cell came from our parents, and from their parents before that, and so on back through the ages. So it stood to reason that cells could continue to divide without limit. What’s more, in the early 20th century, Alexis Carrel (a Nobel laureate) claimed to have grown cells in his labs that continued to divide for decades, with no sign of decline.

(Aside: Jan Witkowski explained in an article back in 1980 that it was likely that Carrel’s seemingly immortal cells had been quietly replenished, without Carrel’s knowledge, by members of his lab who were eager to keep the boss happy.)

Back to the Hayflick limit: because all of our organs are destined to wear out, our bodies will simply die unless we can intervene and restore cells to their youthful state. That would require technology that has not yet been invented. Hayflick himself estimated that the limit of the human lifespan is 125 years.

Hayflick’s limit raised an intriguing puzzle: how does a tiny, microscopic cell keep track of how many times it has divided? In other words, how can a cell know how old it is? Don’t all of our cells have identical DNA? Hayflick himself didn’t have a solution for this, but a few decades later, others figured it out.

The answer to this cellular “clock” puzzle resides, it turns out, in our DNA. More specifically, it depends on the DNA sequences at the very ends of our chromosomes, which are called telomeres.

Telomeres don’t really do anything, and they appear very simple: they consist of a long stretch of six DNA bases, TTAGGG, repeated hundreds of times, end-to-end. All our chromosomes end with telomeres, on both ends.

So here’s the thing: when a cell divides, it has to copy all of its chromosomes. The mechanism for copying isn’t quite perfect, and it can’t go all the way to the end of the chromosome, so the new copy is a little bit shorter. The telomere gets shorter! Fortunately, we have a special enzyme, called telomerase, that fixes this problem by adding a few extra copies of TTAGGG to the end of each chromosome, restoring the proper length. Problem solved, right?

Well, no. Telomerase doesn’t work perfectly, and chromosomes sometimes do get a bit shorter each time they divide. When the chromosomes get too short, the cell can’t divide any more, and it eventually dies.

And yes, scientists have explored the question of whether telomere length might be the key to longevity. No one has figured out a way to keep telomeres long, and it’s not clear that would help anyway. On the contrary, as my Hopkins colleague Mary Armanios reported in a study last year, long telomeres might help individual cells stick around, but they don’t seem to prevent aging.

Does the Hayflick limit mean we really can’t live forever? Well, not necessarily. Some types of stem cells can produce “fresh” cells that could, in theory, replenish our old cells. Perhaps some day we’ll have the technology to replace our organs with new ones, possibly grown in a lab, that will have the youth and energy of a 20-year-old. But without replacing our parts, we are destined to wear out, even if we manage to avoid cancer, infections, and the many other perils that humans face.

Leonard Hayflick made it to 96, a ripe old age by today’s standards. It would have been fitting if he’d reached 125, the limit that he estimated, but no human has ever done that. Yet.

Can you use the gut microbiome to diagnose autism? I think not

noreply@blogger.com (Steven Salzberg) — Wed, 17 Jul 2024 11:30:00 +0000

Last week, the New York Times published a story claiming that we might be able to use the gut microbiome to diagnose autism. The Times story was based on a just-published scientific paper that claimed the same thing.

This report set off all my skeptical alarm bells. My initial reaction was “oh no, more bad science around autism.” For one thing, as most scientists studying autism are aware, the modern anti-vaccine movement started with a scientific paper, back in 1998, that claimed, falsely, that childhood vaccines caused autism. That paper in The Lancet was later shown to be fraudulent and was eventually retracted, but not before a huge amount of damage was done. Its lead author, Andrew Wakefield, went on to become a hero to the anti-vaccine movement, and he continues to promote anti-vaccine misinformation to this day.

The new paper (from the journal Nature Microbiology) is not making outrageous claims like that, nor was the New York Times. However, anyone claiming autism is caused by microbes in the gut should know that the notorious Lancet study was based on a hypothesis about a “leaky gut,” a hypothesis that was discredited long ago. (I don’t want to give it any credibility, but that hypothesis held that virus particles in some vaccines somehow “leaked” from the gut and made their way to the brain. It was nonsense at the time and still is.) That’s one reason why the suggestion that microbes in the gut might cause autism (or even be used to diagnose it) raises so many alarm bells.

I’ve now looked at the study, and frankly I don’t believe a word of it. Let me be clear, though: I’m not trying to prove scientifically that the study is wrong, which would require many months of effort and a much more detail than I can put into a column anyway. Fortunately, though, there’s an earlier study that did that job for me, which I’ll get to below.

However, the science behind this study is closely related to my own work, so I feel pretty comfortable offering my opinion. So what did the authors do?

Well, as the new study explains, they collected poop (”faecal samples”) from 1,627 children, some of whom had been diagnosed with autism and some who hadn’t, and they sequenced DNA from the poop. Then they looked for bacteria, viruses, and other microbes in the DNA sequence data.

That’s right: the “gut microbiome,” is really just a polite term for bacteria that live in the intestines and the colon, some of which come out in poop. Of course, some bacteria in poop might come from the food that a person ate, but mostly these are so-called gut bacteria.

I’ve been involved in many studies like this myself, so I’ve seen that these experiments yield hundreds of different species from every sample. The data sets are very complex, and a widespread problem in the field is that these data are often misinterpreted. In the Nature Microbiology paper, the authors took these very complex data sets and fed them to a machine learning program, and voila! The AI program was able to do a pretty good job (far from perfect, I should note) identifying the autistic children, based on the melange of microbes in their poop.

Right. I don’t believe any of this, as I wrote above. Why not? Well, first of all, machine learning programs are really good at telling apart two sets of subjects (such as children with and without autism) if you give them enough data. It sometimes turns out that the learning programs are keying in on irrelevant features that the scientists didn’t intend.

For example, this 2021 paper looked at over 400 studies that used machine learning to predict Covid-19, all of which had claimed some success, and found that all of the studies were essentially useless “due to methodological flaws and/or underlying biases.” Of course, the gut microbiome study wasn’t one of those, and some machine learning experiments do work, but we should be very skeptical.

Another reason for skepticism is that the new paper doesn’t even try to tell us what the machine learning models actually learned–it just treats the programs as a “black box” that we should trust.

Perhaps the biggest flaw in the study of autism and children’s gut microbiota is this: children with autism tend to be finicky eaters, and their parents try all sorts of diets in the hope that they can at least alleviate the symptoms of autism with food. There are countless websites–many of them scams, unfortunately–claiming that special diets can help these children. Why is this important? Because a special diet will alter your gut microbiome, sometimes quite significantly.

Thus even if the machine learning models in the new study are correct, the causality almost certainly goes the other way: children with autism might have a different microbiome because they’re eating different foods. Thus it’s autism that indirectly affects the microbiome. Unfortunately, both the New York Times and the scientific paper suggested the opposite.

Now on to that earlier scientific paper I mentioned above. It turns out 3 years ago, a group of researchers in Australia published a major study in the journal Cell that addressed precisely the problem I just pointed out. In that study, the scientists collected and sequenced poop from 247 children both with and without autism. They found “negligible direct associations between ASD [autism spectrum disorder] and the gut microbiome.“

On the contrary, the authors warned: “microbiome differences in ASD may reflect dietary preferences ... and we caution against claims that the microbiome has a driving role in ASD.”

In other words, three years ago a study in a major scientific journal found that there was no connection between autism and the contents of the gut microbiome. They went on to warn that if you see differences in the gut microbiome in autistic kids, those are caused by their diet, so don’t go claiming that the microbiome causes autism. The authors of the newer study, and the reporters at the New York Times, apparently decided otherwise.

So no, the gut microbiome can’t be used to diagnose autism.

A randomized controlled trial of parachutes had a surprising outcome. Anti-vaxxers, take note.

noreply@blogger.com (Steven Salzberg) — Mon, 01 Jul 2024 11:00:00 +0000

One of my themes in this column over the years has been that you need to be skeptical of many of the claims out there about science and medicine. A healthy dose of skepticism can be a good thing, especially when someone is telling you something that seems surprising.

On the other hand, anti-science forces often pretend that they too are just being skeptical, or “just asking questions,” when what they’re doing is actually science denialism. Denialism is what someone is doing when the science is basically settled, but they refuse to accept it.

Let’s consider perhaps the clearest example of denialism, and the one that causes the most harm to public health: vaccine denialism. The anti-vaccine movement, which has grown alarmingly fast during the Covid-19 pandemic, insists that vaccines don’t save lives, and even more they insist that vaccines cause neurological damage. The latter claim is a favorite of Robert F. Kennedy Jr., as he’s proclaimed in multiple books and articles, and of his VP running mate Nicole Shanahan as well.

The claim that vaccines cause autism was first promoted in a bogus 1998 article in The Lancet by Andrew Wakefield. That article was later shown to be fraudulent, and the journal retracted it, but not before it spawned the modern anti-vaccine movement and made Wakefield one of their heroes. I’ve written many columns on this topic, and others have written far more, but the movement persists.

Scientists and doctors have pointed out, over and over again, that vaccines have saved millions of lives, and are one of the greatest medical advances in the history of civilization. The rapid development of the Covid-19 vaccine was a triumph, and it undoubtedly saved tens of millions more lives.

In defending their denialism, anti-vaxxers frequently ask this question: “where are the randomized controlled trials for vaccines?” They imply that scientists haven’t run such trials because they (the scientists) know that vaccines don’t really work.

That’s nonsense, of course. Scientists have conducted hundreds of studies, involving millions of people, showing how vaccines prevent disease and death.

But we don’t have any randomized controlled trials for childhood vaccines, and we never will, for an obvious reason: it would be deeply unethical. Let me explain.

A randomized control trial (an RCT) works like this: first, you identify a large group of people whom you want to treat, say by giving them vaccines. Then you divide them at random into two groups: the treatment group, who get the vaccine, and the control group, who get nothing. To prevent bias, you might also “blind” the subjects and experimenters so that no one knows who’s getting treated. For example, you could use shots filled with saline solution for the control group, so they think they’re getting a vaccine.

Once you’ve administered the treatment, you follow everyone for some period of time and see who does better. If the treatment group does better, then we say that the treatment worked.

Obviously, we cannot run an RCT for childhood vaccines, because withholding vaccines from children could grievously harm or even kill them. Instead, we can use data collected over time from millions of children, some of them vaccinated and some not, and measure vaccines’ effects from that. It’s not perfect, but these observational data show overwhelming evidence that vaccines for diseases including measles, mumps, rubella, polio, and smallpox are incredibly effective.

Yet anti-vaccine activists continue to call for RCTs, and they pretend that scientists who point out what I just wrote are not to be trusted.

Now to those parachutes in the title of this piece. We know that parachutes work, right? And yet where are the randomized controlled trials? Maybe we shouldn’t use parachutes until some scientists conduct that study? Hmm.

Well, if you’re thinking of skydiving and wondering about this question, you’re in luck! Because a few years ago, a group of scientists at Harvard, UCLA, and the University of Michigan ran an RCT on parachutes! And they published it, too, in the highly regarded British Medical Journal, now called BMJ.

I’m sure you’re curious about how they did this study, and how it turned out. Well, I’m going to tell you.

It was a small study: they approached 92 aircraft passengers and enrolled just 23 people. They randomized them into two groups, with 12 people wearing parachutes and 11 jumping with just an empty backpack.

What happened? Amazingly, there was no difference! Also amazingly, no one died! How could that be?

Well, reading the details of this (ahem) well-executed study, one learns that “randomized participants ... could have been at lower risk of death or major trauma because they jumped from an average altitude of 0.6 m on aircraft moving at an average of 0 km/h.”

In other words, participants did jump from a plane, but they were jumping from less than a meter off the ground and the plane wasn’t moving. A figure from the study illustrates the experiment:

Representative study participant jumping from aircraft with an empty backpack. This individual did ... [+]

THIS IS AN OPEN ACCESS ARTICLE DISTRIBUTED IN ACCORDANCE WITH THE CREATIVE COMMONS ATTRIBUTION NON COMMERCIAL (CC BY-NC 4.0) LICENSE, WHICH PERMITS OTHERS TO DISTRIBUTE, REMIX, ADAPT, BUILD UPON THIS WORK NON-COMMERCIALLY, AND LICENSE THEIR DERIVATIVE WORKS ON DIFFERENT TERMS, PROVIDED THE ORIGINAL WORK IS PROPERLY CITED AND THE USE IS NON-COMMERCIAL. SEE: HTTP://CREATIVECOMMONS.ORG/LICENSES/BY-NC/4.0/.

So as you see, this particular RCT of parachute use didn’t prove anything. Even so, the authors note, tongue in cheek, that “Beliefs grounded in biological plausibility and expert opinion have been proven wrong by subsequent rigorous randomized evaluations. The PARACHUTE trial represents one more such historic moment.”

In case you’re wondering how on earth the BMJ would publish a study like this, I can explain that the date of publication was Christmas 2018. The BMJ has a long tradition of publishing satirical but seemingly serious articles on Christmas, and this was a particularly good one.

On the other hand, though, my larger (and serious) point is that the public shouldn’t lose trust in science. Even when science gets things wrong–and it does–it’s still the best toolkit we have for figuring out whether or not something works, or is true. The recently popular cultural trope that truth is malleable, and that each person can choose their own “facts,” is dangerous. When it comes to scientific facts, that’s just wrong.

Parachutes work, and not using them would be exceedingly risky. Vaccines aren’t quite as guaranteed as parachutes, but they come pretty close.

RFK Jr. is a famous anti-vaxxer. How does this make him qualified for President?

noreply@blogger.com (Steven Salzberg) — Mon, 27 May 2024 11:30:00 +0000

I’ve written about the anti-vaccine movement and its many proponents more times than I can count. So why write about it again? Because one of them is running for President of the United States.

Robert Kennedy Jr. is famous for two things: first, he’s famous because he’s the son of a former Senator and the nephew of a former president. His father, Robert Kennedy Sr., served as Attorney General under President John Kennedy and then as a US Senator. Tragically, both JFK and RFK were assassinated in the 1960s, and RFK might very well have been elected president in 1968, as he was leading the Democratic field when he was killed.

Having a politician as one’s father does not qualify anyone for office, although many children of politicians use their famous name to win elections. That’s clearly what RFK Jr. is now hoping for.

But what RFK Jr. is really famous for now, and for the past 20 years, is something entirely different. As I wrote nearly a decade ago, Kennedy is obsessed with the notion that vaccines cause autism. He’s particularly obsessed with the thoroughly discredited idea that thimerosal, a preservative used in some vaccines, causes autism.

His efforts to convince people of the harms of vaccines landed Kennedy in the number two position on the infamous list of “The Disinformation Dozen,” This list, created by the Center for Countering Digital Hate, contains “the twelve anti-vaxxers who are responsible for almost two-thirds of anti‑vaccine content circulating on social media platforms.” Yes, this is what RFK Jr. has been focusing his energy on, at least until he decided to run for President.

Ten years ago, Kennedy published an entire book on this topic, called “Thimerosal: Let the Science Speak,” and he promoted it both in the press and in the halls of Congress. He had personal meetings with then-U.S. Senator Barbara Mikulski and Sen. Bernie Sanders to try to convince them to take action based on his claims. Why is it that a scientifically unqualified anti-vaccine advocate got a private audience with two U.S. Senators? Because he’s a Kennedy.

RFK Jr. gives hundreds of speeches a year, and up until the early 2000s, he spoke mostly on environmental issues. I heard one or two of his interviews during that era, and he was quite convincing. His usual argument was that large corporations were engaged in some kind of conspiracy to damage the environment so that they could increase their profits. That made sense to me!

But then he found the thimerosal issue and went completely off the rails. One example was a Salon.com and Rolling Stone article (jointly published in both magazines) that he wrote in 2005, which claimed not only that thimerosal-containing vaccines cause autism, but that “the government” knew about it and had been covering it up. Kennedy wrote that

“The story of how government health agencies colluded with Big Pharma to hide the risks of thimerosal from the public is a chilling case study of institutional arrogance, power and greed.” [quote from RFK Jr.]

Alarming-sounding stuff. The article was full of dramatic claims like this one. The only problem was, all of them were false.

To explain, let’s review what thimerosal is and why it has probably saved many lives. There was never a conspiracy because there was nothing to hide.

Thimerosal is a preservative that was used in many vaccines for decades. Why? Well, as I’ve explained before, early vaccines (back in the pre-WWII era) were administered from multi-dose bottles, in which bacteria would sometimes grow. In one particularly disastrous incident in 1928, 12 children in Australia died from staph infections after receiving the diptheria vaccine from the same multi-dose bottle. After the introduction of thimerosal, bacterial infections caused by vaccination virtually disappeared.

Why the panic from RFK Jr. and others about thimerosal? Well, it’s a mercury-based preservative, and RFK assumed (wrongly) that the tiny amounts of ethylmercury in vaccines caused autism or other neurological problems. One problem with this idea is that ethylmercury is very different from environmental mercury, which is called methylmercury and which can indeed be toxic. Ethylmercury is cleared from the body far more quickly–and the minuscule amounts in vaccines have never been shown to cause any harm.

But many anti-vaxxers, especially RFK Jr., have continued to spread alarming stories about vaccines (particularly through Children’s Health Defense, an organization founded by Kennedy), and a disturbing number of parents have withheld vaccines from their children because they didn’t know who to believe.

In the late 2000's, in an effort to address the concerns of anti-vaccine alarmists, a special U.S. vaccine court conducted three lengthy hearings in which the anti-vax advocates were asked to present their best cases. One of the cases focused specifically on the question: does thimerosal in vaccines cause autism? In that case, the judge concluded:

“The numerous medical studies concerning the issue of whether thimerosal causes autism, performed by medical scientists worldwide, have come down strongly against the petitioners’ contentions. Considering all of the evidence, I find that the petitioners have failed to demonstrate that thimerosal-containing vaccines can contribute to the causation of autism.”

As a lawyer, Kennedy should have been able to understand this. The science agrees with the court: in study after study, scientists found no link between thimerosal and autism or any other kind of neurological disorder. That should have been the end of the matter, but of course it wasn’t.

Furthermore, as RFK Jr knows, thimerosal was removed from childhood vaccines in the U.S. over 20 years ago, and the rate of autism diagnosis continued to rise after that. This fact alone contradicts his major claim: if thimerosal was fueling an autism epidemic, then cases should have declined after vaccines stopped including it.

What was shocking to me, the first time I heard Kennedy talk about thimerosal in vaccines, was how absolutely certain he was. He came across as a man who remained utterly convinced that vaccines cause autism, despite the mountain of evidence against him.

After RFK Jr.'s Salon article appeared, scientists responded quickly and convincingly, pointing out its numerous flaws and distortions. Salon tried to fix the problem, issuing five corrections before throwing up their hands and removing the article entirely from their website. Rolling Stone also took down the article. Salon’s editor-in-chief wrote an apology, saying

“I regret we didn’t move on this more quickly, as evidence continued to emerge debunking the vaccines and autism link. But continued revelations of the flaws and even fraud tainting the science behind the connection make taking down the story the right thing to do .”

Kennedy has steadfastly refused to admit any errors, ever. When I wrote about him in the past, his website still displayed the original Salon article, without even the small corrections that Salon.com had made. (That website, robertfkennedyjr.com, no longer exists now that he’s running for President.)

Kennedy also published another anti-vaccine book just last year, titled “Vax-Unvax: Let the Science Speak.” (In case you didn’t notice, Kennedy has zero credentials to write a book about vaccine science, but that has never slowed him down.) And in case there’s any doubt about his leanings, early in 2024 Kennedy hired Del Bigtree, a “top anti-vaccine activist,” as his campaign communications director.

By ignoring the scientific evidence that shows that thimerosal and vaccines have no link to autism, Robert Kennedy placed himself firmly in the camp of conspiracy theorists and cranks. He’s also demonstrated breathtaking arrogance. He believes that despite his lack of scientific training, he knows the truth that every scientist who’s studied this issue has missed.

Even worse, Kennedy has used his fame to spread anti-vaccine misinformation, which grew far worse during COVID. Though I doubt he will listen to me (he’s ignored everyone else), Kennedy needs to take a hard look at the harm he’s causing to defenseless children, the elderly, and cancer patients, and anyone else with a weak or compromised immune system.

When I heard Kennedy talk about environmental topics, where I agreed with him, I was impressed by his passion and his seeming command of the issues. But having heard him speak about thimerosal and vaccines, I now realize that he’s a dangerous ideologue, willing to distort the truth so thoroughly that he can’t be trusted on any topic, even ones where I agree with him. His campaign for President, although certainly doomed to fail, is likely to increase the spread of his harmful anti-vaccine tropes.

Finally, I couldn’t help but notice that the bio on RFK Jr’s campaign’s website makes no mention of his anti-vaccine activism, even though it’s been his top priority for the past 20 years, and it’s the main reason he has the visibility he has today. It does mention “his nonprofit, Children’s Health Defense” but doesn’t say that the primary work of that nonprofit is to spread scary misinformation about vaccines. I’m just guessing here, but it appears that some of his campaign advisers have decided that being a famous anti-vaxxer might not be the best qualification for President.

Update, May 28, 2024: Since this story was published on May 27, RFK Jr. has been contacted for comment.

Hormone replacement therapy is beneficial and safe, it turns out

noreply@blogger.com (Steven Salzberg) — Mon, 06 May 2024 11:30:00 +0000

A new study that just appeared in the Journal of the American Medical Association has some good news for women who take estrogen replacement therapy.

To jump to the punch line: estrogen therapy helps to alleviate hot flashes and other symptoms of menopause, and it carries little risk. And even better news: the study also reported that estrogen-only therapy might actually decrease the risk of breast cancer.

Why does this matter? Because about 20 years ago, millions of women stopped taking estrogen, even if it was helping them, because of a report that hormone replacement therapy might increase (not decrease) the risk of breast cancer.

These latest results come from the long-running Women’s Health Initiative, a National Institutes of Health-funded study of more than 160,000 women who were given various hormone therapies and then followed for up to 20 years. The WHI was responsible, somewhat notoriously, for the cancer scare in 2002, when the NIH reported–without consulting many of the scientists leading the study–that hormone replacement therapy increased the risk of breast cancer. This was wrong, as I explained in this column a few years ago, but as a result, many women stopped taking estrogen, and physicians stopped recommending it.

The confusion stemmed from the use of two different types of hormone therapy: (1) estrogen alone, or (2) estrogen plus progestin. The increased risk occurred solely in the combination therapy group (estrogen plus progestin), and not in the estrogen-only group. Despite this crucial difference, the WHI halted the studies of both treatments in 2002, and their press releases didn’t fully explain the difference.

And yet, as Dr. Robert Langer explained in 2017, the WHI trial of estrogen alone (without progestin) continued to track its subjects, and in 2004 that study reported that estrogen-only therapy led to a reduction in breast cancer, and a reduction in coronary heart disease as well.

(Aside: the Women’s Health Initiative website boasts that their 2002 report contains “revolutionary findings about combined hormone therapy,” emphasizing only the harm. I couldn’t find any comparable highlight describing the benefits of estrogen-only therapy.)

The new study, which appeared in JAMA on May 1, confirms several earlier studies that have reported a cancer benefit for estrogen therapy. In addition to its beneficial effects on menopause symptoms (which are widely acknowledged), the new study found that, after an average of 10.7 years, “rates of breast cancer were significantly lower in the CEE group [estrogen only] compared with the placebo group (HR, 0.77).” That HR value means that women who took estrogen had a 23% reduction in their risk of breast cancer.

Further supporting these findings is a 2022 study from NIH, available as a preprint in medRxiv here, which found that women taking estrogen only, compared to no hormones at all, had “significant risk reductions for all study cancers, breast, lung, endometrial, colorectal and ovarian” as well as a 20% reduction in mortality. The 2022 NIH study also found, similarly to the 2002 findings from WHI, that when estrogen was combined with progestin, the risk of breast cancer increased.

And there’s more. This 2012 study out of Denmark studied women who received estrogen-only therapy for 10 years starting in the early 1990s. They then followed these women for another 16 years, and found that women taking estrogen had a lower risk of heart attack, heart failure, or death–and no increased risk of cancer.

(As another aside: the new JAMA paper also reported results on a completely separate study of calcium plus vitamin D. They found that taking supplemental calcium+D didn’t provide any benefit in reducing the risk of bone fractures, confirming what I wrote in a recent column, here.)

So what’s the bottom line? We now have a raft of evidence showing that for post-menopausal women, estrogen therapy can offer significant benefits not only in treating hot flashes and other “bothersome menopausal symptoms” (to quote JAMA), but also in reducing the risk of some types of cancer. In contrast, hormone replacement therapies that use progestin, which is commonly used in birth control pills, might increase the risk of cancer and should be avoided.

As with most medical treatments, the true picture is complicated, but millions of women today might benefit from estrogen therapy. If you think you might be one of them, talk to your physician.

Calcium and Vitamin D Supplements Still Don't Work, New Study Says

noreply@blogger.com (Steven Salzberg) — Mon, 18 Mar 2024 11:30:00 +0000

I think I’ll have to add calcium to my list of the Top Six Supplements You Should Not Take. Here’s why.

A year and a half ago, I reported on a very large study of 26,000 men and women that asked if vitamin D helps to prevent bone fractures, as many people (including some doctors) believe.

Well, it doesn’t. That study found that people who took vitamin D had exactly the same risk of bone fractures as those who didn’t. It didn’t matter how much vitamin D they took, nor did it help if they also took supplemental calcium: either way, vitamin D had no effect.

(Aside: everyone needs vitamin D, but most people get all they need from a normal diet. Alternatively, just 10 minutes of sunlight gives you about 4 times your daily recommended vitamin D requirement.)

Well, now there’s a huge new study, just out in the Annals of Internal Medicine, that followed over 36,000 older women, looking at the effects of a combination of vitamin D and calcium over a 22-year period. (That’s a really long time for a study, and kudos to the authors for their determination and effort.) The scientists leading the study looked not only at the effects of supplements on hip fractures, but also whether supplements changed the risk of dying from cancer or heart disease.

The results? Well, the study found no reduction in the risk of hip fractures, which isn’t surprising given that earlier studies found the same thing. But because it was such a lengthy study, following people for more than 20 years, they could ask something else: did vitamin D and calcium have any effect on mortality? Or to put it more bluntly, did the supplements prevent death?

Well, no. But the report was a bit more nuanced than that. It turns out that deaths from cancer went down a tiny bit, and deaths from heart disease went up a tiny bit.

First, though, let me explain the overall experiment. Approximately half the women in the study, just over 18,000, were assigned to take both vitamin D and calcium every day. They were given pills with 1000 mg of calcium carbonate (400 mg of elemental calcium) and 400 IU of vitamin D3 daily. The other half of the participants took placebo pills, but neither group knew whether their pills were placebos or not.

Over the course of 22 years, 1817 women taking supplements died of cancer, compared to 1943 women in the placebo group who died of cancer. That sounds kind of good, right? The study authors report that this result – 126 fewer deaths – was statistically significant (just barely), but there are good reasons to be skeptical of this “significance” claim.

On the other hand, 2621 women taking supplements died of heart disease, versus 2420 women in the placebo group. So there were 201 more deaths from heart disease among women taking vitamin D and calcium: not so good.

Combining both causes of death, we see that in the women taking supplements, there were 75 more deaths from either cancer or heart disease. The study also reported numbers for all causes of death, and there were still very slightly more deaths in the supplement group. (The annual death rate increased from 2.14% to 2.15% for those taking supplements, a non-significant change.)

So on the whole, taking supplements didn’t seem to provide any benefit at all, and it certainly didn’t reduce the risk of death.

Why would supplemental vitamin D and calcium increase the rate of heart disease, or decrease the rate of cancer? Well, first I should emphasize that it’s entirely possible that these supplements have no effect at all, and the difference in death rates must just be random variation. There have been multiple studies speculating on how vitamin D might help to prevent cancer, but the effect, if any, is very small. And as for heart disease, maybe, as the authors of the new study speculate, long-term calcium supplements create calcifications in coronary arteries, which would be a bad thing. For now, this is merely a hypothesis.

So here is my new list of the top 7 (no longer 6) supplements that you should not take:

Vitamin C
Vitamin A and beta carotene
Vitamin E
Vitamin B6
Multi-vitamins
Vitamin D
Calcium

You can read more about the first five, some of which can be downright bad for you, in The Top Five Vitamins You Should Not Take.

What’s left? Well, if you don’t have a deficiency, there’s no reason to take any supplemental vitamins at all. If you want to spend a little more money at the grocery, buy some fresh fruit instead. You’ll be healthier for it.

As a final caveat, I should point out that although routine supplementation is worthless and megadoses of vitamins can be harmful, if you think you have a vitamin deficiency, consult with your doctor. Serious vitamin deficiencies might be the result of other health problems that your doctor can help you address, and treatments for specific conditions or diseases may include vitamins.

Why did humans lose our tails? Blame a "jumping gene"

noreply@blogger.com (Steven Salzberg) — Mon, 04 Mar 2024 12:30:00 +0000

Most animals have tails, including almost all mammals. For some reason, we humans don’t. This difference has been the source of much speculation among scientists over the years, and many arguments have been made about why we don’t tails.

One line of reasoning goes like this: tails are very useful for animals that live in trees, but once our ancestors came down from the trees and started living on the open plain, they didn’t need those tails any more. But why lose them? Lots of animals don’t live in trees, and they still have tails.

Even among the primates, most species have tails, but chimpanzees, gorillas, orangutans, and bonobos–the great apes–don’t. In fact, one way to tell great apes apart from other apes is by the presence of a tail. We humans are simply great apes without so much hair. Or, as the English scientist Desmond Morris called us in his famous book, humans are “The Naked Ape.”

So why am I writing about this now? Well, in a newly published article in Nature, a group of scientists from NYU, led by Itai Yanai and Jef Boeke, seem to have figured out what made us lose our tails. It’s all due to a piece of DNA that copies itself and jumps around our genome.

It’s a bit geeky, but stay with me and I’ll try to explain.

It seems that sometime around the divergence of the great apes from other primates, about 15-20 million years ago, a “jumping gene” popped into a gene called TBXT in our ancestor. (The B in TBXT stands for brachyury, which means “short tail.”)

The jumping gene here is just a piece of DNA a few hundred letters long*, not really a gene all by itself. But once that jumping gene got into TBXT, it was in just the right position to make the cells in our ancestor produce a shorter version of TBXT. The shortened gene was missing one of its pieces, but it still worked – well, sort of. Our ancestors managed just fine, but they lost their tails.

(Aside: the piece that’s chopped out is called exon 6, for those who really want to know.)

Given that this happened over 15 million years ago, how did the scientists prove their hypothesis? Well, other mammals have the same gene, but they make a longer version. So the authors of the new paper created a version of the TBXT gene in mice that included the jumping gene–and, as predicted, some of the mice lost their tails entirely.

Admittedly, this doesn’t exactly prove that one jumping gene caused us to lose our tails. Without a time machine to take us back 15 million years (with a DNA sequencing machine in tow), we can’t truly prove what happened eons ago. But it’s a compelling story, because we know that our genomes, and those of other great apes, have this unique jumping gene that other mammals lack.

So now we know how we lost our tails. We still don’t know exactly why, though. Some scientists speculate that being tail-less might have helped us to walk upright, or that it might have been better to lose the tails once our ancestors stopped living in trees.

On the other hand, guinea pigs don’t have tails either, and they don’t walk on two legs. And koalas don’t have tails, even though they live in trees. Some of these questions may just have to remain a mystery.

*Technically, the jumping genes in this story are called Alu elements, and they occur all over our genome. Famed geneticist Haig Kazazian, a former Hopkins colleague who passed away just two years ago, explained in a 2004 paper that Alus are a form of “nonautonomous retrotransposon.”

Sadly, the Washington Post once again falls for acupuncture pseudoscience

noreply@blogger.com (Steven Salzberg) — Mon, 29 Jan 2024 12:30:00 +0000

It’s like playing whac-a-mole. No matter how many times I write a column showing that some wildly implausible practice is nonsense, new articles pop up claiming “Hey, look at this! It really works!”

So I’m going to try to whack another mole, because people can be harmed by bad information, especially when it comes in the form of medical advice.

Recently the Washington Post ran a column under the headline, “Does acupuncture work for chronic pain? Here’s what the science says.” (The column first appeared back in July, but the Post’s website promoted it again just last week.)

Before giving you the Post’s answer, let me give you the correct answer. No! Not “maybe” or “sometimes” or “we’re not sure.” Acupuncture doesn’t treat anything, and it carries a real risk of harm, particularly from infections. I’ll get to that below.

I’ve written on this topic many times before (in 2013, in 2012, in 2010, and more), and I’ve even called out the Washington Post for their pro-acupuncture pseudoscience (see this column, which I wrote in 2016). The physicians over at Science-Based Medicine have debunked more acupuncture studies than I can count; they’ve even created a special webpage (which I highly recommend) dedicated to explaining the bogus claims that acupuncture proponents make.

Acupuncture, in case you don’t know this, is a practice where people who call themselves acupuncturists (they are not doctors) stick needles into your body to “treat” various conditions. The claim is that these needles can manipulate your vital life force, or “qi”, which runs along supposed acupuncture lines throughout your body.

That’s just wrong. Modern biology has taught us a whole lot about human physiology, and there just aren’t any lines with mystical forces flowing through them. There are nerve fibers, true, but acupuncturists don’t use those. (And if their needles were piercing nerves, it would hurt like heck.)

Acupuncture and qi are part of Traditional Chinese Medicine, or TCM, a collection of largely ineffective and sometimes very harmful folk beliefs. TCM’s popularity started to grow in the mid-20th century when Chairman Mao launched a propaganda campaign pushing it. Mao himself never used TCM, but his government couldn’t afford real medicine, so they convinced people that inexpensive folk medicine was just as good. It wasn’t.

But I digress.

Acupuncturists claim to treat many conditions, but they especially like to claim that they can treat chronic pain, for at least a couple of reasons. First, pain is inherently subjective, so the only way to measure if a treatment is working is to ask the patient. This makes it hard to study objectively. And second, pain symptoms usually wax and wane, even without any treatment. Patients usually want treatment when the pain is at its worst, which means once the pain subsides, the patients will give credit to whatever they were doing at that time. So pain is fertile ground for people selling quack treatments.

Now let’s get to that column in the Washington Post. The column promises to tell you “what the science says,” and it quickly gets to the point, saying yes, it does! First it puts forward the logically flawed (and non-scientific) claim that hey, the U.S. Medicare system now covers acupuncture for back pain, so it must be effective.

Ugh, where do I start? Well, like it or not, Medicare approval of a treatment doesn’t mean the treatment works. (And conversely, some treatments that work are approved for coverage by Medicare.) So that’s just a logical fallacy. I wish it were true that Medicare was purely science-driven, but both the federal and state government have been lobbied for years by acupuncturists (and other purveyors of dubious therapies) to provide public tax dollars to cover their practices. For a deeper dive into these lobbying efforts, I recommend the lengthy takedown by Jann Bellamy explaining that acupuncture is “legalized quackery.”

The Post article then goes on to discuss the science, for which it relies primarily on a single study, a meta-analysis published in 2019 by Andrew Vickers. (The column was written by Dr. Trisha Pasricha, who has sterling credentials, including training at Johns Hopkins Medicine where I also work. Alas, good credentials don’t always mean that you can trust the holder of those credentials, and this is one of those instances.)

Vickers has published multiple meta-analyses, and if he’s shown anything, it’s how easy it is to cherry-pick from the (extensive) acupuncture literature and find studies that prove whatever point you want to make. The Post column asserts that Vickers used 39 “high-quality” studies, but that is debatable. Many of the studies were done in China, which (as Science-Based Medicine physicians David Gorksi and Steven Novella have pointed out) virtually never publishes a negative study of acupuncture.

I’ve done a deep dive into one of Vickers meta-analyses of acupuncture–an earlier one–for one of my medical school classes, where I use it to illustrate how bad studies can be mis-reported by scientists themselves and by the media. I don’t have time to go through it here, but among other problems, Vickers doesn’t seem to understand how placebo controls work.

Here’s what I mean by cherry-picking. Vickers went through 100’s of studies to pick the 39 that he included. One of those supposedly high-quality studies looked at acupuncture for knee arthritis. That study found that both acupuncture and sham acupuncture (the placebo arm) and the same small effect on knee pain, and that patients who received no treatment at all reported more pain than patients. The authors of the study (and Vickers) concluded–wrongly–that because acupuncture was better than nothing, it must be working. Wrong! If you don’t beat the placebo, then your treatment fails.

For a drug trial, failing to beat the placebo means the game is over. But with acupuncture, it means “more studies are needed,” and the whac-a-mole game continues.

Oh, and I should add that as far as knee arthritis goes, the reduction in pain in both the acupuncture and placebo group was much less than has been reported in studies that use ibuprofen.

That’s right, ibuprofen is far better than acupuncture. Not to mention cheaper and more convenient.

If this weren’t enough, a more recent study has already contradicted the Vickers study as physician-blogger Steven Novella pointed out in a recent column. Novella wrote that “the evidence is too low quality to conclude that acupuncture works, as desperate as proponents are to say we can reach that conclusion.” So no, Dr. Pasricha, the latest science does not say that acupuncture works. Quite the opposite.

I’m still understating how badly acupuncture has failed every well-designed study to test its effectiveness. Studies have shown that placing the needles in random locations works just as well as using so-called acupuncture points. Other studies showed that sham acupuncture, where the needles don’t pierce the skin but where subjects believe they did, also works just as well. And “expert” acupuncturists can’t agree on the locations of acupuncture points.

And don’t get me started on acupuncture and the risk of infection. Acupuncturists aren’t trained in real medicine, and they don’t use proper sterile procedures. This means that they don’t necessarily sterilize their hands, or your skin at all of those points where they’re plunging needles into you. There have been thousands reports of infections due to acupuncture (dating back decades), some of them fatal. And because acupuncturists aren’t part of the medical system, we can be virtually certain that infections are under-reported.

Acupuncture isn’t going away any time soon, because people are making money from it, and no matter how many studies show that it’s nothing more than a fiction, those people will keep insisting on more studies. Plus they can point to hundreds of poorly-done studies that claim to show benefits, and argue–as the Post column does too–that “more research is needed.” I’m not making this up: that precise phrase appears in Dr. Pasricha’s article.

There are even scientific journals entirely devoted to acupuncture (here and here, for example), and they make money too, for the for-profit publishers that produce them. So you can be sure that more studies are coming, and some of them will be positive, even though acupuncture is utterly ineffective.

Even so, the Washington Post can and should do better. Here’s my (free) advice for those considering acupuncture: save your money, and just take some ibuprofen.

Good news for "Research Parasites": NEJM takes it back, 8 years later

noreply@blogger.com (Steven Salzberg) — Mon, 01 Jan 2024 12:30:00 +0000

After years of debate, the National Institutes of Health finally rolled out a data sharing policy early this year, one that should greatly increase the amount of data that biomedical researchers share with the public. This week, three prominent scientists from Yale described, in an op-ed in the New England Journal of Medicine, how “the potential effects of this shift ... toward data sharing are profound.”

For some of us, it’s deliciously ironic that this op-ed appeared in NEJM, which just a few years ago coined the term “research parasites” to describe anyone who wants to make discoveries from someone else’s data. That earlier piece, written in 2016 by the NEJM’s chief editors, was simply dripping with disdain. It caused a huge outcry, including a response from me in these pages and a sharply worded response from the Retraction Watch team, published in Statnews. The editor backed down (slightly) in a follow-up letter just a few days later, but the damage was done.

One interesting consequence was that a group of scientists created a Research Parasite Award, now awarded each year (entirely seriously, despite the tongue-in-cheek name) at a major biomedical conference, for “rigorous secondary data analysis.”

The 2016 op-ed in NEJM was itself a response to a call for greater data sharing published in the New York Times by cardiologists Eric Topol and Harlan Krumholz–and Krumholz, we should note, is a co-author of the latest piece in NEJM. Meanwhile, the former editor of NEJM retired years ago, and it appears that the journal is now ready to join the 21st century, even if it’s a few decades late.

What is all this fuss about? Well, many people outside of the scientific research community probably don’t realize that vast amounts of data generated by publicly-funded research–work that is paid for by government grants–are not usually released to the public or to any other scientists.

On the contrary: in much of biomedical research, data sets collected with government funding are zealously kept private, often forever. The usual reasons for this are simple (although rarely admitted openly): the scientists who collected the data want to keep mining it for more discoveries, so why share it? Sometimes, too, researchers package up the data and sell it, which is completely legal, even though the government paid for the work.

(It’s not just medical research data, either: once I tried to get some data from a paleontologist, only to learn that he treated every fossil he ever collected as his personal property. But that’s a blog for another day.)

Many scientists have been fighting this culture of secrecy for a long time. Our argument is that all data should be set free, at least if it’s the subject of a scientific publication. It’s not just scientists making this argument: since the early 2000s, patient groups began to realize they couldn’t even read the studies about their own diseases unless they paid a for-profit journal to access the paper. Those groups lobbied–successfully, after a years-long fight–that any publicly-funded research had to be published on a free website, not locked behind the doors of private publishers. Their effort led to an NIH database called PubMedCentral, which contains the full text of thousands of articles.

The new NIH data sharing policy is one consequence of the Open Science movement (which I’m a part of), which argues that science moves much faster when it’s done in the open. This means sharing data, software, methods, and everything else. There’s now a U.S. government website dedicated to Open Science, open.science.gov, which includes more than a dozen federal agencies including NIH, NSF, and the CDC.

A bit more history: as far as I can tell, the earliest voices for data sharing emerged during the Human Genome Project, an international effort beginning in 1989 that produced the first draft of the human genome in 2001. When a private company (Celera Genomics) emerged in 1998, a dramatic race ensued, and as one strategy for competing, the public groups announced that, in contrast to the private group, they would release all their data openly on a weekly basis, long before publication. That wasn’t how things had worked before.

Very soon after that, scientists in genomics (my own field) realized that all genome data, whether from bacteria, viruses, animals, or plants, ought to be released freely. The publicly-funded sequencing centers received millions of dollars to generate the data, but they weren’t the only places who could analyze it. NIH and NSF agreed, and pretty soon they required all sequencing data to be released promptly.

This same spirit didn’t touch most medical research, though. Even though far more money–billions of dollars a year in NIH funds–is spent on disease-focused research, data from those studies remained locked up in the labs that got the funds. This is now changing.

As the Yale scientists (Joseph Ross, Joanne Waldstreicher, and Harlan Krumholz) point out in their NEJM editorial, open data sharing has already yielded tremendous benefits. For example, they point out that hundreds of papers have been published using public data from the NIH’s National Heart, Lung, and Blood Institute, including studies that revealed new findings about the efficacy of digoxin, a common drug used to treat heart failure.

The new NIH policy covers all of NIH, not just one institute, and we can hope it will unlock new discoveries by allowing many more scientists to look at the valuable data currently kept behind closed firewalls.

But simply requiring scientists to have a “data management and sharing policy,” as the NIH is now doing, might not be enough. Many thousands of scientific papers already say they share data and materials–but as it turns out, the authors don’t always want to share.

A study published last year illustrated how toothless some current policies are. That study identified nearly 1800 recent papers in which the authors said they would share their data “upon request.” They wrote to all of them, only to find that 93% of the authors either didn’t respond at all, or else declined to share their data. That’s right: only 7% of authors shared their data, despite publishing a statement that they would.

The NEJM editorial proposes a different solution, one that could be far more effective: putting scientific data into a government repository. This is something the government itself can enforce (because they control the funding), and once the data is in a public repository, the authors won’t be able to sit on it as (some of them) now do.

It’s good to see NEJM joining the open science movement. Science that is shared openly will inevitably move faster, and everyone–except, perhaps a few data hoarders–will benefit.

A simple trick to make better coffee: cut the static!

noreply@blogger.com (Steven Salzberg) — Tue, 12 Dec 2023 13:23:00 +0000

You’d think that coffee afficionados had tried everything by now, and that few if any tricks remained undiscovered. Well, you could be right–but there’s one trick that most ordinary coffee drinkers probably don’t know, and it’s remarkably easy to do.

I’ll jump right to the punchline, and then I’ll explain the (new) science that explains it. To make richer coffee in the morning, simply spritz a little water on your beans before grinding them. That’s it!

So what happens when you do this, and why does it make better coffee? Well, as explained in this new paper in the journal Matter, by Christopher Hendon and colleagues at the University of Oregon, it’s all about reducing the static electricity that the grinding process creates.

Grinding coffee causes triboelectrification. If you’ve never heard of that, not to worry–neither had I, until I read the paper. Basically, when the beans rub together, they create static, and that makes the ground coffee clump together (and sometimes fly into the air).

Then when you make the coffee, the clumping means that the water flows through the grounds unevenly, absorbing less of the coffee particles than it might. Ideally, all the coffee grounds should be evenly and densely packed, and static electricity prevents that.

Water reduces triboelectrification quite a bit, it turns out.

So what happens? Well, after extensive experimentation–and I do mean extensive–the scientists found that the amount of coffee solids in a cup of espresso increased from 8.2% to 8.9% when adding a bit of water to the beans before grinding. That’s a relative increase of 8.5%. Richer coffee!

Reading the paper, I realized these scientists had a lot of fun doing these experiments. They measured the water content in 31 types of coffees, and tried a wide range of settings for their grinders, for the water temperature, and more.

They also roasted their own beans to varying degrees of darkness. They tried dozens of combinations of beans and roasting strategies, measuring the water content after roasting and the amount of static electricity generated upon grinding. They observed that darker roast coffees usually generate finer ground particles, and finer particles in turn generate more static electricity.

They drank a lot of coffee to get this right! But hey, sometimes science requires sacrifices, right?

I should mention that the trick of adding a little water to the beans is already known to some experts, although the precise science behind it was unknown until now. It even has a name (as the paper points out): the “Ross Droplet Technique.”

As the paper concludes, “a few simple squirts of water [may] have solved the problems of clumping, channeling, and poor extractions while aiding in the pursuit of attaining the tastiest espresso.” You only need a few drops of water–give it a try.

One important caveat is that if you use the French press method to make coffee, where the grounds are immersed in water, then this trick won’t make any difference.

What’s next? Well, I should point out that this study focused entirely on espresso. Does it work for regular coffee as well? Probably so, but more research is needed.

Vaccines Show Surprising Link To Reduced Risk Of Alzheimer’s

noreply@blogger.com (Steven Salzberg) — Tue, 31 Oct 2023 11:30:00 +0000

Well, the anti-vaccine community is not going to like this one.

A growing body of evidence, buttressed by a new report out last month, shows that people who are vaccinated have a significantly lower risk of Alzheimer’s disease.

Yes, that’s right: in addition to the obvious benefit of protecting you from infections, multiple different vaccines have now been shown, in two large studies, to be associated with fewer cases of Alzheimer’s.

How big is the effect? Well, the earlier study, published about a year ago, looked at the flu vaccine. Scientists from the University of Texas Health Science Center, led by neurologist Paul Schulz, collected data on more than 1.8 million older patients from around the U.S., of whom half had received the flu vaccine and half had not. Their average age was 74 years, and the scientists examined health records for four subsequent years to see how many developed signs of Alzheimer’s in that time.

In the vaccinated group, nearly 48,000 patients (out of 936,000) developed Alzheimer’s during the four-year follow-up period, about 5.1% of all patients. That might sound like a lot, but in the unvaccinated patients, nearly 80,000 developed Alzheimer’s. To put it another way, patients who got the flu vaccine had a 40% lower risk of Alzheimer’s, 5.1% versus 8.5%.

It appears this benefit isn’t specific to the flu vaccine, though. In the newer study published this September, the same group from the University of Texas looked at three more vaccines: the Tdap vaccine (tetanus, diphtheria, and pertussis), the shingles vaccine and the pneumococcus vaccine. They were able to collect records on 1.65 million people, among whom more than 500,000 had received one or more of the vaccines. All of the patients were over 65 years old.

Remarkably, all three of the vaccines showed similar and quite significant benefits against Alzheimer’s disease. In an eight-year follow-up period, the risk of Alzheimer’s was 30% lower (7.2% versus 10.2%) in patients who had the Tdap vaccine versus those who hadn’t. For the shingles vaccine, the reduction in risk was 25%, 8.1% versus 10.7%. And for the pneumococcal vaccine, the risk was 27% lower, 7.9% versus 10.9%.

(Note that this study looked at the older shingles vaccine. The newer one, Shingrix, has only been widely available since 2017. The scientists hypothesize that the newer vaccine, because it’s more effective against shingles, may provide even greater protection against Alzheimer’s.)

So how might this work? Is Alzheimer’s caused by an infection, and the vaccines prevent Alzheimer’s by preventing the infection? Well, the short answer is no, probably not. Although we don’t know the cause of Alzheimer’s, we don’t have any strong evidence that it’s the direct result of an infection.

Furthermore, with data showing that at least four different vaccines offer similar levels of protection against Alzheimer’s, the evidence indicates that the effect cannot be specific to the flu vaccine, or the Tdap vaccine, or with any of the other vaccines or their ingredients.

The University of Texas group that published the study speculated that vaccines might work to protect against Alzheimer’s by “long-term reprogramming of innate immune cells,” also called “trained immunity.” This hypothesis is far too complex to try to explain here–and it involves immunology, which I don’t really understand myself and which is “absurdly intricate” as science writer Ed Yong put it. So let’s just say that this is an intriguing idea that needs more research.

And for anyone who thinks that getting an infection and recovering (instead of getting vaccinated) might offer the same benefit, that doesn’t seem to work: another study looked at precisely this question and found no connection between the number of influenza infections and the risk of Alzheimer’s. So the vaccine seems to confer a benefit that the disease itself does not. (I mention this because a popular–but wrong–claim of anti-vaccine activists is that you get better immunity from infection by catching the disease and then recovering. Not a good idea.)

Also, I have to add that these studies report correlation, not causation. So even though the effects are large and significant, we don’t know for certain that vaccines do something to directly prevent Alzheimer’s. Maybe people who get vaccinated also have other behaviors that help them avoid Alzheimer’s–although the study design tried to minimize this possibility.

Vaccines have enormous, extensively documented benefits: they prevent suffering and disease, and they’ve saved countless millions of lives. And now it appears that they offer something else: a lower risk of Alzheimer’s. So if you haven’t received your boosters, now you have one more reason to get them.

Most of our common cold medicines don’t work

noreply@blogger.com (Steven Salzberg) — Mon, 09 Oct 2023 11:00:00 +0000

We still don’t have a cure for the common cold. In your local pharmacy, though, you can find many shelves filled with products that claim to treat the symptoms.

Well, it turns out that one of the most widely used ingredients, long believed to be effective at treating congestion, doesn’t work at all. The ingredient, phenylephrine, has been in use for decades, and it’s in many common cold medicines that are taken by millions of people each year, including Nyquil Severe, Sudafed PE, Robitussin CF, Tylenol Cold & Flu and others.

It turns out that phenylephrine was never properly studied for effectiveness. How can this be? It’s FDA approved, which usually means it has to be safe and effective, right? Not exactly, as I explain below.

As for phenylephrine: well, the studies have finally been done, and last month an FDA panel unanimously concluded, after reviewing the results, that phenylephrine is “useless and no better than a placebo.” It probably won’t cause you any harm, but it won’t have any effect on your stuffy nose.

To understand how this happened—and why it might be true of many other FDA-approved remedies that you can buy at the pharmacy—you have to know about how the FDA approval process has changed over the years. Pharmacists Randy Hatton and Leslie Hendeles, who worked for years trying to get phenylephrine properly reviewed, explained in a recent New York Times editorial that when the FDA was originally created, way back in 1938, it was only required to ensure that drugs were safe.

At the time, that was tremendous progress. Prior to 1938, drug manufacturers could claim pretty much whatever they wanted to.

But it wasn’t under 24 years later, in 1962, that Congress required the FDA to show that drugs were also effective. Therefore the thousands of drugs approved prior to 1962 were mostly safe, but they might not actually treat the disease they were intended to treat. After 1962, the FDA created a process to check those previously approved drugs, but they’ve never had enough staff or funding to check most of them. So phenylephrine was never properly reviewed, until now.

What’s next for phenylephrine? The FDA might ban it from the market, but that will take time, and it might not happen, because the FDA doesn’t have to follow the advice of its panels, although it usually does. Meanwhile, you can still buy cold remedies with phenylephrine, and they still claim to treat congestion.

And don’t even get me started on other treatments that are not only ineffective but that aren’t even subject to review by the FDA, such as homeopathic remedies. These include Zicam, which claims in large print on the front of its packaging that it “shortens colds.” It doesn’t, and Zicam’s manufacturer doesn’t even have to prove it, because it’s homeopathic. If you zoom way in one of the labels on the Zicam website, you’ll find the disclaimer that “Claims [are] based on traditional homeopathic practice, not medical evidence. Not FDA evaluated.” On some of the packages, I couldn’t even find the small print.

(Aside: Congress protected homeopathic preparations from FDA scrutiny way back in 1938, thanks to a homeopath who was also a U.S. Senator, and who helped write the original FDA legislation.)

I wrote about Zicam and other ineffective cold remedies in 2014 (”The Top Five Cold Remedies that Do Not Work”), and that advice still holds. Now we can add another one to the list.

We simply don’t have any drugs that work particularly well for the common cold, despite the many claims you can find online and on the labels of so-called cold remedies. The best thing you can do is just drink warm liquids such as tea or lemon-infused water, stay home and get plenty of rest.

West Virginia Says It’s Too Poor To Support Its Only Major University

noreply@blogger.com (Steven Salzberg) — Mon, 21 Aug 2023 11:30:00 +0000

As students and faculty prepared for the start of the new academic year this month, the president of West Virginia University, Gordon Gee, made a startling announcement: he’s eliminating 169 faculty jobs, about 16% of the full-time professors, and dropping 32 undergraduate and graduate degree programs, including all of its foreign language programs.

No foreign language classes? No French, Spanish, Chinese, Russian, anything other than English? Apparently not–and in response to questions, the university suggested that students might be offered an online app instead. It’s not just humanities, either: WVU is also getting rid of its graduate program in mathematics.

These cuts came as a shock to the students and faculty of WVU, who are understandably dismayed. The university administration says it’s just about money, as they face a $45 million deficit that they must do something about.

I’m not buying it. What really seems to be going on (and this is not unique to West Virginia), is that the state has steadily cut its support for WVU over the years, creating ever-larger deficits. The problem now is that the current president, Gordon Gee, seems to be saying that’s all fine with him. He didn’t even ask the state if it could help before he imposed these drastic cuts: as quoted in the Washington Post, Gee said “If I had gone down and asked for $45 million from the state legislature, they would have thrown me out.” Perhaps, but did you even try?

In the same article, State Senator Eric Tarr (R) also said he “wholeheartedly” believes that WVU president Gee is doing the right thing. And yet in the same interview, Sen. Eric said “We have never not supported WVU.”

Hmm, really? Over the past decade, the state has cut its support for WVU by 36%, or nearly $100 million. So it’s pretty clear that the legislature is not supporting WVU, at least not like they did in the past.

With support like that, who needs detractors?

According to one analysis, if West Virginia’s legislature had simply kept WVU’s funding flat for the past decade, WVU’s deficit right now would be far smaller, just $7.6 million rather than $45 million.

President Gee, did you ask the legislators about that?

I can’t help noting that WVU just renewed Gee’s contract for another year, at $800K per year. So they do seem to be able to come up with money for administrators. Gee’s only the 4th highest-paid WVU employee, with the football and basketball coaches each making over $4 million. I wasn’t able to find out how much WVU paid the consulting company rpk Group, whom Gee hired to come up with these severe cuts, but I’ll bet they weren’t cheap.

The state of West Virginia has only one R1-class research university, West Virginia University, with some 25,000 students on its main campus in Morgantown. If this trend continues, the state might no longer have even one major research university. That’s too bad.

And despite what WVU’s Gee and the consultants he hired might claim, this is not just about money; it’s about priorities. Currently, only five states don’t have an R1 level university: Alaska, Idaho, South Dakota, Vermont, and Wyoming. Does West Virginia want to join that club?

It’s true that West Virginia is one of the poorest states in the U.S., with a poverty rate of 16.8%. But can it really not afford even one major university? For West Virginia residents, WVU is the only R1 university that most of them can afford, because in-state tuition is far cheaper than out-of-state tuition at any other state university.

The way to fix this problem isn’t to eliminate the core elements of a college education, which include foreign languages. The fix is simple: the legislature should step up and say they truly support WVU, and cover its deficit without eliminating any programs. Then they should find a university president who is willing to ask for the funds that a major university needs. I’m sure they can find someone willing to do the job, maybe for even less than $800K per year.

Let’s Consider The Benefits Of Raw Milk

noreply@blogger.com (Steven Salzberg) — Mon, 17 Jul 2023 11:30:00 +0000

As reported this past week in the New York Times and elsewhere, more than half the states in the U.S. now allow the sale of raw milk. In some states, you can only buy raw milk at a farm, but in 14 states you can buy it in stores.

So why are some people excited about raw milk? Well, the implication is that if’ it’s less processed, it must be better, right? After all, we learned recently that ultra-processed foods are pretty bad for you. (There’s pretty good evidence for that.) And milk is one of those products that people associate with health. For the first few months of life, we humans live entirely on milk–but that’s milk from a woman’s breast.

Cow milk is a different matter. It’s not nearly so, shall we say, clean.

It only took a minute for me to find claims that raw milk has all kinds of benefits: supposedly it helps you digest food better, it has more vitamins and minerals, it boosts your immune system, and it’s better for people with lactose intolerance. (I won’t link to any of those claims because they’re all bogus, and I don’t want to give scammers any more web traffic.)

Before listing some of the special properties of raw milk, let’s consider how it’s processed. The main thing we do to milk is pasteurization: a very simple process where the milk is heated just enough to kill any bacteria in it. It’s not boiled, and the mild heating doesn’t destroy any of milk’s nutrients.

Pasteurization is named after the French scientist Louis Pasteur, who invented the process in the 1860s. Originally it was used to preserve wine, but people eventually discovered it worked just as well for milk and other foods. Back in the 1860s, people didn’t even know that bacteria caused disease, and Pasteur was one of the pioneers who figured that out.

So what does raw milk have in it? Well, it can carry a long list of delightful bacteria, including the ones that cause tuberculosis, brucellosis, scarlet fever, salmonella. And of course there is E. coli, including strains that can cause terrible diarrhea.

Bacteria just love milk, it turns out. Raw milk is teeming with them, and many of them are really not good for humans. Fortunately for most of us, pasteurization kills bacteria very effectively.

And there’s one more special thing you get in raw milk that you won’t get in pasteurized milk: cow poop. Funny thing, though: on the advertisements I found for the benefits of raw milk, none of them mentioned this.

So sure, get your raw milk and live like it’s 1850 again! Never mind that pasteurization has saved countless millions of lives. Seriously, folks: there’s no reason whatsoever to drink raw milk. And states that allow the sale of raw milk are endangering the health of their own people.

Does Taurine Really Extend Life? Maybe.

noreply@blogger.com (Steven Salzberg) — Tue, 13 Jun 2023 11:30:00 +0000

Readers of this column will know that I’m highly skeptical of dietary supplements. So you might imagine my reaction when I saw headlines a few days ago about “Taurine, the elixir of life?” (at CNN) and “Supplement slows aging in mice and monkeys” (NY Times).

Unlikely, I thought. But I read the scientific article behind these reports, and now I’m intrigued.

What is taurine? And could it really slow down aging? Well, it seems like it could, just maybe. A new study published last week in Science (one of the top journals in all of science) seems to show, for the first time, that taking large doses of taurine, an essential amino acid, might provide a host of benefits that include slowing down the aging process.

First question first: what is taurine? It’s an amino acid, but it’s not one of the 20 amino acids that comprise all the proteins in your body. It’s a slightly different one, and our bodies naturally produce it in small amounts. We need more than our bodies produce when we’re very young, but we get it from breast milk, and it’s added as a supplement to infant formula.

We also get extra taurine from our diet: the best foods for taurine are meats, especially shrimp and other shellfish, but also beef and the dark meat in chicken and turkey.

What did the new Science paper show? Well, first the authors (from Columbia University, India’s National Institute of Immunology, and the Sanger Institute in the UK) describe how taurine levels clearly decline with age in humans and other mammals. Now, just because taurine declines doesn’t mean that replacing it will reverse the aging process, but at least it establishes plausibility.

They then describe a series of experiments, mostly in mice but also in monkeys, where they fed the animals relatively large amounts of taurine each day, and the results were pretty darned impressive:

Life span in the mice increased by 10-12%.
In mice that started taurine supplements in middle age, life span increased by 18-25%.
Bone density increased in female mice and osteoporosis seemed to be cured.
Muscle strength increased in both males and females compared to mice who didn’t get taurine.
The number of senescent cells–cells that don’t do much except emit damaging inflammatory signals–seemed to be reduced.

Of course, there’s always a big caveat with results in mice: they’re mice, not humans! And many, many times we’ve seen results in mice that just don’t carry over into humans. So the scientists also did a study (a smaller one) in monkeys, which are much closer to humans genetically. This also had some very good results:

Bone density increased in the spine and legs.
Body fat was lower than it was in monkeys that didn’t get taurine.
Several measures of inflammation decreased.

Monkeys live a lot longer than mice, so the scientists don’t yet know if taurine increases the monkeys’ life span, but all the signs are promising. I was skeptical going into this article, but I couldn’t find any obvious flaws.

In an accompanying article in Science, U. Penn’s Joseph McGaunn and Joseph Baur point out that we don’t know for sure what the risks of long-term supplementation with taurine would be, but it is already widely taken as a supplement in baby formula and in energy drinks, with no known ill effects.

However, the amounts used in the Columbia study were very high, much higher than you’d get from energy drinks or even from standard taurine supplements. I looked up a few, and typical formulations offer 1000 or 2000 mg (which is 1-2 grams) per day. The doses given to monkeys in the study, if converted to a 150-pound person, is equivalent to about 5500 mg (5.5 grams) per day. That’s not very much by weight, and it would be easy enough to take this much taurine, but no one knows the effects in humans of such high doses.

The bottom line: this study is really intriguing. More studies are needed, especially to measure the effects of taurine on humans, but all the signs are positive. I’ll be watching closely to see if the effects in mice and monkeys carry over, and if they do, we may all be taking taurine supplements one day. And I just ordered some taurine powder for myself–why not?

AI is crying out for regulation, while virologists doing gain-of-function research take the opposite tack. Why?

noreply@blogger.com (Steven Salzberg) — Tue, 30 May 2023 11:30:00 +0000

Over the past few months, prominent tech leaders have been raising alarms about the dangers of AI, and politicians are following suit. Just last week, the Senate held hearings on how to regulate AI. The tech industry itself is calling for regulation: just a few days ago, Microsoft’s CEO testified before Congress and asked the federal government “to govern AI at every part of its lifecycle.”

One of the founders of AI, Geoffrey Hinton, just left his high-level position at Google so that he could criticize AI without any constraints from his employer. And a couple of weeks ago, I asked the AI program ChatGPT if we should trust AI. No way, it told me.

This is all kind of surprising. AI experts seem to be saying “stop us before we do any harm.” It’s also kind of refreshing: usually the private sector wants the government to stay out of its affairs.

Now contrast all this with the behavior of virologists on a completely different technology: gain-of-function research on deadly pathogens. As I’ve explained before, gain-of-function (GoF) research takes a deadly pathogen, such as the influenza virus or the Covid-19 virus, and modifies it to make it even more deadly. Many scientists, including me, find this work both alarming and of little benefit, and we’ve been calling for it to be regulated for a decade now.

However, unlike AI experts, many virologists are opposed to any hint of regulation of their GoF work. On the contrary: just recently, 156 leading virologists jointly authored an opinion piece that lauded the many wonderful benefits of GoF, and pooh-poohed any risks.

Don’t worry your pretty little heads, these virologists seem to be saying to the rest of the world. We know what we’re doing, and it’s not that risky. Plus it’s great! Not to put too fine a point on it, but I disagree.

What’s caught my attention this week is not just the contrast in their willingness to be regulated, but the question of how one might imagine doing it, in both cases.

Simply defining what we mean by “AI” today is probably impossible. The number and types of programs that incorporate some form of artificial intelligence is vast and already affects our lives in many ways. The recent alarm bells were caused by one particular type of AI, known as large language models (LLMs), which have the ability to fool people in a new way. For several years now, more alarm bells have sounded (justifiably so) over “deep fakes,” images or videos that appear real but that are completely made up. These use completely different technology.

So even if we agree that AI needs to be reined in, no one can really say with any precision what that would mean.

Now let’s look at gain-of-function research on pathogens. One of the biggest objections that some virologists have made, on many occasions, is that there’s no way to define just the harmful research, so we really should just leave it all alone.

For example, the recent commentary by 156 virologists said that “gain-of-function approaches incorporate a large proportion of all research because they are a powerful genetic tool in the laboratory.” This is nonsense. It’s equivalent to saying “hey, this is science, and you don’t want to ban all science, do you?”

They also defend GoF by trotting out examples of research that were beneficial, such as the recent rapid development of Covid-19 vaccines. As was pointed out recently in the biology journal mBio, this is a red herring: it’s just not that difficult to define GoF “research of concern” and distinguish it from other, much more mundane virology and bacteriology research.

In fact, biologists have already done this, in a recent set of proposed new guidelines for regulating GoF research. As Hopkins researcher Tom Inglesby put it, “if you are going to make a more transmissible strain of Ebola, then you need to have the work reviewed by the U.S. government.”

So why do the AI scientists say “please regulate us” while many virologists say “leave our gain-of-function work alone”? It’s not because it’s too hard to define one or the other–if it were, the AI experts wouldn’t even consider regulation as a possibility.

No, it seems that it’s all about money. AI is thriving in both academia and industry, with tremendous growth ahead. The people calling for regulation just aren’t worried about money. They know that AI will continue to thrive, and they are calling for regulation because they seem to have genuine concerns about the threat that AI poses to society.

On the other hand, the world of gain-of-function research is very small, and almost entirely dependent on government funding. Although I’m sure they’ll deny it, these scientists are worried that they’ll lose their grants if even a small portion of GoF research is shut down. They may also be worried about more direct threats to their finances: the conflict-of-interest statement on that recent article by 156 virologists goes on for 731 words. (That is one of the longest conflict-of-interest statements I’ve ever seen on a scientific article.)

I decided to ask an AI (ChatGPT) these questions. When asked about regulating GoF, it replied with a long answer that concluded,

“Ultimately, the decision to regulate gain-of-function research involves weighing the potential risks and benefits. Striking the right balance requires collaboration between scientists, policymakers, and relevant stakeholders to establish guidelines, promote responsible research practices, and implement appropriate oversight mechanisms.”

ChatGPT’s answer about regulating AI was similar, concluding:

“Regulation can play a crucial role in ensuring that AI systems are developed and deployed responsibly... The specific nature and extent of regulation will likely depend on the application and level of risk associated with AI systems. Striking the right balance between regulation and fostering innovation is essential to ensure that AI technology benefits society while safeguarding against potential risks and ethical concerns.”

Overall, not bad advice. Now if only those virologists will listen.

Should we allow AI to control the battlefield? AI itself thinks not.

noreply@blogger.com (Steven Salzberg) — Mon, 08 May 2023 11:30:00 +0000

Artificial Intelligence, or AI, seems to have finally arrived. With the introduction of ChatGPT last November, millions of people suddenly discovered that AI was far, far more than just a research activity. The range and sophistication of ChatGPT’s answers to questions across a wide range of disciplines is, frankly, pretty stunning.

AI is already in lots of places where you might not even realize it. Google Translate has been using AI for years, and it’s remarkably good, although nowhere near as good as a human translator. The technology that Pandora uses to customize your music is a type of AI, as is the technology behind Tesla’s self-driving cars. Within my own field, the program AlphaFold2 was a true breakthrough in scientists’ ability to predict the structure of proteins.

Along with these apparently beneficial developments, though, comes a great deal of concern. As AI gets better and better, can we continue to trust it to make decisions for us? It’s one thing if an AI recommends a song that we don’t like, which we can just ignore, but if AI is driving our cars, then mistakes might be much more costly.

And there are far riskier tasks that AI might be doing soon: what if the military starts using AI on the battlefield? One might be tempted to say no, of course they won’t do that, but what if another country starts using AI this way? Can we simply ignore that?

To be honest, I haven’t been worried, at least not yet. I have a little secret to confess: I did my Ph.D. thesis in AI, in the area called machine learning. I haven’t been doing AI research for the past 25 years, but I think I still understand at least a little of the basics behind the technology.

Thanks mostly to the attention that ChatGPT is getting, though, there’s suddenly a huge concern that AI represents a danger to society, although no one is exactly sure why. President Biden had a meeting just this week with the CEOs of Google, Microsoft, and OpenAI (the creators of ChatGPT) to talk about these concerns, where he told the execs that “What you’re doing has enormous potential and enormous danger.”

Of course, politicians have no idea what AI technology is–although I had to laugh at this quote from the White House press secretary: “The president has been extensively briefed on ChatGPT and knows how it works.” Um, no he doesn’t. I’m skeptical that the CEOs of Google and Microsoft know how it works either. However, you don’t need to understand the technology to understand the dangers.

Just recently, one of AI’s early pioneers, Geoffrey Hinton, has been speaking out to warn the public that AI has reached a point where “there’s a danger of something really bad happening.” Not surprisingly, other experts, such as German scientist Jürgen Schmidhuber, disagree.

The chair of the FTC, Lina Khan, says we can regulate AI effectively, and perhaps we can. But I’m not so sure.

Much of the concern in the press seems to be about the use of AI to spread misinformation. For example, AI can help create “deep fakes” that can be used to convince people that, say, an election was stolen even when it wasn’t. That’s a legitimate concern, but it’s happening even without AI.

A better question, which a family member just asked me, is should we be worried about AI making decisions on the battlefield? I thought I should take this question directly to the source, so I asked ChatGPT itself. The answer I got was remarkably clear and direct; I’ll quote it here in full:

“Yes, people should be concerned about AI making decisions on the battlefield. There are several reasons for this.

Firstly, AI lacks human empathy, judgment, and intuition. In a complex and dynamic environment such as the battlefield, human decision-making is often guided by experience, intuition, and an understanding of the broader context. AI lacks the ability to consider these intangible factors and may make decisions solely based on pre-programmed algorithms or data inputs, which could lead to unintended consequences or even catastrophic errors.

Secondly, the use of AI in military decision-making raises significant ethical concerns. For instance, an AI system may be programmed to prioritize the protection of friendly forces at the expense of civilian lives, leading to potentially devastating consequences for non-combatants caught in the crossfire. Additionally, AI systems may be susceptible to hacking or manipulation, which could result in unintended consequences or a loss of control over the decision-making process.

Finally, there is the risk that reliance on AI systems may lead to the erosion of human decision-making capabilities, potentially diminishing the overall quality of military decision-making and increasing the likelihood of errors or unintended consequences.”

So there you have it: ChatGPT itself gives us several reasons why it’s a terrible idea to let AI make decisions that might cost human lives. We should listen to what it’s telling us, because as it gets more intelligent (and it will), it might decide not to be so honest in the future. And I have to say that it’s reasoning here is both well-written and compelling.

One thing that worries me as well is that the very term “artificial intelligence” is much too broad. We should be concerned about giving any technology the power to control our lives, whatever someone calls it. But when an AI itself says “don’t trust me,” then I think we might want to listen.

Gain of function research needs to be banned, but we need to define it properly

noreply@blogger.com (Steven Salzberg) — Mon, 17 Apr 2023 11:30:00 +0000

I’ve been writing about dangerous gain-of-function research on viruses for years, originally on the flu virus and more recently on the Covid-19 virus. Many people are deeply concerned about this research, which might have caused the Covid-19 pandemic, and yet there are still no real regulations controlling it, neither in the U.S. nor anywhere else.

I can already hear the objections: oh, but what about the new rules that NIH put in place in 2017, after a 3-year “pause” in some gain-of-function (GoF) research? Those rules were utterly ineffective, but I’ll get to that in a minute.

Despite my arguments, and the concerns of many other scientists, which have been expressed in various forums and articles for at least a decade now, the virology community continues to insist that any limits on GoF are unnecessary, and that GoF is wonderfully beneficial. A group of 156 virologists even wrote an opinion piece, published in the Journal of Virology, making this very point.

I’ve tried to convince some of my colleagues in the infectious disease world that GoF should be banned, and I’ve discovered that many of them–even some non-virologists–are opposed to any government regulation of GoF research.

They are wrong. However, they do raise one important concern that I think is valid, and that I will address in this column. Their concern is that any government regulation will be ham-handed, and will likely end up limiting or preventing a range of very useful experiments that have the potential to lead to beneficial new drugs and vaccines.

I get it. When the government tries to regulate science, it can write rules that are far too broad, or that get mis-interpreted even if well-written, and unintended consequences follow. So let’s not do that: below I’ll explain what I think needs to be banned.

But let’s not forget why we are having this debate right now: there is a very real possibility that the Covid-19 pandemic started in a lab that was doing GoF research on coronaviruses. We know that the Wuhan Institute of Virology (WIV) was doing this kind of research–that fact is not under dispute. We don’t know (and we may never know) if the original Covid-19 virus first appeared as a result of a lab leak, but it might have. That’s why we’re asking whether such research is worth the risk.

Before I explain what I think the rules should be, let’s look at the current NIH rules, which I mentioned above. First, though, let’s remember that NIH rules only apply to research funded by NIH. Research that is funded privately, or by any other part of the government, is unaffected by these rules and remains entirely unregulated.

So: back in 2017, when the NIH lifted the 3-year funding pause, they put in place some rules (detailed here) for work on “potential pandemic pathogens,” or PPPs. (The government loves acronyms.)

The pause itself was prompted by work on avian influenza, led by virologists Ron Fouchier and Yoshihiro Kawaoka, that was designed to turn some deadly bird flu viruses into human flu viruses. The work was successful: the researchers did indeed create viruses that had the potential to infect humans. These results were really alarming to many scientists: I wrote about it at the time, and other scientists also raised the alarm. Those concerns are what led to the funding pause.

Since 2017 then, the NIH regulates (but doesn’t ban) research on PPPs that are both:

“likely highly transmissible and likely capable of wide and uncontrollable spread in human populations, and
likely highly virulent and likely to cause significant morbidity and/or mortality in humans.”

One of the first things to notice about this definition is that avian influenza–the very work that prompted the new rules–isn’t really covered.

Another thing to notice is that work on coronaviruses in bats–the GoF work that was apparently going on in the Wuhan Institute of Virology, and that may have caused the Covid-19 pandemic–wouldn’t have been covered either. Those bat viruses would not have been considered “likely highly transmissible in humans,” not before the pandemic.

Of course, we all know differently now.

In any case, the rules that NIH introduced in 2017 only applied to a very narrow class of work, and as far as I can tell, they didn’t restrict anything. On the contrary: the NIH resumed funding the GoF work on avian influenza work by Fouchier and Kawaoka soon after lifting the funding pause. And let’s not forget that NIH rules aren’t a ban: it remains perfectly legal to do any kind of GoF work.

So how can we put in place intelligent restrictions that will prevent dangerous GoF research in the future?

First, rather than rejecting any restrictions whatsoever, as some virologists have done, scientists should work with the government to craft a thoughtful set of limitations. For starters:

Research that creates new strains of the Covid virus (SARS-CoV-2) that might have greater virulence or transmissibility should be entirely banned.
Research that takes non-human viruses, including avian flu and bat coronaviruses, and gives them the ability to infect any new animals, should be banned.

To scientists who can’t even agree on these restrictions, I would say that it appears you oppose any restrictions whatsoever. If that’s your position, then the government might step in and impose far broader bans, which are not likely to be good. If you’ll agree to these two restrictions, perhaps we can broaden them slightly to cover other types of highly risky GoF work.

Finally, let me return to a point I’ve made before, but that bears repeating: the supposed benefits of GoF research are essentially zero. The claim that GoF research that makes a virus more deadly will help us “understand pathogenicity” or “be prepared for the next pandemic” are just hand-waving arguments. I wrote a whole column just last month explaining why these claims are fundamentally wrong, so I won’t repeat that here.

If we do ban some GoF research, with carefully-crafted rules, we won’t lose anything. Instead, we’ll gain at least two things: first, virologists can apply their expertise to truly beneficial virology work, and second, the scientific community will regain some of the trust it has lost during the pandemic. That would seem like a good thing.

Herbal extracts that cure an enlarged prostate? Not likely.

noreply@blogger.com (Steven Salzberg) — Mon, 10 Apr 2023 11:30:00 +0000

Saw palmetto, which is NOT effective for

treating enlarged prostates.

(Note: see the brief update at the bottom of this post for a response from the manufacturer.)

I haven’t looked at medical scams recently, and I thought I’d venture back into that world just a little bit this week, to see what is happening.

As always, the scams are everywhere, with products claiming to cure just about everything. What surprised me, though, is how blatant some of them have become. Some sites have no caveats or disclaimers at all, despite the fact that their claims are utterly false. They don’t even pretend that they are worried about a regulatory agency objecting to their false claims. The boldness can be startling–or, if you’re not sufficiently skeptical, convincing.

Let’s look at one site that strikes me as particularly egregious, which sells a dietary supplement called Prostoxalen as a cure for prostate problems. I was directed to this site by another site, ShopBodyVibes, that sells an even wider range of bogus cures (more on that below).

The marketers of Prostoxalen, which they sell for $40 for a bottle of 60 pills, are nothing if not direct. At the top of their website, they promise that Prostoxalen will “get rid of the constant pressure on the bladder, unpleasant pain and all other ailments related to prostate enlargement! Once and for all!”

Nowhere do they provide even a shred of evidence for this claim.

And there’s more: they also claim that Prostoxalen will cure erectile dysfunction: “if you've noticed erection problems, our capsules will fix that issue as well,” the site states.

Again, no evidence at all.

I was expecting at least a citation to a poorly-done study published in a low-quality journal - after all, even homeopathic treatments, which are laughably ineffective, can find some bad science to support their claims.

But no, not for Prostoxalen. Maybe its marketers think that the testimonials alone (which appear to be fake) are sufficient.

So what on earth is in these pills? Well, it turns out that they’re just plant extracts and vitamins. The main ingredients are extracts of saw palmetto, pumpkin seeds, cranberries, tomatoes, nettles, and willowherb, along with a couple of common vitamins.

Great! So all you need is cranberries, tomatoes, and pumpkin seeds, and your prostate problems will go away. I’m surprised that anyone has an enlarged prostate, if this is all it takes to cure it.

But here’s the problem: there is no good scientific evidence that any of these ingredients will cure or relieve the symptoms of enlarged prostate. Not even a tiny bit.

(If you want to dig deeper, you can find multiple scientific studies of saw palmetto, which is widely marketed as a treatment for enlarged prostates. A carefully-done randomized trial out of Washington University, back in 2013, show that it simply doesn’t work, even at high doses.)

The name Prostoxalen sounds just a little bit like they might want you to think it’s a drug, doesn’t it? Maybe something to do with the prostate? Fortunately, the website answers this question in a FAQ list, which says: “No, Prostoxalen is not a drug. It is a food supplement in the form of capsules.”

Aha, that explains it. Dietary supplements aren’t regulated by the FDA, unless you claim that they’re a drug or that they can treat a medical condition.

What I expected to see on the website, but didn’t, was this disclaimer: “these statements have not been evaluated by the Food and Drug Administration. This product is not intended to diagnose, treat, cure, or prevent any disease.” That’s the small-print language that appears on thousands of websites and products, and that allows supplement makers to make all kinds of hints and suggestions while avoiding regulation. Typically they use phrases like “supports prostate health,” as one saw palmetto product puts it.

It appears that Prostoxalen is manufactured and sold by a company in Poland, identified on the website only as PLT Group. So I guess they just don’t care what the FDA thinks–even though they are marketing this in the U.S. (I contacted them through their website, but they didn’t respond.)

So no, there is no magic pill that cures or relieves the symptoms of enlarged prostates, and any such cure is almost certain to require more than a few plant extracts.

Finally, about that site that directed me to Prostoxalen: that was ShopBodyVibes, a site that sells products to “make the penis longer” (Eroxel), “cleanse the body of toxins” (BurnBooster), “reduce varicose veins” (Variforce), “eliminate knee pain” (Ortezan), and a “breast enlargement serum” called BooUp. I’m not making this up. Needless to say (but I’ll say it), none of these products works–and yet the site has no disclaimers, nor does it provide any evidence for the claims.

The ShopBodyVibes site repeats all the claims from the Prostoxalen website (see here), again with no disclaimers. If you wonder what is in this product, (as I did), ShopBodyVibes suggests that “Everyone who is interested in learning the detailed composition of the product can read the list of ingredients, which is available on the manufacturer’s official website.”

Perhaps unsurprisingly, the ShopBodyVibes site has no indication of where it is located. It appears to be outside the U.S., which explains its stunning lack of any attempt to qualify its many bogus claims. It also has enough similarity to the Prostoxalen site to suggest that both sites might be owned by the same group in Poland. They didn’t respond to my inquiries.

And if you’re wondering how I stumbled upon BodyVibes: they were promoted by an article on Goop (yes, that’s Gwyneth Paltrow’s lifestyle company) about “wearable stickers that promote healing.” Yes, BodyVibes sells those too. I wrote about these magic stickers back in 2017, and my advice then still applies: they still don’t work, but if you like stickers, you can get a sheet of 50 for a couple of bucks.

Update: the manufacturer of Prostoxalen replied to my inquiry after this post appeared. Their message, in full, said: “our product has passed all the required tests before being launched on the market. It has proven to be highly effective, safe and legally introduced. We are a Polish company - the product is on the list of the National Sanitary Inspectorate at the Ministry of Health in Poland.” They did not provide any evidence or citations to support these claims, particularly the “highly effective” claim.

Scientists can now create mice with two fathers

noreply@blogger.com (Steven Salzberg) — Mon, 20 Mar 2023 11:30:00 +0000

Scientists at Osaka University in Japan have just created baby mice with two dads. That’s right: these mice have two parents, and both parents are males.

How did they do it, and what might this mean for humans?

Well, as reported recently in the journal Nature, it wasn’t easy. The scientists fertilized 630 eggs to get just seven mouse pups, but all seven mouse pups appeared normal and grew into fertile adults.

Let’s dig into the process just a little bit. The research team, led by biologist Katsuhiko Hayashi, first took cells from male mice, and they had to somehow re-program the cells to create egg cells.

One thing about egg cells in mammals: they are always female. Or to be more precise, they have two copies of the X chromosome. Males have one X and one Y chromosome, and the male mouse cells in this experiment started out that way too.

Hayashi’s team first took cells from male mice and turned them into pluripotent stem cells–a special type of cell that can then be turned into many other types of cells, including eggs. Then they grew these cells in Petri dishes until some of them spontaneously lost their Y chromosomes. Now the cells had 1 copy of the X chromosome, but no Y.

That only got the scientists part of the way to where they needed to be. The team then used another genetic trick that induced some of these cells to pick up an extra X chromosome while they were replicating. At that point, they had created mouse cells with two X chromosomes: in other words, the cells were genetically female.

The next step was to convince these XX cells to turn into egg cells. They did that using additional genetic techniques to coax the pluripotent cells to divide and form egg cells, each of which had just one copy of every chromosome (as egg cells do), including the X chromosome.

Those were the hard parts. Once they had the egg cells, the scientists fertilized them with sperm from other males, and then implanted 630 fertilized eggs in female mice. It wasn’t a very efficient process, but it worked: seven of the embryos successfully matured into baby mice, which grew into normal, fertile adults. (Note that mice only take 3-6 months to reach maturity.)

You might be wondering if all mice (or other mammals) with two male parents would have to be males. Well no, not at all. Sperm cells, which come from males, have either an X or a Y chromosome. After fertilizing the eggs, which all have X, the result is either XX (female) or XY (male), depending on which chromosome the sperm carried.

The scientists who did this work emphasized that we’re still a long way from making it work in humans. Among other things, we’d have to be sure that all of the steps involved in turning the male cell into an egg didn’t create harmful mutations elsewhere.

You might also ask if this means that we can also create babies using two female parents. Well, probably yes, but not using the process described here: to create a baby from two females, we’d need to take a female cell (any cell would do) and then turn it into a sperm cell. This is possible too! As it happens, a 2021 paper from Emory University described how scientists have recently created sperm cells from pluripotent cells in rhesus macaques. If viable sperm cells can be created, then they can be used to fertilize eggs, which would give us offspring with two female parents. (In this case, all of the babies would be female.)

But at least in principle, it may soon be possible for two men to have a child where both of them are the child’s genetic father.

Gain-of-function research on viruses justifies itself with a scientific error

noreply@blogger.com (Steven Salzberg) — Mon, 27 Feb 2023 12:30:00 +0000

We still don’t know where Covid-19 started, although we’re pretty sure it started in or near the city of Wuhan, China. The leading theories are that it started either in the Huanan Wholesale Seafood Market (in Wuhan), a live animal food market, or in the Wuhan Institute of Virology (WIV), a large virus research center in another part of the city.

We might never know, because we’d need access to all of the viruses being studied at WIV in late 2019, and those viruses might not even exist any longer.

I’ve been on the fence about this question since the pandemic started (as I wrote here and here and here), in part because we just don’t have enough data. However, I’m now starting to lean more strongly towards the hypothesis that the Covid-19 virus started in the Wuhan Institute of Virology. I just listened to the interview that Sam Harris did with science journalist Matt Ridley and biologist Alina Chan, who together wrote an entire book on the origins of Covid-19, and the evidence they compiled is compelling.

Let’s look at a few key points.

First, the virus itself, SARS-CoV-2, almost certainly originated in bats, and those bats almost certainly came from caves in southern China, over 1000 kilometers away from Wuhan. The bats didn’t get to Wuhan on their own.

So either someone transported bats to the Huanan Seafood Market, or they transported viruses from the bats to WIV. These are our choices.

Second, WIV was doing research on coronaviruses for years. Their scientists traveled regularly to caves in southern China to find novel viruses, and they’ve acknowledged that WIV’s labs had bat viruses, including viruses related to SARS-CoV-2, before the pandemic began.

Third–and this point is under some dispute–many scientists have argued that the virus was a naturally-occurring one. However, this doesn’t make it more likely that the virus originated in the seafood market. It’s just as likely that a scientist or technician working at WIV was accidentally infected, and then went home (maybe stopping by the seafood market on the way) and started a worldwide pandemic.

Fourth, it’s hard to believe that it’s merely a coincidence that one of the top virology labs in China just happened to be located in the city where the pandemic began. WIV was not only the foremost lab in China doing work on SARS-like viruses, but they also claimed previously that they intended to do gain-of-function work to make these viruses more pathogenic.

This startling fact emerged when a 2018 grant proposal by EcoHealth Alliance, a US-based nonprofit that was working with WIV, was leaked to the press in 2021. Even though that proposal was never funded, the text describes how EcoHealth would genetically engineer new viruses, taking the spike protein from one bat coronavirus and inserting it into a different one, and then infecting mice to see what happens.

But wait, some will say: we now have peer-reviewed studies pointing to the seafood market as the epicenter of the pandemic. (I wrote about those studies back in March 2022.) However, as Alina Chan and Matt Ridley explained to Sam Harris (and in their book), the Chinese authorities in early 2020 focused all their attention on the seafood market, to the exclusion of anywhere else. They collected loads of samples from people who had been in or near the market, and very little from anywhere else. Thus we seem to have a classic case of confirmation bias: when you only look at the place where you’re convinced the virus originated, and you find some evidence, then you stop looking. We simply don’t know if the virus was anywhere else.

Now, to the main topic for today: the scientific error used to justify gain-of-function research on dangerous viruses, the error that might have led to the Covid-19 pandemic. Let me explain.

Why, one might ask, were scientists from the Wuhan Institute of Virology going out into the wild, to places where humans would not otherwise go, and bringing back deadly viruses?

This doesn’t just happen in China. The US is funding a large effort to do exactly the same thing: through a program called DEEP VZN (”deep vision,” get it?), USAID is funding scientists in the US and in Africa, Asia, and Latin America to venture into unpopulated areas of the jungle, and to find animals carrying viruses that might infect humans. They’re hoping (!) to discover 8,000 to 12,000 new viruses, and they’re particularly interested in viruses that could cause the next pandemic.

Why does anyone do this? Virus hunters believe that through these efforts, they can predict which of these viruses are destined to become the next pandemic. Furthermore, the argument goes, through gain-of-function research, virologists will be able to determine just what the new pandemic strains will look like. Then, armed with this knowledge, they can convince governments and private companies to design, manufacture, and stockpile vaccines against these viruses. This way (the argument goes) when the pandemic emerges, we’ll be ready.

At the center of this scientific strategy is an obvious error about evolution.

I’ll have to get a bit technical to explain here, so bear with me: the genome of the SARS-CoV-2 virus contains about 30,000 bases of RNA. The key protein that lets it infect human cells is called the Spike protein, which is about 1300 amino acids long and is encoded by about 3900 RNA bases. RNA has an alphabet of 4 letters (A, C, G, and U), which means that each of those positions can mutate into one of the other 3 letters. So we have almost 12,000 possible mutations that affect just one base in the Spike protein.

But 2 or more mutations can happen at once, quite easily, and this too could make the virus more infectious. How many combinations of 2 positions and 3 mutations are possible? Well, about 650,000,000.

And these aren’t the only mutations that might create a pandemic virus. So we’re supposed to believe that:

gain-of-function experiments in the lab will create precisely the same mutations that would happen in the wild, and
virologists can then predict, based on their experiments, that a virus is likely to cause a pandemic, and
this evidence is so convincing that governments will manufacture and stockpile vaccines based on these experiments, and
that this in turn will allow us to prevent the next pandemic.

Yeah, right. The evolutionary mistake is in the first point above, by the way.

Something happened in Wuhan. You might think that virologists, upon hearing about the gain-of-function research at WIV, would pause and think, oh no, we hope our colleagues’ research didn’t cause the pandemic! But instead, they closed ranks and doubled down.

In case you think I’m exaggerating, consider this: just a month ago, 156 virologists co-authored an article in the Journal of Virology that declared:

“gain-of-function research-of-concern can very clearly advance pandemic preparedness and the development of vaccines and antivirals. These tangible benefits often far outweigh the theoretical risks posed by modified viruses.”

In case that wasn’t clear enough, they assert twice more in the article that gain-of-function research will help us prepare for pandemics.

Virologists have been making this argument for years, and yet their experiments had no benefit at all–none, zero, zip–when we were finally faced with a true pandemic. Why should we believe this claim now?

Instead, it’s possible that gain-of-function research, along with the search for novel viruses in the wild, might have accidentally caused the pandemic.

Let me conclude by emphasizing that the vast majority of research on viruses and infectious diseases is incredibly important. Vaccines, antibiotics, antivirals, and other treatments have saved millions of lives, and the scientists doing this work should be applauded. Shutting down dangerous gain-of-function research–by which I mean research designed to take a virus or bacterium and make it more deadly in humans or in other animals–would only affect a tiny percentage of virologists worldwide. Let’s tell them to stop. If they can’t find something better to do, other scientists can.