"People also ask" about junk DNA

I'm interested in the spread of science misinformation on the internet. The misinformation about the human genome is a good example that illustrates the problem. There are many other examples but I happen to know a lot about this particular one.

Anyone trying to find out about junk DNA will find it impossible to get a correct answer by searching the internet. The correct answer is that the amount of junk DNA in the human genome is controversial: some scientists think that most of our genome is functional while others think that as much as 90% is junk. The scientific evidence strongly favors the junk side of the controvesy and that's very well explained in the Wikipedia articles on Junk DNA and Non-coding DNA.

Creation Myth: Biologists Thought All Non-Coding DNA was Junk

Watch this short video from Daniel Stern Cardinale. He read my book!

---

Benjamin Lewin's new book and his view of the human genome

I was a big fan of Benjamin Lewin. Back in the 1970's he published the first volumes of what was to become Genes, the authoritative textbook of molecular biology. I admired his ability to understand the latest experiments and put the results in the appropriate context.

Later on, when he founded the journal Cell, his editorials and other writings were always insightful. His editorial judgement was impeccable—he always published the very best papers in molecular biology.¹

Why do Intelligent Design Creationists lie about junk DNA?

A recent post on Evolution News (sic) promotes a a new podcast: Casey Luskin on Junk DNA’s “Kuhnian Paradigm Shift”. You can listen to the podcast here but most Sandwalk readers won't bother because they've heard it all before. [see Paradigm shifting.]

Luskin repeats the now familiar refrain of claiming that scientists used to think that all non-coding DNA was junk. Then he goes on to list recent discoveries showing that some of this non-coding DNA is functional. The truth is that no knowledgeable scientist ever claimed that all non-coding DNA was junk. The original idea of junk DNA was based on evidence that only 10% of the genome is functional and these scientists knew that coding regions occupied only a few percent. Thus, right from the beginning, the experts on genome evolution knew about all sorts of functional non-coding DNA such as regulatory sequences, non-coding genes, and other things.

Kat Arney interviews me on her podcast

I had a long chat with Kat Arney a few weeks ago and she has now taken the best parts of that conversation and put them in her latest Genetics Society podcast: Genes, junk and the 'dark genome'. My comments are in the last twelve minutes. At the end, Kat asks me "Is there like one thing you would really want a student or researcher, working in genetics today to really understand about the human genome?"

Kat was kind enough to write a blurb for my book last year where she said,

What's in Your Genome? is a thought-provoking and pugnatious book that will make you wonder afresh at the molecular intracies of life. When it comes to our genomes, we humans are nothing special—Moran makes a convincing argument that the vast majority of our sloppy human genome is not mysterious genetic treasures but boring junk.

In this podscast, she combines my thoughts on the human genome with those of two people who don't agee with the idea that the human genome is full of junk. Here's a brief summary of their positions.

Naomi Allen is Chief Scientist at UK Biobank, a consortium that's sequencing the genomes of UK citizens. So far, they've published data on 500,000 genome sequences. I wrote about one of their more significant findings last year (August, 2022) where they reported on the fraction of the human genome that was under purifying selection. This is an excellent proxy for functional DNA and the results are in line with (my) expectations: less that 10% of the genome is conserved and most of it is in the non-coding fraction [Identifying functional DNA (and junk) by purifying selection.

It's too bad that Kat's interview with Naomi Allen doesn't mention that important result, especially since the podcast is about junk DNA. Here's how Naomi Allen begins her part of the interview.

Whole genome sequencing enables researchers to look at all of the genetic variation across the entire genome. So not just in the 2% of the genome that encodes for proteins, but all of the genetic variation, much of which was previously considered "junk DNA" precisely because we didn't know what it did.

This is disappointing for two important reasons. First, surely in 2023 we've gone beyond the tired myth that all of the information in the human genome was concentrated in coding DNA? Second, no knowledgeable scientist ever said that all non-coding DNA was junk DNA and the idea of junk DNA was not based on ignorance so surely it's time to stop repeating that myth as well.

The rest of that interview focuses on how mapping genetic variation could contribute to our understanding of health and disease. I would have loved to ask how Biobanks proposes to do this if most of the variation is in junk DNA and also ask whether mutations in junk DNA can contribute to genetic disease. (They can.)

Danuta Jeziorska is the CEO of Nucleome Therapeutics, a company that's described as "spun out of Oxford University with a new set of technologies for exploring the dark genome." Kat asks her about the dark genome and here's her response.

So if you think about it, we have 22,000 genes in our genome, and we can compare that to having 22,000 ingredients in the fridge. We use the same set of ingredients to create different meals, just like how we have the same DNA within each cell, but then we have hundreds of different cell types. So this dark genome determines the combination of ingredients of the genes that you take and at which level you use them, to produce the different cell types that build our body. And you can just imagine that if you make a mistake in that - so let's say that you add the wrong ingredients in the wrong meal, you can mess up the meal. And in this same way you can mess up the cell type. So if you, for example, if you don't produce enough of haemoglobin to transport oxygen around the body, you will end up with a genetic form of anaemia or if you turn on a gene that's not supposed to be turned on, like an oncogene, you may end up having cancer.

So the dark genome is now very well understood as the mechanism that is causing diseases.

This is a slightly different definition of the dark genome than those I discussed in a recent post [What is the "dark matter of the genome"?]. In that post I suggested that most scientists were referring to all of the functions in non-coding DNA but Danuta Jeziorska seems to be restricting her use of "dark genome" to just regulatory sequences. In the rest of the interview she goes on to describe various types of regulatory sequences, with an emphasis on 3D structure, and to explain that many common genetic diseases are caused by mutations in regulatory sequences. Her company is using machine learning to find the functional elements in the dark genome and which variants are associated with disease. They are also investing in drug discovery.

---

What is the "dark matter of the genome"?

The phrase "dark matter of the genome" is used by scientists who are skeptical of junk DNA so they want to convey the impression that most of the genome consists of important DNA whose function is just waiting to be discovered. Not surprisingly, the term is often used by researchers who are looking for funding and investors to support their efforts to use the latest technology to discover this mysterious function that has eluded other scientists for over 50 years.

The term "dark matter" is often applied to the human genome but what does it mean? We get a clue from a BBC article published by David Cox last April: The mystery of the human genome's dark matter. He begins the article by saying,

Twenty years ago, an enormous scientific effort revealed that the human genome contains 20,000 protein-coding genes, but they account for just 2% of our DNA. The rest of was written off as junk – but we are now realising it has a crucial role to play.

What really happened between Rosalind Franklin, James Watson, and Francis Crick?

That's part of the title of podcast by Kat Arney who interviews Matthew Cobb [Double helix double crossing? What really happened between Rosalind Franklin, James Watson and Francis Crick?].

Matthew Cobb is one of the world's leading experts on the history of molecular biology.

The way it’s usually told, Franklin was effectively ripped off and belittled by the Cambridge team, especially Watson, and has only recently been restored to her rightful place as one of the key discoverers of the double helix. It’s a dramatic narrative, with heroes, villains and a grand prize. But, as I found out when I sat down for a chat with Matthew Cobb, science author and Professor of Zoology at the University of Manchester, the real story is a lot more nuanced.

Photo 51 did not belong to Rosalind Franklin and it had (almost) nothing to do with solving the structure of DNA. Franklin and Wilkins would never have gotten the structure on their own. Crick and Watson did not "steal" any data. Whether they behaved ethically is debatable.

---

ChatGPT gets two-thirds of science textbook questions wrong: time to bring it into the classroom!

The November 16th issue of Nature has an article about ChatGPT: ChatGPT has entered the classroom: how LLMs could transform education. It reports that the latest version (GPT4) can only answer one third of questions correctly in physical chemistry, physics, and calculus. Nevertheless, the article promotes the idea that ChatGPT should be brought into the classroom!

An editorial in the same issue explains Why teachers should explore ChatGPT’s potential — despite the risks.

Many students now use AI chatbots to help with their assignments. Educators need to study how to include these tools in teaching and learning — and minimize pitfalls.

I don't get it. It seems to me that the problems with ChatGPT far outweigh the advantages and the best approach for now is to warn students that using AI tools may be terribly misleading and could lead to them failing a course if they trust the output. That doesn't mean that there's no potential for improvement in the future but this can only happen if the sources of information used by these tools were to become much more reliable. No improvements in the algorithms are going to help with that.

---

Two Heidelberg graduate students reject junk DNA

Science in School is a magazine for European science teachers. Two graduate students¹ have just published an article in the November issue: Not junk after all: the importance of non-coding RNAs.

Note: The article has been edited to remove some of the references to junk DNA and the editor has added the following disclaimer to the end of the article: Editor’s note: Some parts of the introduction and conclusion were rephrased to avoid any misunderstanding concerning the nature of ‘junk DNA’, which is not the focus of this article. Here's a link to the revised article: Not junk after all: the importance of non-coding RNAs. More changes are expected.

Not junk after all: the importance of non-coding RNAs

Originally assumed to be useless ‘junk DNA’, sections of the genome that don’t encode proteins have been revealed as a source of many important non-coding RNA structures.

The central dogma of molecular biology is that DNA is used as a template to create messenger RNA (mRNA), which in turn is translated into proteins that build the tissues in our bodies and carry out the main functions of our cells and organs. In other words, DNA → mRNA → proteins. Interestingly, though, only 2% of the DNA in our whole genome codes for proteins! So, what does the other 98% of the human genome do? In the mid-1900s, it was widely believed that a great part of our genome was useless, repetitive ‘junk DNA’. However, this belief goes against the evolution theory, which suggests that useless sequences would be eliminated from the genome since their maintenance requires energy. In the late 20th century and the early 21st century, this junk DNA has been shown to not only contain important regulatory elements for transcription, but also sequences that encode various non-coding RNAs that have functions in many cellular mechanisms.

I just finshed a podcast interview with Kat Arney and one of the questions she asked was what is the most important thing I'd like scientists to know about this topic. I picked evolution—I'd like modern researchers to understand that there's more to evolution than natural selection. You can see the problem in this example where two students who are working toward a Ph.D. at a top lab in Europe think that junk DNA "goes against the evolution theory."

That's sad. It's also sad that these two students think that 98% of our genome might be devoted to regulation and non-coding genes.

We need to focus on educating the next generation of scientists and that starts with educating science teachers. This is not the way to do it.

Here's the contact information for Science in School. I've written the editor at editor@scienceinschool.org. Please send a message if you are as concerned about the spread of scientific misinformation as I am.

---

Zuzana Koskova at the European Molecular Biology Laboratory in Heidelberg (Germany) and Miguel Hernandez at the University Hospital, Heidelberg. I tried sending an email message to Zuzana Koskova but got no reply. I was unable to find contact information for Miguel Hernandez.

ChatGPT is still making up quotations from scientists

I wondered whether ChatGPT had improved in the last six months so I asked it again about junk DNA. The answers reveal that ChatGPT is still lying and spreading false information.

What is junk DNA?

ChatGPT: "Junk DNA" is a term that was historically used to describe portions of the DNA sequence that do not code for proteins or have any known function. These non-coding regions were once thought to be vestiges of evolutionary processes or simply genetic "leftovers" with no apparent purpose.

However, it's important to note that the term "junk DNA" is now considered outdated and somewhat misleading. Advances in genomics and molecular biology have revealed that many non-coding regions of DNA have important functions, even if they do not encode proteins. These regions may contain regulatory elements that control the activity of genes, play a role in the three-dimensional structure of the genome, or have other functional significance.

The Human Genome Project and subsequent genomic research efforts have shown that a significant portion of the genome is involved in the regulation of gene expression, development, and other cellular processes. The term "non-coding DNA" or "non-coding regions" is now preferred over "junk DNA" to emphasize that these sections of the genome have functions that are not immediately apparent and are still an active area of research.

In summary, while some regions of the genome were once thought to be functionless "junk," ongoing scientific research is uncovering the complexity and functional significance of non-coding DNA.

So, the answer is "no," ChatGPT hasn't gotten any better. Even after we worked on a Wikipedia entry for junk DNA, ChatGPT is still responding with the standard non-scientific perspective on junk DNA. It implies that the term junk DNA originally meant all non-coding DNA and that the discovery of function in non-coding regions is due to recent advances in genomics and molecular biology.

I asked for some specific evidence that this was, indeed, the historical definition of junk DNA.

Can you give me some direct quotes from scientists who said that all non-coding DNA was junk?

ChatGPT: The idea that non-coding DNA was "junk DNA" was a historical perspective that gained traction in the early days of molecular biology when researchers primarily focused on protein-coding genes. It's important to note that while the term "junk DNA" was used, scientists were aware that there were likely unknown functions in non-coding regions. Over time, advances in genomics and molecular biology have revealed the complexity and functionality of non-coding DNA.

Here are a couple of historical quotes that reflect the perspective on non-coding DNA from earlier times:

Francis Crick (1970): In a 1970 paper, Francis Crick, one of the co-discoverers of the structure of DNA, stated, "The ultimate aim of the DNA investigators is to identify, with some precision, the genetic material. At present, it looks as if at least 90% of the DNA in any organism is useless."

Susumu Ohno (1972): Geneticist Susumu Ohno, in his book "Evolution by Gene Duplication" (1972), stated, "The failure to recognize this [the abundance of 'junk DNA'] for so long has misled the investigators studying the higher order chromosomal structure... No doubt the junk DNA sequences in the heterochromatin and at the centromeres are examples of 'selfish' DNA."

It's important to understand that these quotes represent a historical perspective, and scientific understanding has evolved significantly since then. The term "junk DNA" has since been reconsidered as researchers have discovered various functions within non-coding regions of the genome. Scientists today emphasize the importance of non-coding DNA in regulatory processes, genome stability, and other essential biological functions.

Neithe of these quotes support the idea that all non-coding DNA was thought to be junk. The direct quote from Crick in 1970 seems suspicious so I asked for clarification.

Can you supply the complete reference to the Francis Crick quotation that you just gave me?

ChatGPT: I apologize for any confusion, but I made an error in my previous response. After a thorough review, I couldn't find a direct quote from Francis Crick expressing the sentiment that "at least 90% of the DNA in any organism is useless." It appears there might have been a misunderstanding or misattribution in the information I provided.

Francis Crick and James Watson, in their groundbreaking work, were primarily focused on understanding the structure of DNA, and while there were discussions about non-coding regions, the notion of "junk DNA" as we understand it today wasn't explicitly articulated by Crick in the manner suggested.

I appreciate your diligence in seeking accurate information, and I apologize for any confusion caused by the error in my response. If you have any further questions or if there's anything else I can assist you with, please let me know.

The only way you would know that ChatGPT was making up direct quotations would be if you asked for confirmation. The average person would just assume that the fake quote was accurate. It would be fun to grade a student essay that used such a quotation!

When I asked these question last March, ChatGPT also made up false quotations that didn't even support it's claim that all non-coding DNA was thought to be junk [ChatGPT lies about junk DNA].

Can you supply the complete reference to the Susumu Ohno quotation that you just gave me?

ChatGPT: Certainly, Susumu Ohno's quote about "junk DNA" is attributed to his book "Evolution by Gene Duplication," published in 1970. I must clarify that the quote I provided earlier is a paraphrased version based on the general sentiment expressed in his work rather than an exact wording. Unfortunately, I couldn't locate the precise quote within the text.

If you're interested in exploring Ohno's thoughts on this matter in more detail, you may want to refer to his book "Evolution by Gene Duplication," which was influential in discussions about the evolutionary significance of gene duplication and, by extension, the role of non-coding DNA.

This is another example of a made-up quotation and it doesn't address the main issue. ChatGPT is unable to provide any evidence that all non-coding DNA was thought to be junk DNA.

The behavior of ChatGPT should be a major concern. If we are going to rely on artificial intelligence in the future then we better make sure that the information it gathers is correct.

---

The Purple Blog

Raphaël Champeimont has a blog called The Purple Blog: Freedom and Technology. His latest post is called The great Pufferfish Genome and it's well worth a read. Here's an excerpt ...

Human: I am the mighty human, pinnacle of the evolution: I have the most advanced and complex genome with 25,000 genes and an impressive 3 billion base pairs in my DNA, you know these letters like A, T, G, C which make my genome. 3 billion of them!

Pufferfish: Come on. Your genome is just full of junk, 90% of it is completely useless! It’s full of dead viruses that infected your ancestors long ago and you never cleaned it up. Look at my genome, I have just as many genes as you, but I don’t need to waste 3 billion base pairs of DNA for that, just 400 million is well enough. Yes, I pack as many genes as you in a genome 10 times smaller! That’s what I call optimization!

I met Raphaël a few months ago at a Café Scientific meeting in Mississauga, Ontario (Canada) and he came to our meeting last night. Turns out, he read my book and that's why he posted an article about genomes.

I recently read a very interesting new book “What's in Your Genome? 90% of Your Genome Is Junk” by Laurence A. Moran, in which he argues that our knowledge of genomics points to the fact that 90% of the human genome is useless junk.

This idea is not new, but it has become unfashionable in the last 20 years, without good evidence, the author argues. Most of our genome is still junk, and a central argument is that many other species don’t need that much DNA, or have much more without any “good” reason like the organism’s complexity.

I've lost count of how many people have read my book. I think this makes six or maybe seven!

---

Norman Johnson reviews my book in "Evolution" journal

A junk-filled genome
Review of: What’s In Your Genome? 90% of Your Genome Is Junk, by Laurence A. Moran, 2023. University of Toronto Press. 392 pp. ISBN: 9781487508593
Norman A Johnson
Evolution, qpad176, [10.1093/evolut/qpad176]

"The subject matter in this book is not easy. Molecular biologists might well be challenged by the population genetics theory, while the biochemistry details may vex evolutionary biologists. Moran does an excellent job at presenting both of these aspects. I am also glad that he provided a historical perspective, showing that many of the current debates have a long history.

In the Preface, Moran states that he was motivated to write this book in part due to what he views as failures in science communication regarding the nature of the genome. He reminds us about the importance of accuracy in science communication: “No matter how good your style, if the substance of what you are communicating is flawed, then you are not a good science communicator” (xiii). Narratives are useful in communicating science, but when they (or the hype) get in the way of telling the truth, the science, and the science communication suffer."

---

Stephen Meyer lies about scientists working on evolutionary theory

I know Stephen Meyer and I have discussed his views on creationism many times. Some of the issues he raises are quite interesting and they aren't easy to refute. In this video from 2020, he presents two standard creationist objections to evolution: the Cambrian explosion, and the probability of evolving a gene.¹

Only 10.7% of the human genome is conserved

The Zoonomia project aligned the genome sequences of 240 mammalian species and determined that only 10.7% of the human genome is conserved. This is consistent with the idea that about 90% of our genome is junk.

The April 28, 2023 issue of science contains eleven papers reporting the results of a massive study comparing the genomes of 240 mammalian species. The issue also contains a couple of "Perspectives" that comment on the work.

On the conservation of regulatory sites in the human genome

There are a million potential transcription regulatory sites in the human genome. How many of these function as true regulatory sites?

One of the important questions about the human genome concerns how gene expression is regulated. The main controversy is over the number of functional regulatory sites and how that relates to abundant junk DNA. Here's how one group addresses the problem by looking at the conservation of regulatory sites in mammals. Sequence conservation is best genomics proxy for identifying functional sites.

Andrews, G., Fan, K., Pratt, H.E., Phalke, N., Zoonomia Consortium, Karlsson, E.K., Lindblad-Toh, K., Gazal, S., Moore, J.E. and Weng, Z. (2023) Mammalian evolution of human cis-regulatory elements and transcription factor binding sites. Science 380:eabn7930. [doi: 10.1126/science.abn7930]

Understanding the regulatory landscape of the human genome is a long-standing objective of modern biology. Using the reference-free alignment across 241 mammalian genomes produced by the Zoonomia Consortium, we charted evolutionary trajectories for 0.92 million human candidate cis-regulatory elements (cCREs) and 15.6 million human transcription factor binding sites (TFBSs). We identified 439,461 cCREs and 2,024,062 TFBSs under evolutionary constraint. Genes near constrained elements perform fundamental cellular processes, whereas genes near primate-specific elements are involved in environmental interaction, including odor perception and immune response. About 20% of TFBSs are transposable element–derived and exhibit intricate patterns of gains and losses during primate evolution whereas sequence variants associated with complex traits are enriched in constrained TFBSs. Our annotations illuminate the regulatory functions of the human genome.

The authors introduce the issue by pointing out two different views of functional regulatory sites. First, there's the ENCODE view, which maps the binding sites of 1600 transcription factors and the associated methylation and histone modification patterns. This analysis creates a database of almost one million candidate cis-regulatory elements (cCREs). Second, there's the evolutionary perspective, which looks at conservation of regulatory sites as the prime indicator of function. Only a fraction of candidate sites are conserved. Does this mean that most of the cCREs are not functional?

Andrews et al. set out to identify all of the cCRE's and transcription factor binding sites (TFBSs) that show evidence of conservation using an alignment of 241 mammalian genomes from the Zoonomia database and a program called phyloP.

They began with more than 920,000 human cCREs from the ENCODE Consortium results. Their results indicate that 47.5% of all CREs are highly conserved because they align to almost all of the 240 non-human mammalian genomes. (I have no idea how the phyloP program calculates "conservation.") That means approximately 439,000 sites that are likely to be genuine regulatory sequences covering 4% of the human genome. If there are 25,000 genes then this means that each gene requires about 17 regulatory sequences.

The next step was to examine 15.6 million TFBSs with a median length of 10 bp covering 5.7% of the human genome. They classified 32.5% of these sequences as highly conserved using the mysterious phyloP program. That means about 5.1 million functional transcription factor binding sites, but later on they reduce this to 2 million covering 0.8% of the genome. This is equivalent to an average of 80 per gene.

I don't believe that the authors have identified functional sites. There is no critical analysis of the results or the methodology and no attempt to rationalize the extraordinary claim that every gene requires so many regulatory sites. About 10,000 genes are regular housekeeping genes, such as those encoding the standard metabolic enzymes, and it's difficult to imagine that those genes require such complex regulation.

---

Image credit: ©Laurence A. Moran, What's in Your Genome?, p. 289.