Intelligent Design Creationists are heavily invested in refuting junk DNA because it casts doubt on their model of an intelligently designed human. Over the years they have advanced all kinds of arguments against junk DNA and some ID supporters actually address the real scientific issues (e.g. Jonathan Wells). However, most Intelligent Design Creationists are as ignorant about the scientific dispute over junk DNA as they are about evolution and lots of other science issues that conflict with their underlying religious beliefs.
A few days ago (March 26, 2024), the Discovery Institute's Center for Science and Culture published a short video on "The MYTH of Junk DNA" where they ignored most of the science and appealed to the majority of creationists who don't care about the truth. We have enough data to conclude that the Discovery Institute isn't just ignorant of the real science but is actually lying in this video. We know this because there are prominent Senior Fellows of the Center for Science and Culture who know that the material in this video is wrong and/or mispleading.
Should universities remove online courses that contain incorrect or misleading information?
There are lots of scientific controversies where different scientists have conflicting views. Eventually these controversies will be solved by normal scientific means involving evidence and logic but for the time being there isn't enough data to settle a genuine scientific controversy. Many of us are interested in these controversies and some of us have chosen to invest time and effort into defending one side or the other.
But there's a dark side of science that infects these debates—false or misleading information used to support one side of a legitimate controversy. To give just one example, I'm frustrated at the constant reference to junk DNA being defined as non-coding DNA. Many scientists believe that this was the way junk DNA was defined by its earliest proponents and then they go on to say that the recent discovery of functional non-coding DNA refutes junk.
I don't know where this idea came from because there's nothing in the scientific literature from 50 years ago to support such a ridiculous claim. It must be coming from somewhere since the idea is so widespread.
Where does misinformation come from and how is it spread?
Paul Nelson is a Senior Fellow of the Discovery Institute—the most important source of intelligent design propaganda. Paul and I have been disagreeing about science for many years. He is prone to interpret anything he finds in the scientific literature as support for the idea that scientists have misunderstood their subject matter and failed to recognize that science supports intelligent design. My goal has always been to try and explain the actual science and why his interpretations are misguided. I have not been very successful.
The photo was taken in London (UK) in 2016 at a meeting on evolution. It looks like I'm holding my breath because I'm beside a creationist but I assure you that's not what was happening. We actually get along quite well in spite of the fact that he's wrong about everything. :-)
I'm discussing a recent paper published by Nils Walter (Walter, 2024). He is arguing against junk DNA by claiming that the human genome contains large numbers of non-coding genes.
This is the seventh post in the series. The first one outlines the issues that led to the current paper and the second one describes Walter's view of a paradigm shift/shaft. The third post describes the differing views on how to define key terms such as 'gene' and 'function.' In the fourth post I discuss his claim that differing opinions on junk DNA are mainly due to philosophical disagreements. The fifth, sixth, and seventh posts address specific arguments in the junk DNA debate.
I'm discussing a recent paper published by Nils Walter (Walter, 2024). He is arguing against junk DNA by claiming that the human genome contains large numbers of non-coding genes.
This is the fifth post in the series. The first one outlines the issues that led to the current paper and the second one describes Walter's view of a paradigm shift. The third post describes the differing views on how to define key terms such as 'gene' and 'function.' The fourth post makes the case that differing views on junk DNA are mainly due to philosophical disagreements.
The most important issue, according to Nils Walter, is whether the human genome contains huge numbers of genes for lncRNAs and other types of regulatory RNAs. He doesn't give us any indication of how many of these potential genes he thinks exist or what percentage of the genome they cover. This is important since he's arguing against junk DNA but we don't know how much junk he's willing to accept.
There are several hundred thousand transcripts in the RNA databases. Most of them are identified as lncRNAs because they are bigger than 200 bp. Let's assume, for the sake of argument, that 200,000 of these transcripts have a biologically relevant function and therefore there are 200,000 non-coding genes. A typical size might be 1000 bp so these genes would take up about 6.5% of the genome. That's about 10 times the number of protein-coding genes and more than 6 times the amount of coding DNA.
That's not going to make much of a difference in the junk DNA debate since proponents of junk DNA argue that 90% of the genome is junk and 10% is functional. All of those non-coding genes can be accommodated within the 10%.
The ENCODE researchers made a big deal out of pervasive transcription back in 2007 and again in 2012. We can quibble about the exact numbers but let's say that 80% of the human is transcribed. We know that protein-coding genes occupy at least 40% percent of the genome so much of this pervasive transcription is introns. If all of the presumptive regulatory genes are located in the remaining 40% (i.e. none in introns), and the average size is 1000 bp, then this could be about 1.24 million non-coding genes. Is this reasonable? Is this what Nils Walter is proposing?
I think there's some confusion about the difference between large numbers of functional transcripts and the bigger picture of how much total junk DNA there is in the human genome. I wish the opponents of junk DNA would commit to how much of the genome they think is functional and what evidence they have to support that position.
But they don't. So instead we're stuck with debates about how to decide whether some transcripts are functional or junk.
What does transcript concentration tell us about function?
If most detectable transcripts are due to spurious transcription of junk DNA then you would expect these transcripts to be present at very low levels. This turns out to be true as Nils Walter admits. He notes that "fewer than 1000 lncRNAs are present at greater than one copy per cell."
This is a problem for those who advocate that many of these low abundance transcripts must be functional. We are familiar with several of the ad hoc hypotheses that have been advanced to get around this problem. John Mattick has been promoting them for years [John Mattick's new paradigm shaft].
Walter advances two of these excuses. First, he says that a critical RNA may be present at an average of one molecule per cell but it might be abundant in just one specialized cell in the tissue. Furthermore, their expression might be transient so they can only be detected at certain times during development and we might not have assayed cells at the right time. I assume he's advocating that there might be a short burst of a large number of these extremely specialized regulatory RNAs in these special cells.
As far as I know, there aren't many examples of such specialized gene expression. You would need at least 100,000 examples in order to make a viable case for function.
His second argument is that many regulatory RNAs are restricted to the nucleus where they only need to bind to one regulatory sequence to carry out their function. This ignores the mass action laws that govern such interactions. If you apply the same reasoning to proteins then you would only need one lac repressor protein to shut down the lac operon in E. coli but we've known for 50 years that this doesn't work in spite of the fact that the lac repressor association constant shows that it is one of the tightest binding proteins known [DNA Binding Proteins]. This is covered in my biochemistry textbook on pages 650-651.1
If you apply the same reasoning to mammalian regulatory proteins then it turns out that you need 10,000 transcription factor molecules per nucleus in order to ensure that a few specific sites are occupied. That's not only because of the chemistry of binary interactions but also because the human genome is full of spurious sites that resemble the target regulatory sequence [The Specificity of DNA Binding Proteins]. I cover this in my book in Chapter 8: "Noncoding Genes and Junk RNA" in the section titled "On the important properties of DNA-binding proteins" (pp. 200-204). I use the estrogen receptor as an example based on calculations that were done in the mid-1970s. The same principles apply to regulatory RNAs.
This is a disagreement based entirely on biochemistry and molecular biology. There aren't enough examples (evidence) to make the first argument convincing and the second argument makes no sense in light of what we know about the interactions between molecules inside of the cell (or nucleus).
Note: I can almost excuse the fact that Nils Walter ignores my book on junk DNA, my biochemistry textbook, and my blog posts, but I can't excuse the fact that his main arguments have been challenged repeatedly in the scientific literature. A good scientist should go out of their way to seek out objections to their views and address them directly.
1. In addition to the thermodynamic (equilibrium) problem, there's a kinetic problem. DNA binding proteins can find their binding sites relatively quickly by one dimensional diffusion—an option that's not readily available to regulatory RNAs [Slip Slidin' Along - How DNA Binding Proteins Find Their Target].
Walter, N.G. (2024) Are non‐protein coding RNAs junk or treasure? An attempt to explain and reconcile opposing viewpoints of whether the human genome is mostly transcribed into non‐functional or functional RNAs. BioEssays:2300201. [doi: 10.1002/bies.202300201]
I'm discussing a recent paper published by Nils Walter (Walter, 2024). He is trying to explain the conflict between proponents of junk DNA and their opponents. His main focus is building a case for large numbers of non-coding genes.
This is the third post in the series. The first one outlines the issues that led to the current paper and the second one describes Walter's view of a paradigm shift. The third post describes the differing views on how to define key terms such as 'gene' and 'function.' In this post I'll describe the heart of the dispute according to Nils Walter.
I'm discussing a recent paper published by Nils Walter (Walter, 2024). He is trying to explain the conflict between proponents of junk DNA and their opponents. His main focus is building a case for large numbers of non-coding genes.
This is the third post in the series. The first one outlines the issues that led to the current paper and the second one describes Walter's view of a paradigm shift.
Any serious debate requires some definitions and the debate over junk DNA is no exception. It's important that everyone is on the same page when using specific words and phrases. Nils Walter recognizes this so he begins his paper with a section called "Starting with the basics: Defining 'function' and 'gene'."
Nils Walter attempts to present the case for a functional genome by reconciling opposing viewpoints. I address his criticisms of the junk DNA position and discuss his arguments in favor of large numbers of functional non-coding RNAs.
Nils Walter is Francis S. Collins Collegiate Professor of Chemistry, Biophysics, and Biological Chemistry at the University of Michigan in Ann Arbor (Michigan, USA). He works on human RNAs and claims that, "Over 75% of our genome encodes non-protein coding RNA molecules, compared with only <2% that encodes proteins." He recently published an article explaining why he opposes junk DNA.
Walter, N.G. (2024) Are non‐protein coding RNAs junk or treasure? An attempt to explain and reconcile opposing viewpoints of whether the human genome is mostly transcribed into non‐functional or functional RNAs. BioEssays:2300201. [doi: 10.1002/bies.202300201]
The human genome project's lasting legacies are the emerging insights into human physiology and disease, and the ascendance of biology as the dominant science of the 21st century. Sequencing revealed that >90% of the human genome is not coding for proteins, as originally thought, but rather is overwhelmingly transcribed into non-protein coding, or non-coding, RNAs (ncRNAs). This discovery initially led to the hypothesis that most genomic DNA is “junk”, a term still championed by some geneticists and evolutionary biologists. In contrast, molecular biologists and biochemists studying the vast number of transcripts produced from most of this genome “junk” often surmise that these ncRNAs have biological significance. What gives? This essay contrasts the two opposing, extant viewpoints, aiming to explain their basis, which arise from distinct reference frames of the underlying scientific disciplines. Finally, it aims to reconcile these divergent mindsets in hopes of stimulating synergy between scientific fields.
Philip Ball has just published a new book "How Life Works." The subtitle is "A User’s Guide to the New Biology" and that should tell you all you need to know. This is going to be a book about how human genomics has changed everything.
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.
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.
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 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.
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.
Evelyn Fox Keller died a few days ago (Sept. 22, 2023). She was a professor of History and Philosopher of Science at the Massachusetts Institute of Technology (Boston, MA, USA). Most of the obituaries praise her for her promotion of women scientists and her critiques of science as a male-dominated discipline. More recently, she turned her attention to molecular biology and genomics and many philosophers (and others) seem to think that she made notable contributions in that area as well.
This is a video of a debate that took place in Kraków, Poland on June 2, 2023. The topic was "Intelligent design in nature—illusion or reality?" (Spoiler alert! - the answer is "illusion.") The participants were Michael Behe and Richard v. Sternberg for the creationists and Michael Ruse and Malgorzata Moczydlowska-Vidal for the science/philosophy side. The video is almost three hours long and I don't recommend watching the whole thing.
Ruse, as usual, is incoherant and more focused on religion and telling Christians how they should behave. The Polish paleontologist didn't do a very good job of addressing the claims of the creationists.1 Michael Behe gave his standard pitch about irreducible complexity and the bacterial flagellum.
The interesting part was Sternberg's defense of intelligent design. I hadn't seen him before although I've been familiar with his writings over the past twenty years. His opening presentation begins at 17:50 and it's worth watching to see how important the junk DNA debate is to the ID crowd.
Sternberg begins by noting that he was skeptical of the arguments put forward by Richard Dawkins in "The Selfish Gene" where Dawkins says that 98% of our DNA is noncoding junk. (Dawkins never said any such thing!) Sternberg says that when he started looking for function in this part of the genome he found that it was replete with function. Then he brings up the ENCODE results and claims that they challenged the concept of a gene (not true). Sternberg says that the new definition of a gene is that it is polyfunctional and "constantly changing in real time." He says,
... how can you have a theory based on an entity that you cannot define and how can you discuss the evolution of something that is kind of this amorphous notion ...
Sternberg seems to think that redefining the gene shows that evolutionary biology is out of touch with reality. He claims that the discovery of the epigenome is futher evidence that there are multiple layers of information that take us far beyond the theory of neo-Darwinism that was crafted in the nineteen teens and the 1920s.
Sternberg reflects the views of many Intelligent Design Creationists who tout the "debunking" of junk DNA as one of their greatest intellectual achievements because they predicted all along that there couldn't be large amounts of junk DNA in our genome because that's incompatible with intelligent design. What's different in the case of Richard Sternberg is that the discovery of function in most of our genome is what led him to the position that design is the best explanation.
I find it strange that Intelligent Design Creationists are relying so heavily on the so-called debunking of junk DNA, especially since in Sternberg's case he is well aware of the fact that some prominent scientists have criticized ENCODE. It's a risky strategy to put so much emphasis on a result that may turn out to be wrong. If our genome is mostly junk DNA (it is!) then the major part of their argument for design falls apart.
From reading the ID literature, it seems that they are supremely confident that most of our genome will turn out to be full of function. It will be interesting to see how they respond when the scientific community concludes that 90% of our genome is junk. From my perspective, they are digging themselves into a deep hole that will be very difficult to climb out of. Maybe it's time to stop digging?
Sternberg made one quip that's worth highlighting. At about 1:46:20 he talks about a saying that he learned in the air force; you don't receive flak unless you're over a significant target. That's cute. He uses it to explain why intelligent design is coming under such heavy attack. He is, of course, correct. When you drop bombs on people you can expect them to get upset. When you attack some of the most important concepts in science you can expect some pushback. That doesn't mean your bombing is justified. If it were justified then scientists would embrace your criticisms instead of shooting them down.
Sternberg scores big at 2:51:11 when he asks, "Can there be Darwinian evolution ... or any evolution in general, without natural selection?" The correct answer is yes. Malgorzata Moczydlowska-Vidal says no and so does Michael Ruse. Ruse then goes on to explain why he dismisses random genetic drift. Sternberg then explains neutral evolution and Michael Lynch's drift-barrier hypothesis and why some biologists use them to explain some of the ID challenges. Sternberg (and Behe) appear to know more about evolution than their opponents.
1. She concentrated on presenting evidence for the history of life but both Behe and Sternberg accept common descent and the correct age of the Earth.
John Mattick continues to promote the idea that he is leading a paradigm shift in molecular biology. He believes that he and his colleagues have discovered a vast world of noncoding genes responsible for intricate gene regulation in complex eukaryotes. The latest salvo was fired a few months ago in June 2023.
Mattick, J.S. (2023) A Kuhnian revolution in molecular biology: Most genes in complex organisms express regulatory RNAs. BioEssays:2300080. [doi: 10.1002/bies.202300080]
Thomas Kuhn described the progress of science as comprising occasional paradigm shifts separated by interludes of ‘normal science’. The paradigm that has held sway since the inception of molecular biology is that genes (mainly) encode proteins. In parallel, theoreticians posited that mutation is random, inferred that most of the genome in complex organisms is non-functional, and asserted that somatic information is not communicated to the germline. However, many anomalies appeared, particularly in plants and animals: the strange genetic phenomena of paramutation and transvection; introns; repetitive sequences; a complex epigenome; lack of scaling of (protein-coding) genes and increase in ‘noncoding’ sequences with developmental complexity; genetic loci termed ‘enhancers’ that control spatiotemporal gene expression patterns during development; and a plethora of ‘intergenic’, overlapping, antisense and intronic transcripts. These observations suggest that the original conception of genetic information was deficient and that most genes in complex organisms specify regulatory RNAs, some of which convey intergenerational information.
This paper is promoted by a video in which he explains why there's a Kuhnian revolution under way. This paper differs from most of his others on the same topic because Mattick now seems to have acquired some more knowledge of the mutation load argument and the neutral theory of evolution. Now he's not only attacking the so-called "protein centric" paradigm but also the Modern Synthesis. Apparently, a slew of "anomalies" are casting doubt on several old paradigms.
This is still a paradigm shaft but it's a bit more complicated than his previous versions (see: John Mattick's paradigm shaft). Now his "anomalies" include not only large numbers of noncoding genes but also the C-value paradox, repetitive DNA, introns, enhancers, gene silencing, the g-value enigma, pervasive transcription, transvection, and epigenetics. Also, he now seems to be aware of many of the arguments for junk DNA but not so aware that he can reference any of his critics.1 His challenges to the Modern Synthesis include paramutation which, along with epigenetics, violate the paradigm of the Moden Synthesis because of non-genetic inheritance.
But the heart of his revolution is still the discovery of massive numbers of noncoding genes that only he and a few of his diehard colleague can see.
The genomic programming of developmentally complex organisms was misunderstood for much of the last century. The mammalian genome harbors only ∼20 000 protein-coding genes, similar in number and with largely orthologous functions as those in other animals, including simple nematodes. On the other hand, the extent of non-protein-coding DNA increases with increasing developmental and cognitive complexity, reaching 98.5% in humans. Moreover, high throughput analyses have shown that the majority of the mammalian genome is differentially and dynamically transcribed during development to produce tens if not hundreds of thousands of short and long non-protein-coding RNAs that show highly specific expression patterns and subcellular locations.
The figure is supposed to show that by 2020 junk DNA had been eliminated and almost all of the mammalian genome is devoted to functional DNA—mostly in the form of noncoding genes. There's only one very tiny problem with this picture—it's not supported by any evidence that all those functional noncoding genes exist. This is still a paradigm shaft of the third kind (false paradigm, false overthrow, false data).
1. There are 124 references; Dawkins and ENCODE make the list along with 14 of his own papers. Most of the papers in my list of Required reading for the junk DNA debate are missing. The absence of Palazzo and Gregory (2023) is particularly noteworthy.
Paradigm shifts are rare but paradigm shafts are common. A paradigm shaft is when a scientist describes a false paradigm that supposedly ruled in the past then shows how their own work overthrows that old (false) paradigm.1 In many cases, the data that presumably revolutionizes the field is somewhat exaggerated.
John Mattick's view of eukaryotic RNAs is a classic example of a paradigm shaft. At various times in the past he has declared that molecular biology used to be dominated by the Central Dogma, which, according to him, supported the concept that the only function of DNA was to produce proteins (Mattick, 2003; Morris and Mattick, 2014). More recently, he has backed off this claim a little bit by conceding that Crick allowed for functional RNAs but that proteins were the only molecules that could be involved in regulation. The essence of Mattick's argument is that past researchers were constrained by adherance to the paradigm that the only important functional molecules were proteins and RNA served only an intermediate role in protein synsthesis.
There's something called "the EDIT lab blog" written by people at King's College In London (UK). Here's a recent post (May 19, 2023) that was apparently written by a Ph.D. student: J for Junk DNA Does Not Exist!.
It begins with the standard false history,
The discovery of the structure of DNA by James Watson and Francis Crick in 1953 was a milestone in the field of biology, marking a turning point in the history of genetics (Watson & Crick, 1953). Subsequent advances in molecular biology revealed that out of the 3 billion base pairs of human DNA, only around 2% codes for proteins; many scientists argued that the other 98% seemed like pointless bloat of genetic material and genomic dead-ends referred to as non-coding DNA, or junk DNA – a term you’ve probably come across (Ohno, 1972).
You all know what's coming next. The discovery of function in non-coding DNA overthrew the concept of junk DNA and ENCODE played a big role in this revolution. The post ends with,
Nowadays, researchers are less likely to describe any non-coding sequences as junk because there are multiple other and more accurate ways of labelling them. The discussion over non-coding DNA’s function is not over, and it will be long before we understand our whole genome. For many researchers, the field’s best way ahead is keeping an open mind when evaluating the functional consequences of non-coding DNA and RNA, and not to make assumptions about their biological importance.
As Sandwalk readers know, there was never a time when knowledgeable scientists said that all non-coding DNA was junk. They always knew that there was functional DNA outside of coding regions. Real open-minded scientists are able to distinguish between junk DNA and non-coding DNA and they are able to evaluate the evidence for junk DNA without dismissing it based on a misunderstanding of the history of the subject.
The question is why would a Ph.D. student who makes the effort to write a blog post on junk DNA not take the time to read up on the subject and learn the proper definition of junk and the actual evidence? Why would their supervisors and other members of the lab not know that this post is wrong?
