Nils Walter disputes junk DNA: (7) Conservation of transcribed DNA

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 and sixth posts address specific arguments in the junk DNA debate.

• Nils Walter disputes junk DNA: (1) The surprise
• Nils Walter disputes junk DNA: (2) The paradigm shaft
• Nils Walter disputes junk DNA: (3) Defining 'gene' and 'function'
• Nils Walter disputes junk DNA: (4) Different views of non-functional transcripts
• Nils Walter disputes junk DNA: (5) What does the number of transcripts per cell tell us about function?
• Nils Walter disputes junk DNA: (6) The C-value paradox

Sequence conservation

If you don't know what a transcript is doing then how are you going to know whether it's a spurious transcript or one with an unknown function? One of the best ways is to check and see whether the DNA sequence is conserved. There's a powerful correlation between sequence conservation and function: as a general rule, functional sequences are conserved and non-conserved sequences can be deleted without consequence.

There might be an exception to the the conservation criterion in the case of de novo genes. They arise relatively recently so there's no history of conservation. That's why purifying selection is a better criterion. Now that we have the sequences of thousands of human genomes, we can check to see whether a given stretch of DNA is constrained by selection or whether it accumulates mutations at the rate we expect if its sequence were irrelevant junk DNA (neutral rate). The results show that less than 10% of our genome is being preserved by purifying selection. This is consistent with all the other arguments that 90% of our genome is junk and inconsistent with arguments that most of our genome is functional.

This sounds like a problem for the anti-junk crowd. Let's see how it's addressed in Nils Walter's article in BioEssays.

There are several hand-waving objections to using conservation as an indication of function and Walter uses them all plus one unique argument that we'll get to shortly. Let's deal with some of the "facts" that he discusses in his defense of function. He seems to agree that much of the genome is not conserved even though it's transcribed. In spite of this, he says,

"... the estimates of the fraction of the human genome that carries function is still being upward corrected, with the best estimate of confirmed ncRNAs now having surpassed protein-coding genes,[12] although so far only 10%–40% of these ncRNAs have been shown to have a function in, for example, cell morphology and proliferation, under at least one set of defined conditions."

This is typical of the rhetoric in his discussion of sequence conservation. He seems to be saying that there are more than 20,000 "confirmed" non-coding genes but only 10%-40% of them have been shown to have a function! That doesn't make any sense since the whole point of this debate is how to identify function.

Here's another bunch of arguments that Walter advances to demonstrate that a given sequence could be functional but not conserved. I'm going to quote the entire thing to give you a good sense of Walter's opinion.

A second limitation of a sequence-based conservation analysis of function is illustrated by recent insights from the functional probing of riboswitches. RNA structure, and hence dynamics and function, is generally established co-transcriptionally, as evident from, for example, bacterial ncRNAs including riboswitches and ribosomal RNAs, as well as the co-transcriptional alternative splicing of eukaryotic pre-mRNAs, responsible for the important, vast diversification of the human proteome across ∼200 cell types by excision of varying ncRNA introns. In the latter case, it is becoming increasingly clear that splicing regulation involves multiple layers synergistically controlled by the splicing machinery, transcription process, and chromatin structure. In the case of riboswitches, the interactions of the ncRNA with its multiple protein effectors functionally engage essentially all of its nucleotides, sequence-conserved or not, including those responsible for affecting specific distances between other functional elements. Consequently, the expression platform—equally important for the gene regulatory function as the conserved aptamer domain—tends to be far less conserved, because it interacts with the idiosyncratic gene expression machinery of the bacterium. Consequently, taking a riboswitch out of this native environment into a different cell type for synthetic biology purposes has been notoriously challenging. These examples of a holistic functioning of ncRNAs in their species-specific cellular context lay bare the limited power of pure sequence conservation in predicting all functionally relevant nucleotides.

I don't know much about riboswitches so I can't comment on that. As for alternative splicing, I assume he's suggesting that much of the DNA sequence for large introns is required for alternative splicing. That's just not correct. You can have effective alternative splicing with small introns. The only essential parts of introns sequences are the splice sites and a minimum amount of spacer.

Part of what he's getting at is the fact that you can have a functional transcript where the actual nucleotide sequence doesn't matter so it won't look conserved. That's correct. There are such sequences. For example, there seem to be some examples of enhancer RNAs, which are transcripts in the regulatory region of a gene where it's the act of transcription that's important (to maintain an open chromatin conformation, for example) and not the transcript itself. Similarly, not all intron sequences are junk because some spacer sequence in required to maintain a minimum distance between splice sites. All this is covered in Chapter 8 of my book ("Noncoding Genes and Junk RNA").

Are these examples enough to toss out the idea of sequence conservation as a proxy for function and assume that there are tens of thousands of such non-conserved genes in the human genome? I think not. The null hypothesis still holds. If you don't have any evidence of function then the transcript doesn't have a function—you may find a function at some time in the future but right now it doesn't have one. Some of the evidence for function could be sequence conservation but the absence of conservation is not an argument for function. If conservation doesn't work then you have to come up with some other evidence.

It's worth mentioning that, in the broadest sense, purifying selection isn't confined to nucleotide sequence. It can also take into account deletions and insertions. If a given region of the genome is deficient in random insertions and deletions then that's an indication of function in spite of the fact that the nucleotide sequence isn't maintained by purifying selection. The maintenance definition of function isn't restricted to sequence—it also covers bulk DNA and spacer DNA.

(This is a good time to bring up a related point. The absence of conservation (size or sequence) is not evidence of junk. Just because a given stretch of DNA isn't maintained by purifying selection does not prove that it is junk DNA. The evidence for a genome full of junk DNA comes from different sources and that evidence doesn't apply to every little bit of DNA taken individually. On the other hand, the maintenance function argument is about demonstrating whether a particular region has a function or not and it's about the proper null hypothesis when there's no evidence of function. The burden of proof is on those who claim that a transcript is functional.)

This brings us to the main point of Walter's objection to sequence conservation as an indication of function. You can see hints of it in the previous quotation where he talks about "holistic functioning of ncRNAs in their species-specific cellular context," but there's more ...

Some evolutionary biologists and philosophers have suggested that sequence conservation among genomes should be the primary, or perhaps only, criterion to identify functional genetic elements. This line of thinking is based on 50 years of success defining housekeeping and other genes (mostly coding for proteins) based on their sequence conservation. It does not, however, fully acknowledge that evolution does not actually select for sequence conservation. Instead, nature selects for the structure, dynamics and function of a gene, and its transcription and (if protein coding) translation products; as well as for the inertia of the same in pathways in which they are not involved. All that, while residing in the crowded environment of a cell far from equilibrium that is driven primarily by the relative kinetics of all possible interactions. Given the complexity and time dependence of the cellular environment and its environmental exposures, it is currently impossible to fully understand the emergent properties of life based on simple cause-and-effect reasoning.

The way I see it, his most important argument is that life is very complicated and we don't currently understand all of it's emergent properties. This means that he is looking for ways to explain the complexity that he expects to be there. The possibility that there might be several hundred thousand regulatory RNAs seems to fulfil this need so they must exist. According to Nils Walter, the fact that we haven't (yet) proven that they exist is just a temporary lull on the way to rigorous proof.

This seems to be a common theme among those scientists who share this viewpoint. We can see it in John Mattick's writings as well. It's as though the logic of having a genome full of regulatory RNA genes is so powerful that it doesn't require strong supporting evidence and can't be challenged by contradictory evidence. The argument seems somewhat mystical to me. Its proponents are making the a priori assumption that humans just have to be a lot more complicated than what "reductionist" science is indicating and all they have to do is discover what that extra layer of complexity is all about. According to this view, the idea that our genome is full of junk must be wrong because it seems to preclude the possibility that our genome could explain what it's like to be human.

---

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 neutralist-selectionist debate in 2024

The neutral theory was first proposed by Mootoo Kimura in 1968 (Kimura, 1968). The following year, a similar idea was published in a seminal paper by Jack King and Thomas Jukes (King and Jukes, 1969). King and Jukes emphasized the importance of non-Darwinian mechanisms of evolution in order to explain protein based phylogenetic trees and the molecular clock. They made it clear that neutral alleles fixed by random genetic drift play an important part in evolution.

There appears to be considerable latitude at the molecular level for random genetic changes that have no effect upon the fitness of the organism. Selectively neutral mutations, if they occur, become passively fixed as evolutionary changes through the action of random genetic drift.

The idea of selectively neutral changes at the molecular level has not been readily accepted by many classical evolutionists, perhaps because of the pervasiveness of Darwinian thought (King and Jukes, 1969).

Why Philosophy of Biology?

Robert Lawrence Kuhn has published a series of videos on his "Closer to Truth" site. On March 4, 2024 he posted a teaser video introducing Season 23: "Why Philosophy of Biology." The video contains short clips of his interviews with philosophers of biology (see list below).

Here's the blurb covering the introduction to the new season.

How can philosophy advance biology? How can biology influence philosophy? In this first series on Philosophy of Biology, Closer to Truth explores the challenges and implications of evolution. We ask how life on earth came to be as it is, and how humans came to be as we are. We address biologically based issues, such as sex/gender, race, cognition, culture, morality, healthcare, religion, alien life, and more. When philosophy and biology meet, sparks fly as both are enriched.

Those are all interesting questions. Some of them can only be answered by philosophers but others require major input from scientists. One of the important issues for philosophy of science seems to be the confict between the philosophy of the early 20th century, which was developed with physics as the model science, and the the success of molecular biology in the latter half of the 20th century, which didn't play by the same rules. (See the short interview with Paul Griffiths, whom I greatly admire, for a succinct explanation of this problem.)

I'm very conflicted about the role of philosphy in understanding the science of biology and even more conflicted about whether philosophers can recognize good science from bad science (Richard Dawkins, Denis Noble). I'm also puzzled by the apparent reluctance of philosophers to openly challenge their colleagues who get the science wrong. Watch the video to see if my scepticism is warranted.

• Michael Ruse
• Elliot Sober
• Elisabeth Lloyd
• Peter Godfrey-Smith
• John Dupré
• Paul Griffiths
• Richard Dawkins
• Quayshawn Spencer
• Denis Noble
• Samir Okasha
• Massimo Pigliucci
• Alan Love
• Philip Kitcher

---

Nils Walter disputes junk DNA: (6) The C-value paradox

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/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.

• Nils Walter disputes junk DNA: (1) The surprise
• Nils Walter disputes junk DNA: (2) The paradigm shaft
• Nils Walter disputes junk DNA: (3) Defining 'gene' and 'function'
• Nils Walter disputes junk DNA: (4) Different views of non-functional transcripts
• Nils Walter disputes junk DNA: (5) What does the number of transcripts per cell tell us about function?

Nils Walter disputes junk DNA: (5) What does the number of transcripts per cell tell us about function?

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.

-Nils Walter disputes junk DNA: (1) The surprise

-Nils Walter disputes junk DNA: (2) The paradigm shaft

-Nils Walter disputes junk DNA: (3) Defining 'gene' and 'function'

-Nils Walter disputes junk DNA: (4) Different views of non-functional transcripts

Transcripts vs junk DNA

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]

Nils Walter disputes junk DNA: (4) Different views of non-functional transcripts

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.

-Nils Walter disputes junk DNA: (1) The surprise

-Nils Walter disputes junk DNA: (2) The paradigm shaft

-Nils Walter disputes junk DNA: (3) Defining 'gene' and 'function'

Nils Walter disputes junk DNA: (3) Defining 'gene' and 'function'

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.

-Nils Walter disputes junk DNA: (1) The surprise

-Nils Walter disputes junk DNA: (2) The paradigm shaft

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 disputes junk DNA: (2) The paradigm shaft

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 second post in the series. The first one outlines the issues that led to the current paper.

Nils Walter disputes junk DNA: (1) The surprise

Walter begins his defense of function by outlining a "paradigm shift" that's illustrated in Figure 1.

FIGURE 1: Assessment of the information content of the human genome ∼20 years before (left)[110] and after (right)[111] the Human Genome Project was preliminarily completed, drawn roughly to scale.[9] This significant progress can be described per Thomas Kuhn as a “paradigm shift” flanked by extended periods of “normal science”, during which investigations are designed and results interpreted within the dominant conceptual frameworks of the sub-disciplines.[9] Others have characterized this leap in assigning newly discovered ncRNAs at least a rudimentary (elemental) biochemical activity and thus function as excessively optimistic, or Panglossian, since it partially extrapolates from the known to the unknown.[75] Adapted from Ref. [9].

Reference #9 is a paper by John Mattick promoting a "Kuhnian revolution" in molecular biology. I've already discussed that paper as an example of a paradigm shaft, which is defined as a strawman "paradigm" set up to make your work look like revolutionary [John Mattick's new paradigm shaft]. Here's the figure from the Mattick paper.

The Walter figure is another example of a paradigm shaft—not to be confused with a real paradigm shift.¹ Both pie charts misrepresent the amount of functional DNA since they don't show regulatory sequences, centromeres, telomeres, origins of replication, and SARS. Together, these account for more functional DNA than the functional regions of protein-coding genes and non-coding genes. We didn't know the exact amounts in 1980 but we sure knew they existed. I cover this in Chapter 5 of my book: "The Big Picture."

The 1980 view also implies, incorrectly, that we knew nothing about the non-functional component of the genome when, in fact, we knew by then that half of our genome was composed of transposon and viral sequences that were likely to be inactive, degenerate fragments of once active elements. (John Mattick's figure is better.)

The 2020 view implies that most intron sequences are functional since introns make up more than 40% of our genome but only about 3% of the pie chart. As far as I know, there's no evidence to support that claim. About 80% of the pie chart is devoted to transcripts identified as either small ncRNAs or lncRNAs. The implication is that the discovery of these RNAs represents a paradigm shift in our understanding of the genome.

The alternative explanation is that we've known since the late 1960s that most of the human genome is transcribed and that these transcripts—most of which turned out to be introns—are junk RNA that is confined to the nucleus and rapidly degraded. Advances in technology have enabled us to detect many examples of spurious transcripts that are present transiently at low levels in certain cells. I cover this in Chaper 8 of my book: "Noncoding Genes and Junk RNA.

The whole point of Nils Walter's paper is to defend the idea that most of these transcripts are functional and the alternative explanation is wrong. He's trying to present a balanced view of the controversy so he's well aware of the fact that some of us interpret the red part of the pie chart as spurious transcripts (junk RNA). If he's wrong, and I am right, then there's no paradigm shift.

You don't get to shift the paradigm all on our own, even if John Mattick is on your side. A true paradigm shift requires that the entire community of scientists changes their perspective and that hasn't happened.

In the next few posts we'll see whether Nils Walter can make a strong case that all those lncRNAs are functional. They cover about two-thirds of the genome in the pie chart. If we assume that the average length of these long transcripts is 2000 bp then this represents one million transcripts and potentially one million non-coding genes.

---

1. The term "paradigm shaft" was coined by reader Diogenes in a comment on this blog from many years ago.

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]

Nils Walter disputes junk DNA: (1) The surprise

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.

How to end the war in Ukraine according to a Canadian Conservative "diplomat"

In my opinion, the war in Ukraine is much more complicated than most people realize. We are constantly bombarded with propaganda from all sides and it inhibits rational thinking. One of the few reliable facts is that Vladimir Putin is a very smart bad person.

Lots of people think they have the answer to ending the war in Ukraine. One of the latest pundits is Chris Alexander who has published his thoughts in the Feb. 16, 2024 edition of Canada's Globe and Mail: Ukraine is paying the price for our nonchalance toward Russia’s leadership. Alexander spent years in Canada's Foreign Service, including many years in Moscow and a stint as Canada's ambassador to Afghanistan. In 2011 he was elected to Parliament as a Conservative MP and served as Minister of Citizenship and Immigration in Stephen Harper's cabinet. His reputation as a politician was very different than his previous, mostly admirable, reputation as a diplomat. Here's a excerpt from his Wikipedia article.

Copilot answers the question, "What is junk DNA?"

The Microsoft browser (Edge) has a built in function called Copilot. It's an AI assistant based on ChatGPT-4.

I decided to test it byt asking "What is junk DNA?" and here's the answer it gave me.

Older but wiser?

With age comes wisdom, but sometimes age comes alone.

Oscar Wilde

Like many baby boomers, I sometimes forget people's names and other important bits of information. Sometimes I can't find a word that's been in my vocabulary for decades. These lapses are often temporary but very annoying. It's a sign of age. (I am 77 years old.)

We often make fun of these incidents and consol ourselves with the knowledge that we may be old but we are much wiser than we were in our younger days. We have years and years of experience behind us and over the years we've learned a thing or two that we never understood when we were listening to the Beatles on the radio. We've lived through the Cuban Missile crisis, the war in Viet Nam, the assassination of two Kennedys and Martin Luther King, and a host of cultural changes. We've lived in several different countries and we've raised children. All of these experiences have made us wiser, or so we think.

Open and closed chromatin domains (and epigenetics)

Gene expression in eukaryotes is influenced by the state of chromatin. Tightly packed nucleosomes inhibit the binding of transcription factors and RNA polymerase so that genes in these regions are "repressed." From time to time these regions loosen up a bit allowing access to transcription complexes and subsequent transcription.

The tightly packed regions are known as closed domains and the accessible regions are open domains. Some authors add an intermediate domain called a permissive domain. This model of eukaryotic gene expression has been around for 50 years and the important mechanisms controlling the switch were worked out in the 1980s. I found a recent review that covers this issue in the context of epigenetics and the image below comes from that paper (Klemm et al., 2019).

Philip Ball's new book: "How Life Works"

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.

"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.

The number of splice variants in a species correlates inversely with the population size - what does that mean?

Most of the genes in eukaryotes contain introns that are removed by splicing during processing of the primary transcript. In some cases the gene produces two different functional RNAs due to differential splicing of the introns. If the product is mRNA then two different versions of the protein can be made as shown in the figure from my book What's in Your Genome? This mechanism is known as alternative splicing.

True alternative splicing is rare—less than 5% of all genes are alternatively spliced.¹ However, when you analyze all of the transcripts in a tissue you will invariably detect many transcripts from junk DNA and many low abundance splice variants. Those transcripts and splice variants are due to transcription errors and splicing errors. Splicing errors arise from the presence of weak splice sites that are occasionally recognized by the normal spliceosome or by the splice factors responsible for true alternative splicing.

How many genes in the human genome (2023)?

The latest summary of the number of genes in the human genome gets the number of protein-coding genes correct but their estimate of the number of known non-coding genes is far too high.

In order to have a meaningful discussion about molecular genes, we have to agree on the definition of a molecular gene. I support the following definition (see What Is a Gene?).

Intelligent Design Creationism and irreducible complexity

Jonathan McLatchie is an Intelligent Design Creationist who now blogs frequently on the Discovery website Evolution News [sic]. His latest post is How NOT to Argue Against Irreducible Complexity where he defends the claim that the human male reproductive apparatus is irreducibly complex and therefore must be a product of intelligent design.

You can read the post yourself to see how ID proponents argue. I want to make another point.

McLatchie thinks that the irreducible complexity argument is very powerful evidence for intelligent design. He writes,

The argument from irreducible complexity against evolution and for design has always held strong intuitive appeal for me, and it has hence become my argument of choice in discussions about the scientific merits of evolution versus design.

Let's look at the logic of the argument from irreducible complexity. Assume that we have identified a structure that's irreducibly complex. There are three possible ways to deal with its origin.

1. There is a plausible naturalistic explanation for the evolution of the irreducibly complex structure.
2. There is currently no detailed naturalistic explanation that accounts for the evolution of the irreducibly complex structure.
3. It is impossible for there to ever be a naturalistic explanation; therefore, god did it.

We know that there are good naturalistic explanations for the evolution of irreducibly complex structures. In fact, McLatchie mentions some of them that refuted his earlier claims. Behe has also backed off some of his claims in light of evidence that irreducibly complex structures can evolve without the help of god(s). This establishes that the mere existence of an irreducibly complex structure is not evidence for intelligent design.

Here's how Behe explains it on page 40 of Darwin's Black Box.

Even if a system is irreducibly complex (and thus cannot have been produced directly), however, one cannot definitively rule out the possibility of an indirect, circuitous route.

In some cases there is currently no good naturalistic explanation for the evolution of an irreducibly complex structure. This could be due to a real difficulty in coming up with a plausible scenario or it could be due to the fact that no scientist has bothered to do the investigation required because they don't care. In either case, the current lack of an explanation is not, in itself, evidence for an intelligent designer.

The third possibility is the one that counts. If you can prove that a naturalistic explanation is impossible then there must be a non-naturalistic explanation such as aliens, or god(s). McLatchie says the the sperm flagellum is irreducibly complex and that he cannot imagine how it could have evolved naturally. According to creationist logic, it follows that some alien, or some god, must have designed the original sperm flagellum.

McLatchie won't tell us when this happened or why the intelligent designer was so interested in sperm, but that's typical of Intelligent Design Creationsts—they require detailed explanations from scientists but not from their fellow creationists.

• Jonathan McLatchie explains irreducible complexity
• The science behind Intelligent Design Creationism
• The meaning of "irreducible complexity"
• A Torley Defense of Irreducible Complexity
• Barry Arrington Explains Irreducible Complexity
• Irreducible Complexity

---