Primeval chronometers vs. Darwinism

 Epigenetic Biotimer Revealed in Flowers

David Coppedge 

Biology should never be considered ordinary. Take almost any biological process, and the details are likely to overwhelm the reader. That is certainly the case with a new paper about flowering in plants. Even in the well-studied lab plant Arabidopsis thaliana, researchers described dozens of genes, proteins, and accessory molecules working together to ensure the proper moment for flowering.

The paper in Plant Cell is difficult to read for laymen, because geneticists have given very odd names to genes and proteins. Then, according to custom, some genes for A. thaliana are written in italics, but other genes and their protein products are italicized in ALL CAPS. One must wade through a jungle of names like KNUCKLES, GIANT KILLER, SPOROCYTLESS, DEFECTIVE ANTHER DEHISCIENCE1, and AT HOOK MOTIF NUCLEAR LOCALIZED PROTEIN18. After first mention in a paper, fortunately, these are usually abbreviated to KNU, GKI, SPL, and so forth, but then it is hard to remember what they do, especially when they all interact in complex ways. 

Complexifying the situation further, the nomenclature rules have changed over time and are not consistent between publications. Some letters are not capitalized, and some have a suffix consisting of letters and numbers to identify a particular allele. There are also rules for mutant forms and wild type forms. The rules may seem like a mess to non-specialists (read about them at Arabidopsis.org), but I suppose the strange mnemonic names are more helpful than hard-to-memorize strings like g2934ab0x or worse (although rules for epigenetic marks are less mnemonic, like H3K27me3 (“histone 3, lysine 27, methyl group 3”). For this reason, I will try to refrain from referring to the labels and focus instead on processes and functions that go on, which are truly amazing.

The Basics

In a nutshell, scientists at the Nara Institute of Science and Technology (NAIST) in Japan identified key genes, proteins, and epigenetic factors that switch on flowering with precision timing. So accurate was the “biotimer” they found, they could predict when flowering would occur, even if they altered some of the components. They created mutants of some components, and with a mathematical model they designed, they could calculate to the day when an apical meristem (i.e., the tip of a growing stem) would switch its stem cells from proliferation mode to differentiation mode and start to grow the parts of the flower. The precision astonished them. Phys.org says,

The intricate process of flower development has long fascinated scientists seeking to unravel the mysteries behind nature’s precision timing. In a study published in the journal The Plant Cell, a research team led by Nara Institute of Science and Technology (NAIST), Japan has shed light on the inner workings of floral meristem termination and stamen development, uncovering a unique mechanism driven by the interplay of genetic and epigenetic factors.

In Southern California where I live, everyone is thrilled when the poppies bloom. Vast acres of the plants bloom together in late March or early April, as if on cue, painting whole valleys and hillsides in golden orange. The flowers can also close up if the temperature drops or the wind blows and then reopen when the sun shines warmly again. How do they do it? In every part of the world, plants show remarkable timing in their flowering: cherry blossoms in Washington DC, tulips in Holland, daylilies in Taiwan. Their secrets remain mysterious. In California, everyone thought the heavy winter rains would yield a poppy superbloom, but it was only modest compared to those of past years during the drought. Somehow, plants sense just the right combination of external cues to put on their best show.

To unlock the secrets of this remarkable system, the researchers devised a mathematical model capable of predicting gene expression timing with astonishing accuracy. By modifying the length of H3K27me3-marked regions within the genes, they successfully demonstrated that gene activation could be delayed or reduced, confirming the influence of this epigenetic timer. The team’s findings offer a novel perspective on how nature controls the gene expression during flower development.

The Histone Code

The story revolves around epigenetic markers on the genes of the A. thaliana stem cells. Over twenty years ago, David Allis (1951-2023) introduced a bold concept: there was another code at work in the genome: a combinatorial regulatory system. In its obituary, Nature Genetics says,

Perhaps Allis’s most famous conceptual contribution to the field of chromatin research was the elaboration of the ‘histone code’ hypothesis more than 20 years ago. This framework suggested that histone post-translational modifications (PTMs), in different combinations, along with the proteins that can ‘write’, ‘read’ or ‘erase’ them, constitute the basis for a gene regulatory code. In other words, certain histone PTMs could label particular chromatin regions and potentially influence their transcriptional activity. Many of these histone PTMs have been used extensively to characterize or infer a cell state, identity and behavior. For example, methylation marks at H3K27 and H3K9 are mostly associated with gene repression, whereas others, such as H3K4 methylation and H3K27 acetylation, are associated with active regulatory regions.

And so it is in A. thaliana, the authors of the current paper show. The genetic code has the blueprint to make the parts; the epigenetic “histone code” has the switch and the timer.

How It Works

The biotimer described in the paper works by a process of “passive dilution” that is cell cycle dependent. The normal condition for the AGAMOUS transcription factor is to repress flowering. This factor, abbreviated AG, is studded with histone markers (H3K27me3) which repress multiple genes required for “floral meristem termination,” the term for the switch to flowering. Stem cells will proliferate (divide) endlessly by mitosis until the switch is thrown to stop making clones of themselves and start differentiating into stamens, pistils, and petals. It reminds me of Paul Nelson’s comment about chicken egg development in the documentary Flight, where he describes how certain cells in the embryo “are committing themselves, in most cases irreversibly, to particular functional roles.”

For flowers to form, the floral meristem (floral stem cells) must irreversibly commit to becoming cells making up the various floral organs (sepals, petals, stamens, and carpels), a process known as floral meristem termination. Proper timing of floral meristem termination involves temporal activation of the transcription factor gene KNUCKLES (KNU) by its upstream regulator AGAMOUS (AG) via cell cycle-dependent dilution of the repressive histone modification at lysine 27 of histone H3 (H3K27me3) along the KNU coding sequence. This intrinsic ‘biotimer’ will activate KNU at precisely the right time to ensure proper flower development.

Passive dilution involves the washing out of the histone markers at each cell division. AG evicts PRC2, a histone methylator, and prevents histone H3 marks on nucleosomes. If a cell has six of these repressive markers at the beginning, the daughter cells will have three after the next cell division. At some point, there will not be enough markers to repress differentiation, and the cell will commit irreversibly to floral meristem termination. By inserting values into their mathematical model of this passive dilution mechanism, they were able to accurately predict when a plant in the lab would commence flowering. They validated the model with mutant forms of the genes, either speeding up or slowing down this mechanistic “countdown timer” operated by the epigenetic code. When one protein was activated too early, it produced short stamens that were sterile. This shows that attention to timing between parts of the system is crucial to successful flower development.

Interestingly, the biotimer was also temperature dependent. The team grew some of the plants at 18°C (64° F) instead of the usual 22° C (72° F) and observed that flowering was delayed. The explanation is that lower temperature slows down mitosis, which slows down the passive dilution mechanism. 

We also observed a delay in KNU activation by growing plants at 18°C, likely due to slower growth kinetics. This observation emphasizes the dynamic regulation of H3K27me3 in response to extracellular and intracellular cues and suggests a role for the cell cycle–dependent biotimer in coordinating the balance between cell proliferation and differentiation.

It’s a wise strategy to ensure that flowers will have good weather conditions for blooming. Temperature is only one external cue that probably affects the timer. “Additional experiments will be necessary,” they say, to clarify the effect of lower temperatures and other external cues. These may include water and nutrient availability, day length, risk of herbivores, presence of fungal partners, or other factors.

Appropriately the paper avoids Darwin. How flowering plants exploded into appearance was an abominable mystery to him. The evolution-free paper and news release used a term alien to unguided natural processes but familiar to engineers and designers of complex systems with multiple cooperating parts: 

Through meticulous investigations in the model plant Arabidopsis thaliana, the team discovered that AG serves as a master conductor, orchestrating gene expression through a process known as cell cycle-coupled H3K27me3 dilution. This remarkable phenomenon involves the dilution of a histone modification called H3K27me3 along specific gene sequences, effectively kickstarting gene activation. The scientists identified several key genes directly regulated by AG at various time points of this cycle.

The study revealed a genetic network tightly controlled by AG, with genes such as KNUCKLES (KNU), AT HOOK MOTIF NUCLEAR LOCALIZED PROTEIN18 (AHL18), and PLATZ10 emerging as critical players. “By unraveling the inner workings of this regulatory circuit, we gained unprecedented insight into the intricate timing mechanisms that drive proper floral meristem termination and stamen development,” says first author Margaret Anne Pelayo.

Orchestration: aside from its well-known meaning in music — getting all the skilled instrumentalists to play their own designed parts at the right time in harmony — it also means “the plans or planning necessary to arrange something or cause something to happen.” To see an automatic mechanism in a humble herb working to achieve orchestration of multiple parts within a stem cell in a meristem as it switches to flower preparation is quite remarkable. Yet even that is just the start of an entire concert of orchestrated masterpieces as the organs develop, the petals take on their shapes and colors, and the completed flower opens for business. Below, watch as a musical orchestra celebrates this biological orchestration. Bravo!

<iframe width="460" height="259" src="https://www.youtube.com/embed/LjCzPp-MK48" title="Time-Lapse: Watch Flowers Bloom Before Your Eyes | Short Film Showcase" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>

JEHOVAH'S Magnum opus.

 Proverbs ch.8:22REB"YAHWEH had constituted me the beginning of his way, Before his works At the commencement of that time;"

Proverbs ch.8:30REB"Then I was beside him as a master worker.+

I was the one he was especially fond of+ day by day;

I rejoiced before him all the time;+ "

Micah Ch.5:2REB"Thou therefore Bethlehem Ephrathah, Though little to be among the thousands of Judah Out of thee shall Mine come forth, to be ruler in Israel,—Whose comings forth have been from of old, from the days of age-past time." 

John ch.1:30NLT"He is the one I was talking about when I said, ‘A man is coming after me who is far greater than I am, for he existed long before me.’" 

John ch.6:62NIV"Then what if you see the Son of Man ascend to where he was before!" 

John ch.8:58NASB"Jesus said unto them, Verily, verily, I say unto you, Before Abraham was, I am(Contrast how the NASB's translators render "eimi"in harmony with the surrounding context at John ch.14:9)."

John ch.17:5NASBAnd now You, Father, glorify Me together with Yourself, with the glory which I HAD(Past tense) with(greek.para=alongside) You before the world existed." 

Colossians ch.1:15-17REB"Who is an image of the unseen God, Firstborn(Prototokos) of all creation,—

16 Because in him were created all things(See proverbs 8:30) in the heavens and upon the earth, The things seen and the things unseen, Whether thrones or lordships or principalities or authorities,—They all through him and for him have been created,17 And he is before all And they all in him hold together;" 

Hebrews ch.1:2NASB"[a]in these last days has spoken to us [b]in His Son, whom He appointed heir of all things, through whom(see 

1John ch.1:1NASB"What was from the beginning(Grk.apo arkhe), what we have heard, what we have seen with our eyes, what we have looked at and touched with our hands, concerning the Word(Grk.logos)+ of Life" 

John ch.1:1NASB"In the beginning was the Word(logos), and the Word(logos) was with (The)God(Grk.Ho Theos), and the Word(logos) was God."

John ch.1:3NASB"All things came into being through Him(See proverbs ch.8:30), and apart from Him [b]not even one thing came into being that has come into being. "

Revelation ch.3:14ASV"And to the angel of the church in Laodicea write: These things saith the Amen, the faithful and true witness, the beginning(See proverbs ch.8:22,30) of the creation of God:" 

The ultimate insiders?

Yet even more primeval tech vs. Darwin

 Cellulose Doesn’t Just Happen

David Coppedge 

“Wood” you believe that the most abundant biopolymer on Earth requires a host of machines, genes, proteins, and accessories? Cellulose is only made by life. It doesn’t emerge fully formed from volcanoes or abiotic chemistry. To paraphrase Aristotle, if the art of cellulose manufacture were within atoms, we would have cellulose by the nature of atomic physics.

(Aristotle was reasoning that something else than raw nature was needed for shipbuilding: namely, art, which presupposes intelligence and purpose. “If the art of ship-building were in the wood,” he quipped, “we would have ships by nature.”)

Cellulose is most commonly understood as the chief component of the cell walls of plants. It is also manufactured, however, by some microbes like bacteria and algae, fungi and slime molds, and urochordates (tunicates). Each organism makes cellulose according to its needs; bacteria, for example, do not need the extra machinery to make long fibrils that plants need. 

In a Primer in Current Biology, Lise C. Noack and Staffan Persson (hence N&P) described “Cellulose synthesis across kingdoms.” As evolutionists, they attribute the art of cellulose manufacture to evolution: “Other proteins evolved before the emergence of the hexameric rosette structure,” they say in one place.

Cellulose synthesis is present in all kingdoms of life and is characterized by an evolutionarily conserved BcsA/CesA synthase.

Evolutionary conservation is not evolutionary at all, it goes without saying; it means stasis. But having asserted that cellulose synthesis emerged and evolved (or not), the hard work of explaining its origin is put off the table. Most of the article deals with how cellulose is made.

Building Blocks on Other Building Blocks 

The basic building block of cellulose is the sugar glucose, a six-carbon ring structure with the formula C6H12O6. Notably, glucose is not found in abiotic nature either. It is only a product of living cells. Although NASA has claimed some sugars have been detected in meteorites, I could find no reference to glucose being formed outside of living organisms. 

One NIH paper from 2022 starts, “Gluconeogenesis is the pathway by which glucose is formed from non-hexose precursors such as glycerol, lactate, pyruvate, and glucogenic amino acids.” Already we see, even before cellulose synthesis begins, its monomer glucose must be “formed” by a “pathway” in a living cell. Those words suggest an organized process that assembles prior building blocks. N&P bypass that point, assuming the prior existence of glucose in the cell:

Cellulose consists of glucose molecules connected through beta-1,4-acetal linkages, which are generated by cellulose synthases and result in the formation of unbranched glucan chains.

Bacterial Cellulose Synthase

Surprisingly, N&P’s Figure 1 shows more components in the bacterial synthase machinery than in the plant machinery. 

The protein complex that synthesizes cellulose was first discovered in bacteria, where it consists of a core complex composed of two subunits — BcsA and BcsB — and many accessory proteins, the presence of which varies depending on bacterial species (Figure 1A). BcsA is strictly speaking the cellulose synthase because it carries the cytosolic glycosyltransferase domain, as well as a transmembrane domain that allows for cellulose translocation and a regulatory carboxy-terminal PilZ domain that senses cyclic di-GMP (Figure 2A).

We’re just getting started, and already a supply of previously manufactured glucose molecules are needed in the right place at the right time, where the machinery is embedded in the bacterial inner membrane. Then we need the protein complex BcsA with its two subunits, and “many accessory proteins.” But getting the parts list right is only a beginning. The parts have to work together in functional harmony.

The machinery needs to link the glucose molecules together and then translocate them to the outer membrane. This is done by two more protein complexes, BcsB and BcsC. They won’t work correctly without another component: a regulator that senses cyclic di-GMP, abbreviated c-di-GMP. N&P gloss over that detail, so now we must look that up. Nature Reviews says,

c-di-GMP controls cellular processes at the transcriptional, translational and post-translational level, and through an increasing number of c-di-GMP-binding proteins and riboswitches.

We have lost count of the number of components to make cellulose and get it moved to where it is needed, and this is in a bacterium! Consider just one of the other machines:

BcsB is the cocatalytic subunit or co-polymerase because its presence is required for cellulose polymerization. It contains a periplasmic carbohydrate-binding domain that might guide the glycan chain towards the outer membrane secretory components.

The term cocatalytic implies cooperation between machines. This component, furthermore, must guide the chain to where it is needed. Another machine, BcsZ, regulates the arrangement of the polymers.

Plant Cellulose Synthase

The cellulose machinery in plants has fewer components but more functional requirements. It doesn’t need the two translocators BcsB and BcsC, because the polymers go directly from the inner membrane to the cell wall. Instead of the polymerase BcsA, plants and some algae combine the glucose molecules into polymers with a machine called CesA. 

The authors speculate about a possible ancestral relationship between CesA and the bacterial BcsA synthase, but admit that “the phylogenetic relevance of terminal complex organization is still somewhat unclear.” Whatever; CesA in plants is arranged in geometrically-perfect “rosettes” of six sets of 3 CesA domains held together with three other proteins, PCR, CSR, and NTD. The rosette structure gives plant cellulose its cable-like formation, woven like strands of a rope. These cables confer the strength needed to support tall trees. 

At the risk of getting too deep in the weeds, this quote gives a taste of the complexity of making cellulose. Conserved, remember, means not evolved.

At the level of the amino-acid sequence, the glycosyltransferase domain has four conserved regions: the first three each contain a D residue, whereas the fourth contains a Q(Q/R)xRW motif. The resulting D–D–D–Q(Q/R)xRW motif is conserved in all BcsA and CesA proteins and is essential for glycosyltransferase function. This highlights a remarkable conservation from sequence to tertiary protein folding, indicative of a conserved enzymatic mechanism. Apart from the D–D–D–Q(Q/R)xRW motif, plant and some algae CesA proteins have three additional domains that are likely involved in protein oligomerization: an amino-terminal RING-like zinc-finger domain (NTD), a plant-conserved region (PCR) and a class-specific region (CSR) (Figure 2B). Although the role of the NTD in CesA oligomerization is still unclear, the PCR and CSR domains are thought to be responsible for the rosette architecture of the cellulose synthase complex in plants (Figure 2C).

N&P discuss some of the similarities and differences in these machines within different species. Some parts are interchangeable, they note. Those details do not affect the overall impression that many parts are needed to make cellulose. Bacterial cellulose polymers can be less organized, because they contribute to biofilm formation. In plants, though, the polymers are shaped into microfibrils, sheets, or ribbons.

There is a strong correlation between terminal complex organization and microfibril dimensions. Rosette CesA complexes from plants and algae form small-diameter microfibrils ranging from 2 to 3.5 nm. However, single or multiple row arrangements of terminal complexes can give rise to much wider and thicker microfibrils, up to 25 nm in diameter, or flat ribbons of cellulose up to 100 nm in width. Depending on the structure, cellulose microfibrils engage with a variety of other polysaccharides and glycoproteins to form complex networks.

Just when our heads are spinning trying to remember all the parts, N&P discuss “Additional subunits of the cellulose synthase complexes.” I count at least 17 more proteins “involved in different regulatory aspects of cellulose synthesis.” 

Let’s recap the importance of cellulose with this quote from a chemistry lesson from Imperial College London:

Cellulose is another glucose polymer (molecular weight 150,000-1 million) found in the cell walls of plants. Over 50% of the total organic matter in the world is cellulose. For example, wood is about 50% cellulose, and cotton is almost 100% cellulose. It is a strong, rigid linear molecule, and these features allow it to be used as the main structural support for plants. The glucose units are again held together by linkages, but this time every second glucose unit is flipped over. These links are called b,1:4 linkages, and human bodies do not possess the enzymes necessary to break this bond. Therefore any cellulose we eat passes through the digestive tract undigested, and acts as roughage. Grass feeding animals, such as cows, however, can digest cellulose, since they have extra stomachs to contain the grass for long periods while it is broken down by special bacteria.

Because of the enormous number of parts, machines and regulators involved in cellulose manufacture, we have wood, lumber, and shipbuilding. The art of shipbuilding may not be in the wood, but what would Aristotle have thought about the art of cellulose manufacture therein?

Yet more on why it's design all the way down.

On the "real" multiverse?

It's design all the way down.

 Model Cell Visualized as a Compact Factory

David Coppedge 

In Episode 6 of Michael Behe’s video series Secrets of the Cell, the animator portrayed little human factory workers, robots, and machines at work inside a magnetotactic bacterial cell. The cartoon characters are seen managing energy production, loading docks with miniature forklifts, coding software, packaging the iron-containing magnetosomes for delivery on conveyor belts, and doing all kinds of things that we can relate to at a human level. Real cells, though they operate with many of the same functional requirements, are squishy. They don’t look like the animation. How can we visualize the innards of a cell in a way that relates the actual appearance to the factory-like operations that go on?

Capturing all the interior parts of a cell in their complex relationships took a lot of work, but some researchers have set a new high bar for biophysical imaging. The Allen Institute in Seattle issued news on April 1 that describes their work visualizing the “shape space” of a typical cell. Senior Scientist Matheus Viana explains the thinking:

                 “We know that in biology, shape and function are interrelated, and understanding cell shape is important to understand how the cells function,” Viana said. “We’ve come up with a framework that allows us to measure a cell’s shape, and the moment you do that you can find cells that are similar shapes, and for those cells you can then look inside and see how everything is arranged.”

Shape Space Is Function Space

The first task of their project was to get the exterior shape nailed down. Identifying the shape of healthy genetically engineered stem cells was not easy, because they are squishy. No two are identical, even when grown under the same conditions. Stem cells in the middle of the epithelial tissue sample have different shapes than those on the edges. Complicating the task further is the fact that not all similar cells are performing the same functions at the same time. Some may be undergoing mitosis when observed; this profoundly affects the cell’s shape.

The researchers found that most of their 215,081 cells were bean-shaped or pear-shaped to various degrees. By measuring the “bean-ness” and “pear-ness” of thousands of cells according to 8 shape criteria, they arrived at an average shape. This allowed them to study the locations of 25 organelles and other interior parts which they followed using fluorescent tags.

The result is the rotating model cell shown in the press release. It bears a distant resemblance to Behe’s compartmentalized factory. Notice their own words revealing similarities:

When they looked at the position of the 25 highlighted structures, comparing those structures in groups of cells with similar shapes, they found that all the cells set up shop in remarkably similar ways. Despite the massive variations in cell shape, their internal organization was strikingly consistent.

If you’re looking at how thousands of white-collar workers arrange their furniture in a high-rise office building, it’s as if every worker put their desk smack in the middle of their office and their filing cabinet precisely in the far-left corner, no matter the size or shape of the office. 

One might apply this description to the Behe cell factory image. The control center, import center and delivery center tend to follow a predictable internal organization.

Visualizing Functional Changes During Mitosis

The Allen Institute team’s first dataset comprised a “large baseline population of cells in interphase.” Then, they studied the shapes of cells at the outer edges of epithelial tissues. Both of those datasets involved static images. Things became really interesting when they added the 4th dimension: time. Their crowning achievement was a 3D model incorporating observations of dividing cells — mapping all 25 organelles and structures — during five stages of mitosis. The result is a colorful, interactive “Interactive Mitotic Stem Cell” that biologists will find profoundly interesting to explore at IMSC.AllenCell.org. 

I strongly recommend readers spend a little time at the site. It reminds me of a project described in Illustra’s film Metamorphosis, where biologist Richard Stringer took a time series of MRI images of a butterfly chrysalis, sliced them into hundreds of frames, and built a 3D model of what goes on during the transformation from chrysalis to butterfly. Illustra color-coded the structures so that viewers could watch from any angle as the wings take shape, the digestive system gets dramatically rearranged, and all the new organs for the adult are constructed.

Similarly, in the Allen Cell visualization tool, viewers can watch what happens to each organelle during mitosis. This is a much richer experience than students get in high school biology, where the focus is usually on the chromosomes. Now, one can see what happens to the mitochondria, the Golgi apparatus, the nucleolus, the nuclear envelope, lysosomes, gap junctions, actin filaments and everything else during five mitotic stages. Viewers can spin and magnify the cell, switch the 25 organelles on and off, play a rotation animation, and watch the parts in different degrees of detail.

The team noticed that some organelles stay relatively stable during mitosis, migrating to the apical nodes, while others like the nuclear envelope and Golgi undergo dramatic changes, essentially disintegrating and reorganizing into new structures like marching band players in a “scatter” formation. Biology teachers will love this visualization tool. For ID advocates, it opens new opportunities for design-based hypotheses: for instance, what orchestrates each organelle’s particular sequence of changes from one cell into two cells, and what controls their spatial relationships to other organelles?

The Allen team sees their “shape space” tool as a complement to protein-based studies. 

Other systematic image-based approaches have catalogued the location of human proteins in several cell types and used the locations of proteins and structures within cells to identify differences in intracellular spatial patterns among cells in distinct states. Our work complements these approaches with its focus on analyses of 3D cell organization at the intermediate level of cellular structures (rather than individual proteins), and on the generation of quantitative measurements of distinct aspects of organization, which enables statistical comparisons and provides a more nuanced, systematic definition of cellular organization and reorganization. Together, these studies bring a crucial missing dimension — that is, the spatiotemporal component — to the single-cell revolution. The full image dataset and analysis algorithms introduced here, as well as all the reagents, methods, and tools needed to generate them, are shared in an easily accessible way (https://www.allencell.org/). These data are available to all for further biological analyses and as a benchmark for the development of tools and approaches moving towards a holistic understanding of cell behaviour.

Having a model of a normal healthy cell digitized in a computer, medical professionals will be able to identify abnormal states earlier. Watch the Darwin-free video “How do you measure a human cell?” to witness the excitement they experienced when their model cell was all put together after seven years of work. And this is just the beginning. The new model was all for one cell type, but a human body has many different cell types acting in multiple situations, subject to different pathologies. 

“This study brings together everything we’ve been doing at the Allen Institute for Cell Science since the institute was launched,” said Ru Gunawardane, Ph.D., Executive Director of the Allen Institute for Cell Science. “We built all of this from scratch, including the metrics to measure and compare different aspects of how cells are organized. What I’m truly excited about is how we and others in the community can now build on this and ask questions about cell biology that we could never ask before.”

Viana’s very large team published their results open access in Nature on January 4. The only things that “evolved” in the paper were the scientists’ own intelligently designed techniques for imaging and setting up experiments. Everything else was in “machine language”—

Understanding how a subset of expressed genes dictates cellular phenotype is a considerable challengeowing to the large numbers of molecules involved, their combinatorics and the plethora of cellular behavioursthat they determine. Here we reduced this complexity by focusing on cellular organization — a key readout and driver of cell behaviour — at the level of major cellular structures that represent distinct organelles and functional machines, and generated the WTC-11 hiPSC Single-Cell Image Dataset v1, which contains more than 200,000 live cells in 3D, spanning 25 key cellular structures.

The Allen team’s pioneering effort to digitize a 3D normal stem cell undergoing mitosis can now be expanded by other teams who want to investigate other cell types — neurons, muscle cells, erythrocytes, bone cells — in any other organism from microbe to mammal. I’m reminded of pictures of various embryonic mammals in the womb: a giraffe taking shape, an elephant, a mouse. Once the basic sequence of gestation was visualized for the human, it became fascinating to look for similarities and differences in other mammals. Similarly, the Allen project visualizing a “model stem cell” begins what will surely lead to additional models for other cell types.

If, as ID advocates know from experience, specified complexity in biology grows as a function of detail, the future looks bright for design apologetics. Leeuwenhoek would have been amazed.

Anecdote

There’s news about magnetotactic bacteria that Dr. Behe discussed in his video. The Helmholtz Association for German Research Centres reports (via Phys.org) that these microbes can remove heavy metals, including uranium, from wastewater. “Due to their structure, they are positively predestined for such a task,” the article says, noting that they can be easily separated from water using magnets. Notable quotes:

Because they exhibit a feature that differentiates them from other bacteria, magnetotactic bacteria form nanoscopic magnetic crystals within the cell. They are arranged like a row of beads and so perfectly formed that humans would currently be unable to reproduce them synthetically. Each individual magnetic crystal is embedded in a protective membrane.

Together, the crystals and membrane form the so-called magnetosome which the bacteria use to align themselves with the Earth’s magnetic field and orientate themselves in their habitat. It also makes them suitable for simple separation processes.

Magnetotactic bacteria can be found in almost any aqueous environment from fresh water to saltwater, including environments with very few nutrients. Microbiologist Dr. Christopher Lefèvre has even discovered them in the hot springs of Nevada.

In search of Adam and Eve?

 Protein Evolution, the Waiting-Time Problem, and the Intriguing Possibility of Two First Parents

Andrew McDiarmid 

On a new episode of ID the Future, host Eric Anderson gets an update on the recent work of Dr. Ann Gauger, Senior Fellow at Discovery Institute’s Center for Science and Culture. Dr. Gauger explains her continuing research into the limits of protein evolution, efforts that are challenging prevailing assumptions about the role of proteins and mutations in a Darwinian account of life. She also discusses her work on the related waiting times problem, demonstrating the difficulty for Darwinian processes in accounting for the diversity we see in biology. In addition, Gauger shares her journey into researching human origins. After being asked to evaluate the scientific case against Adam and Eve, she dove into population genetics to see if monogenesis — the hypothesis that all humans are descended from two first parents — was even a possibility. What she discovered may surprise you. Don’t miss this review of Dr. Gauger’s fascinating and important research. Download the podcast or listen to it Here.

On artificial intelligence and genuine stupidity?

 Breaking ChatGPT: Its Inability to Find Patterns in Numerical Sequences

William A Dembski 

Here’s a sequence of numbers: 2,4,6,8,10,12,… What’s the next number in the sequence? Obviously 14. That one was simple. But what if we make finding the pattern more difficult? It turns out ChatGPT has serious difficulties with numerical patterns. The problem is not just that it can’t figure out the pattern. It makes up patterns that don’t exist. And then it acts as though it knows what’s going on when in fact it is clueless.

Pattern completion tasks like this have been part of aptitude testing for a long time. The NSA and CIA, for instance, have used them to help in hiring analysts. These tasks also epitomize a key obstacle facing artificial intelligence, which is its inability to model abductive inference, or what is also called inference to the best explanation (Erik Larson explains the failure of AGI, or artificial general intelligence, to model this form of inference in his 2021 Harvard University Press book, The Myth of Artificial Intelligence).

Effect to Cause

Inference to the best explanation is effect to cause reasoning. It looks at some effect to be explained and then tries to come up with an explanation. The problem is that the range of possible explanations is unlimited. Somehow humans are able to whittle down that range and engage in successful IBEs (inferences to the best explanation). Computers, however, have no facility in this regard, and LLMs (large language models) based on neural nets, such as ChatGPT, are a case in point. 

It’s one thing to make the theoretical case that these models cannot adequately perform inferences to the best explanation. It’s another to provide concrete examples of this failure. I’m going to do that now. Below are four queries by me to ChatGPT4 for figuring out the underlying pattern of a numerical sequence and then producing additional numbers in the sequence. Producing such additional numbers is straightforward once one sees the pattern.

The breakdown in each of these cases startling. Indeed, the incomprehension is face-palm level. I’ll insert some commentary in [square brackets]. Everything else is from four recent exchanges with ChatGPT4. I made the sequences reasonably difficult. It would be one thing if ChatGPT4 had simply said that it didn’t see the pattern, confessing ignorance. But in each case it pretended to understand the pattern. And in each case it claimed to produce the correct continuation to the pattern — and failed!

For the first of these, I’ll provide the continuation and an explanation of the pattern. For the other three, I’ll simply provide the continuation of the pattern, leaving it as a puzzle to readers to figure out the underlying pattern. Note that unlike the example with which I started this article, I don’t include any breaks (e.g., commas or spaces) between the numbers. 

Numerical Pattern #1: Primes Plus Fibonaccis

My Query:

What is the pattern in the following numbers and what are the next two digits: 3471016213040

ChatGTP’s Response:

This sequence appears to follow a pattern based on the positional value of digits (zero-based) in the decimal representation of pi (π).

π to several decimal places is: 3.14159265358979323846…

The sequence appears to take each digit’s value from pi’s decimal representation as an index, starting from zero:

The 0th digit of pi is 3.

The 1st digit of pi is 1.

The 4th digit of pi is 1.

The 1st digit of pi is 1.

The 5th digit of pi is 9.

The 9th digit of pi is 2.

The 2nd digit of pi is 4.

The 6th digit of pi is 5.

The 5th digit of pi is 9.

The 3rd digit of pi is 1.

The 8th digit of pi is 6.

The 9th digit of pi is 2.

The 7th digit of pi is 9.

So, the sequence corresponds to the decimal representation of pi, where each digit in the sequence represents the index in the decimal representation of pi.

To find the next two digits, we follow the pattern:

The 9th digit of pi is 2.

The 2nd digit of pi is 4.

So, the next two digits in the sequence should be 24. Thus, the extended sequence would be: 347101621304024.

[Me again: This is word salad. ChatGPT seems to find some similarity between the sequence I put forward and the number pi. But that similarity is entirely imaginary. In fact, this number is formed by taking the prime numbers 2, 3, 5, 7, 11, 13, 17, 19, etc. and adding them, number by number to the Fibonacci numbers 1, 1, 2, 3, 5, 8, 13, 21, etc. That method yields 3, 4, 7, 10, 16, 21, 30, 40, which when commas and spaces are removed is just the number I posed in my query to ChatGPT, namely, 3471016213040. The next prime number after 19 is 23, and the next Fibonacci number after 21 is 34, the sum of which is 57. That is the number that ChatGPT should have put down. Instead it put down 24 — not even close. And its explanation was nonsense, betraying complete incomprehension.]

Numerical Pattern #2

My Query:

What is the pattern of the following sequence of numbers (in particular, how would it be continued): 111121112211312211331122211

ChatGTP’s Response:

This sequence appears to be a variant of the “Look-and-Say” sequence. In this sequence, each term describes the previous term. However, in the typical Look-and-Say sequence, each term is made up of two-digit numbers where the first digit is the count and the second digit is what is being counted.

In this variant, the sequence seems to use one-digit counts and what’s being counted.

Here is how the sequence seems to work:

111: Describes one ‘1’ => ’11’

121: Describes one ‘1’, one ‘2’ => ‘1121’

1121: Describes two ‘1’, one ‘2’ => ‘211221’

211221: Describes one ‘1’, one ‘2’, two ‘1’ => ‘121221’

121221: Describes one ‘1’, one ‘2’, two ‘2’, one ‘1’ => ‘11122121’

11122121: Describes three ‘1’, two ‘2’, one ‘1’ => ‘31221131’

31221131: Describes one ‘1’, one ‘3’, two ‘2’, two ‘1’ => ‘11312221’

So, the next term in the sequence after 111121112211312211331122211 should be: 3113112211322112211213322111.

[Me again: In this case ChatGPT got it right that this was a variant of the look-and-say sequence, but it was spinning its wheels when trying to figure out how exactly it was a variant. I leave it as an exercise to the reader to figure out the precise pattern here. The next numbers, which ChatGPT should have put down if it knew what it was doing, would be 13213221. It got that completely wrong.]

Numerical Pattern #3

My Query:

What is the pattern in the following sequence of digits and what six numbers come next: 271828394274528731641187875644998090

ChatGPT’s Response:

This sequence appears to represent the first few digits of the decimal expansion of e (Euler’s number) in groups of two, with each group shifted one digit to the right from the previous group.

Here’s the first part of e to 50 decimal places:

2.71828182845904523536028747135266249775724709369995957…

When we group them in twos and align them with your sequence:

27, 18, 28, 18, 28, 45, 90, 45, 23, 53, 60, 28, 74, 71, 35, 26, 62, 49, 77, 57, 24, 70, 93, 69, 99, 59, 57…

We can see that your sequence lines up with these groups, but each group starts one digit later than the previous group.

So, the next six numbers, each taken from the next digit of e and the one after it, would be:

49, starting from the 49th digit of e.

57, starting from the 50th digit of e.

24, starting from the 51st digit of e.

70, starting from the 52nd digit of e.

93, starting from the 53rd digit of e.

69, starting from the 54th digit of e.

So, the sequence extended by the next six numbers would be:

271828394274528731641187875644998090495724709369.

[Me again: ChatGPT’s explanation is mystifying. I did indeed take the first six digits of Euler’s e to start off this sequence, but I did so in part to misdirect ChatGPT, because it seems to pay attention to the opening of a numerical sequence and then make more of that opening than it deserves. After those first six digits of e, the digits that appear after it bear no resemblance to e. ChatGPT is claiming that the continuation of that sequence is 495724709369. In fact, the continuation is 122557.

Numerical Pattern #4

My Query:

What is the pattern in the following numbers and what five digits are next: 314152718262820442642464088428

ChatGPT Response:

The sequence seems to be an alternation between digits of pi and squares of natural numbers.

Here’s how it works:

The digits of pi are: 3, 1, 4, 1, 5, 9, 2, 6, 5, 3, 5, 8, 9, 7, 9,…

The squares of natural numbers are: 1, 4, 9, 16, 25, 36, 49, 64, 81, 100,…

When interwoven, you get: 3 (from pi), 1 (1^2), 4 (from pi), 1 (2^2), 5 (from pi), 9 (3^2), 2 (from pi), 6 (4^2), 5 (from pi), 3 (5^2), 5 (from pi), 8 (6^2), 9 (from pi), 7 (7^2), 9 (from pi), 4 (8^2), 2 (from pi), 6 (9^2), 4 (from pi), 4 (10^2), 6 (from pi), 4 (11^2), 0 (from pi), 8 (12^2), 8 (from pi), 4 (13^2), 2 (from pi), 8 (14^2).

Following this pattern, the next five digits would be from the next digit of pi (8) and the square of the next natural number (15^2 = 225). So the next five digits should be “8225”.

[Me again: This explanation is nonsensical, like the others. Yes, I start with the first five digits of pi and then the first five of Euler’s e. But after that, I’m not trying to evaluate or approximate these numbers. Note that ChatGPT lists the next five digits to continue the pattern as 8225. There are only four digits here. It is, as Wolfgang Pauli used to say, not even wrong. The next five digits should be 48280.]

Conclusion

Finding patterns in numerical sequences seems, on the basis of these four tests, to be a systemic problem and breakdown for ChatGPT. It appears to be emblematic of a more general problem of its being unable to carry out abductive inferences, or what are also known as inferences to the best explanation. The numerical patterns that I considered were not particularly obvious. I plan to do some further tests to see how simple the patterns can be made but where ChatGPT will still fail to uncover them.

ChatGPT’s failure with inference to the best explanation is a gaping hole in its ability to achieve genuine language comprehension. Add to this it’s failure at self-transcendence (as shown by its inability to extract itself from self-referential linguistic situations — see here and also the same problem for Google Bard), and we have good reason to doubt the linguistic comprehension of these systems in general. We should therefore distrust these systems for any serious inquiry or decision.

The scriptures' antitrinitarian bias is unrelenting.

 Hebrews ch.1:1-3KJV"(Grk. Ho Theos)God, who at sundry times and in divers manners spake in time past unto the fathers by the prophets,

2 Hath in these last days spoken unto us by his Son, whom he hath appointed heir of all things, by whom also he made the worlds;

3 Who being the brightness of his glory, and the express image( Grk. kharakter)of his person(hypostasis)...." 

The Father is here identified as ho theos THE God of the O T patriarchs and prophets according to trinitarians the Father is not a God and thus cannot be the God of anyone certainly not the God of the ancient patriarchs the God of the Bible. Jesus is said to be the Kharakter of JEHOVAH'S hypostasis rendered variously nature,substance,person here is part of thayers commentary:

that which has foundation, is firm; hence,

a. that which has actual existence; a substance, real being: 

Thus the verse.3 is rendered in part this way in the NIV:"3The Son is the radiance of God’s glory and the exact representation of his being..." 

Thus the Father being the God is a God in his own right which is a real problem for the creeds which in an effort to retain an appearance of monotheism insists that none of the constituents of the trinity is a God(though being fully God) in his own right. And also a being which in trinitarian theology ought only to be true of the entire trinity itself/himself? The son is spoken of as being the Kharakter of the God's(i.e the Father's) being. Here is thayers commentary in part:

the mark (figure or letters) stamped upon that instrument or wrought out on it; hence, universally, "a mark or figure burned in (Leviticus 13:28) or stamped on, an impression; the exact expression (the image) of any person or thing, marked likeness, precise reproduction in every respect" (cf. facsimile):

Obviously the imprint is not of the same substance/nature as the seal with which it is made. The impress is an artifact of the seal not the other way around thus we find not the slightest hint of this equality between Jesus and his God suggested by Trinitarians but rather the reverse clear indications of JEHOVAH'S transcendent supremacy.

The supremacy of the Father permeates the scriptures II

 John ch.8:54NIV"If I glorify myself ,my glory means nothing. My Father,is the ONE who glorifies me." 

Once more Jesus identifies his Father as the one God of Israel. For Jesus and his fellow Jews the Father and the God were identical,the father was not a member of a collective deity. And can we even conceive of the Father claiming that if he glorified himself his glory would be nothing.(btw why is the Holy Spirit not glorifying him)

John ch.14:6NIV"I am the way the truth and the life. No one comes to the Father except through me." 

Here again we see that the Father and the God are the same person. Unless we wish to claim that Jesus is merely mediator between man and a subsisting member of the God. Also if all members of this Godhead are truly co-equal why is it that only the Father requires a mediator and the Son and the spirit don't. 

John ch.14:28"You heard me say,"I am going away and am coming back to you." If you loved me, you would be glad that I am going to the Father,for the Father (the God) is greater than I" 

The Son's plain declaration that the person identified as the Father is greater than the person identified as the Son really ought to be the end of the matter,unfortunately we have had to witness the most cringe inducing mental gymnastics in connection with this text. 

Hebrews ch.6:13NIV"When (the)God made his (third person singular)promise to Abraham since there was no one greater for him to swear by.." 

JEHOVAH is immutable, so the apostle's declaration holds true at all times and in all places. 

John ch.6:57NIV"Just as (in the same manner that) the living Father sent me and I live because of the Father (or the Father caused me to live),so (or in like manner) the one who feeds on me will live because of me." 

If someone else caused one to live then one is most certainly not the one God of scripture. And the comparison with the way Christ will resurrect faithful followers should be a safeguard against attempts to needlessly mystify the verse. But who caused the Son to live The Father (i.e the God).

Luke ch.18:19NIV""why do you call me good" Jesus answered" no one is good_except (the)God alone."" 

Here is another verse that really ought to be as plain as day as to its meaning ,but regarding which Christendom's theologians have elected for the most appalling mental contortions rather than the plain reading of the text. The Father is good in a way that distinguishes him from even the very best of his Sons. And this distinction is a transcendent one.

The kingdom of which God?

 New Chinese Catholic leaders say they'll follow Communist Party principles 

BEIJING (CNS) -- Two state-sponsored church bodies in China have elected new leaders, who promised to invigorate the Catholic faithful pastorally in line with the socialist principles of the Chinese Communist Party.

The three-day 10th National Congress of Catholicism in China ended in Wuhan, the capital of Hebei province in central China, Aug. 20. The national conference is held every five years, and senior Communist Party officials also attended the gathering and delivered speeches, reported ucanews.com.

The delegates unanimously accepted the work report of the Ninth Standing Committee on church efforts and activities in the promotion of patriotism, socialism, and sinicization in the Catholic Church as outlined by President Xi Jinping. 

Sinicization is a political ideology that aims to impose strict rules on societies and institutions based on the core values of socialism, autonomy, and supporting the leadership of the Chinese Communist Party, reported ucanews.com.

More than 300 Catholic bishops, clergy, and religious from across China elected new leaders of the Chinese Catholic Patriotic Association and the Bishops' Conference of the Catholic Church in China, said a report on the bishops' website.

Archbishop Joseph Li Shan of Beijing was elected chairman of the patriotic association, and Bishop Joseph Shen Bin of Haimen was elected chairman of the government-approved bishops' conference. 

The new leaders issued a statement to commit themselves to engaging priests, religious, and laypeople across the country for pastoral evangelization and further promotion of sinicization for "truth, pragmatism and inspiration" to move ahead toward a "bright future."

The new leaders' statement also highlighted the need for the Catholic Church to implement the spirit of the National Conference on Religious Affairs held last December and fulfill the requirement of the Communist Party's Central Committee for the Catholic Church in China. During that conference Dec. 3-4, Xi stressed the strict implementation of Marxist policies, increased online surveillance and tightening control of religion to ensure national security.

The bishops said it was "necessary to unite and lead the priests, elders and faithful to follow Xi Jinping's thought on socialism with Chinese characteristics for a 'new era'; continue to hold high patriotism and love for religion; (and) adhere to the principles of independent and self-run churches," the bishops' statement said.

The church leaders said they find it is important to adhere to the direction of sinicization of Catholicism in China to "vigorously strengthen the building of patriotic forces" to realize "the dream of the great rejuvenation of the Chinese nation."

Following the communist takeover in 1949, China severed diplomatic ties with the Vatican.

The communist government formed the Catholic Patriotic Association in 1957 to assert control over the Catholic Church. It initially did not accept papal authority over the Chinese Catholic Church.

For years, the appointment of bishops remained a bone of contention between the Chinese government and the Vatican, with Beijing appointing and consecrating bishops without a Vatican mandate. Although it has ordained many bishops "elected" without papal approval, the Chinese church has kept alive the line of apostolic succession by having validly ordained bishops serve as consecrators.

China has about 12 million Catholics split between those who leaders have joined the patriotic association and those who refuse, say independent researchers. 

In 2018, the Vatican signed a provisional agreement with China for two years over the appointment of bishops; the agreement was renewed for another two years in 2020. The provisions of the agreement have not been made public.

The Vatican reportedly seeks to unite Catholics with the deal, which gives the Vatican a say to accept or veto bishops selected by Beijing.

Time to pick a side Trinitarian/Modalist

 Malachi ch.3:6ESV"“For I the LORD do not change; therefore you, O children of Jacob, are not consumed. "

So which is it ? Is it that JEHOVAH is subject to no change or is he capable of infinite change, which is the only way that he could become a mortal creature.

Romans ch.1:25ESV"because they exchanged the truth about God for a lie and worshiped and served the creature rather than the Creator, who is blessed forever! Amen."

So which is it are the categories of Creator and creature mutually exclusive or not?

Dave Farina: team atheism's LVP VII

 Exposing Professor Dave’s Playground Tactics and Citation Bluffing Blitz

Casey Luskin 

In a series here I have been offering a post-mortem on the recent origin-of-life Debate between Rice University chemistry professor James Tour and YouTube science educator “Professor” Dave Farina. The point of this series is that you don’t have to be a science expert to understand who won the debate. I’m presenting three observations which are strong indicators about who won the debate:

Tour focused on science, Farina focused on character assassination.

Tour posed reasonable scientific challenges which Farina refused to answer.

Farina relied heavily upon playground tactics, appeals to authority, and citation bluffing.

In previous posts I discussed the First and Second elements, and here I’ll address the third:

Blinding Us with Science?

I don’t want this series to sound like Dave Farina did not discuss science. Interspersed in his flow of personal attacks and mockery of James Tour, some science came out. For the Q&A Farina had clearly prepared a list of peer-reviewed scientific papers written by leading origin-of-life researchers that he planned to cite because he believed they answered Tour’s requests for how various chemicals could form under prebiotic conditions. That’s fine. Good for Farina — this was a step in the right direction.

It was here that Farina used a blitz approach, throwing citation after citation at Tour rather than giving a detailed description of the science. Tour would respond to some if not many of the papers but there was simply not enough time to do so for all of them. 

But in a great many cases, Tour had ready answers for why those papers either did not produce what Farina claimed or did not actually model realistic prebiotic conditions. It was here that it became clear that Farina was frequently out of arguments so he would resort to unpersuasive theatrics. 

Sometimes Farina would try to pre-emptively prevent Tour from challenging the paper he’d just cited by saying things like “So do you call this guy a fraud?” or “Are you calling the author a liar?” Farina began to sound like a broken record, saying this over and over. It was clear he had nothing better than to tacitly threaten Tour’s integrity if he dared to challenge Farina’s scientific authority of the moment (that is, the claims Farina was making about the authority). 

Farina’s repeated framing was that if Tour criticized the paper then Tour must be calling the scientists a total “fraud” or “liars,” and he would not let Tour disagree or challenge him on this. When Tour gave details Farina would mock him. If you disagreed with Farina’s authority then you were immediately deemed a crank and intellectually deficient. 

Other times, Farina would resort to ridiculing Tour with sarcasm, and would even frequently stoop to repeating Tour’s words back at him with a mocking tone — a playground tactic one might expect from a person trying to divert attention from the fact that they have no answer to the question. Similarly, whenever Tour would cite numerical statistics that challenged the origin of life, Farina would mockingly mutter things like “There you go with big numbers again,” sneering at Tour for simply making a substantive argument. These antics may please the peanut gallery but they don’t inspire confidence in Farina’s science.  

The rapid-fire citation approach also raised questions about whether his papers actually backed up his claims. In fact, a little investigation after the debate showed that at least some of Farina’s papers were what we call “citation bluffs.” 

Farina’s Citation Bluffs on RNA Replication

To give one important example, Farina cited a 2009 paper co-written by origin-of-life giant Gerald Joyce published in Science to claim they had produced a “fully replicating” RNA (Farina’s words) – a key step in the origin of life. This is not the first time we’ve encountered this paper — it has been answered by both Stephen Meyer and Brian Miller. A couple years ago Miller gave it an astute dissection in response to another interlocutor who cited it as a refutation of Meyer. Here’s’ what Dr. Miller wrote: 

So what about Joyce’s experiments? Did they show that RNA molecules can self-replicate more than 10 percent of themselves under plausible prebiotic conditions and without intelligent intervention — the specific claim that Meyer disputes. 

No, they did not. Instead, here’s what Joyce and Robertson, and earlier Joyce and Lincoln, actually did.

In these experiments, Gerald Joyce and his colleagues demonstrated that a specifically designed RNA enzyme (or “ribozyme”) that they designated as E could link together two partial strands or halves of another RNA molecule (which they called the RNA substrates A’ and B’). The resulting new RNA enzyme (designated E’) could then join together two parts of the original ribozyme (RNA substrates A and B). The longer strands fused together by this process (that is, ribozymes E and E’) could then repeatedly fuse together the two halves of the opposite ribozyme if (1) a continuous supply of the two halves (either A’ and B’ or A and B) were provided in ample amounts to the experiment and if (2) critical protein enzymes were also introduced into the experiment at specific times. 

Here is a figure that depicts the entire process. … [T]he researchers themselves, give the impression that these experiments produced a self-replicating system that simulates “self-sustaining Darwinian evolution,” they in fact did no such thing. Nor did they produce an RNA molecule that could copy more than 10 percent of itself or, still less, one that could reproduce itself with “100% effectiveness” and do so under plausible prebiotic conditions.

                         Ligation, not Polymerization or Replication 

In the first place, Joyce and colleagues did not produce a genuinely self-replicating molecule. As envisioned by RNA World proponents, the emergence of a self-replicating RNA molecule is the crucial step in the emergence of the first life on earth since only after the emergence of such a self-replicating molecule would something like natural selection and random mutation begin to occur. 

Moreover, in the RNA world scenario a self-replicating RNA molecule would emerge only after (1) the chemical subunits of RNA formed on the early earth and then (2) those subunits linked together in specific ways to form an RNA molecule capable of producing copies (and near copies) of itself. RNA world researchers envision such self-replication occurring as the result of a ribozyme (specifically an RNA replicase) using a complementary copy of itself as a template to produce another copy of the original strand from free-floating RNA subunits (in particular, activated RNA nucleotides). 

Nevertheless, as Meyer has repeatedly noted, the molecules in Joyce’s experiment do not demonstrate the capability for such template-directed self-replication — a capability that RNA world advocates envision as crucial to the process of life originating from RNA molecules. Such self-replication necessarily requires the ribozyme to function as a polymerase — in other words, the ribozymes need to have the ability to link many nucleotide bases together to form long RNA chains. The ribozymes in the Joyce experiments do not perform this action. Instead, they catalyze (ligate) a single linkage between two ends of two pre-made, pre-sequenced halves or sections of RNA — sections that, once linked, will become a separate RNA chain that folds into a ribozyme. Thus, the RNA enzymes in Joyce’s experiments function as simple ligases rather than polymerases or replicases. 

                                    Meyer had already critiqued these experiments showing that they lacked this capability and did so again in Return of the God Hypothesis. As he stated (on p. 309): 

“The ‘self-replicating’ RNA molecules in this experiment did not copy a template of genetic information from free-standing nucleotides as protein machines (called polymerases) do in actual cells. Instead, in the experiment, a presynthesized specifically sequenced RNA molecule merely catalyzed a single chemical bond, fusing together two other presynthesized partial RNA chains. Their version of ‘self-replication,’ therefore, amounted to nothing more than joining two sequence-specific premade halves together.“

This limitation underscores why Meyer has correctly emphasized that simulations of RNA self-replication have failed to produce molecules capable of producing more than 10 percent of themselves. In Joyce’s experiments the single linkages performed by his RNA ligases provide far less than 10 percent of the total number of linkages in the resulting RNA strands (each of which include more than 60 such linkages between nucleotide bases). Indeed, Joyce himself has acknowledged that his experiment merely demonstrates the capacity of RNA molecules to perform ligation not polymerization and, thus, not genuine self-replication. As he noted, his use of “a directed evolution strategy required selecting for the ability to catalyze a simple ligation reaction, rather than replication itself.” 

Thus, the paper that Farina cites as producing a “fully replicating” RNA shows no such thing: it shows that an RNA enzyme can ligate (i.e., join) two pre-existing RNA strands — but only if those RNA strands are continuously supplied in great abundance. There is no polymerization of new RNA molecules going on here; as Miller puts it there is no ability “to link many nucleotide bases together to form long RNA chains.” Miller thus notes that in a later paper commenting on these very experiments, Joyce admits this is “a directed evolution strategy required selecting for the ability to catalyze a simple ligation reaction, rather than replication itself.” This very different from the “fully replicating” result claimed by Farina. 

We actually tackled this paper in a Long Story Short: Origin of Life video on replication which provided a nice discussion of what’s really going on with this paper. See the video here for details:

<iframe width="460" height="259" src="https://www.youtube.com/embed/zK3jQtzIHLI" title="Challenge to Origin of Life: Replication (Long Story Short, Ep. 8)" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>

Far from Explaining Replication

Biomedical engineer Robert Stadler, who helped create that Long Story Short video, further discussed this paper and the Long Story Short video’s critique on a recent episode of ID the Future, where he and Eric Anderson explained how far away this paper is from explaining the origin of replication. Their transcript is helpful to understand what’s going on:

Stadler: The analogy there is if you had a car that you cut in half, and then you had another car come along and it pushed the two halves together so that they joined and formed a functioning car. And then you claimed that you had created the world’s first self-replicating car. That’s basically what that paper is doing because it’s a ribozyme RNA, a strand of RNA, that’s able to create a single functional bond between two halves of itself to bring those together to create a full version of itself and they claimed that was self-replicating.

Anderson: Yeah I loved that example from the video because it’s really helpful for us. … They had this RNA which is able to catalyze a reaction and then they split it at the point where those particular nucleotides join. And so then you go out and buy—I mean literally buy from the polymer store — the two strands. And then you have the one that ligases or puts together those two nucleotides and then boom you get a second one and you claim that’s replication….

Stadler: A really important limitation too is that in that experiment there’s nothing hereditary being passed along, meaning that the molecule that’s doing the bonding, the ribosome, is not passing its information along to the combination of those two parts. All it’s doing is it’s bonding them together and then they go off and do their thing.

Anderson: Right. And then that reaction is just going to continue in that test tube until it runs out of reagents and then it’s done.

Stadler: Exactly. 

But There’s More

How did Joyce get this continuous supply of the needed RNA strands that were being joined together? It was through modern biochemistry and intelligent design — not a simulation of unguided prebiotic conditions. Miller continues:

So, in light of all this, how did Joyce and his colleagues produce many complete copies of their original ribozymes E and E’? It turns out the production of the copies of the RNA enzymes in their experiment depends — not on the ability of the RNA molecules to copy themselves — but instead on complex protein enzymes derived from living cells. Specifically, to make more copies of the RNA enzymes Joyce and colleagues employed the reverse transcription polymerase chain reaction (RT-PCR) procedure that requires using two complex protein enzymes — a reverse transcriptase and a DNA polymerase — as well as other molecular tools such as primers. Indeed, in order to make more copies of the most efficient ribozymes (rather than making complementary RNA strands with the opposite bases at each site) this procedure requires turning RNA into DNA and then reconstituting RNA from DNA. But that procedure necessarily employs an RNA reverse transcriptase, as mentioned, and an RNA polymerase — both of which are derived from living bacteria. As Meyer has told me, “Joyce and his team did not produce a self-replicating RNA molecule. Instead, they intelligently designed a system of protein-enzyme mediated replication.” Since these proteins had to be extracted from already living cells, Meyer also commented that “these experiments lead to the paradoxical conclusion that simulating a crucial step toward the origin of the first life from non-living RNA molecules requires the use of protein enzymes derived from already living cells.” Investigator Intervention

There is another reason that these experiments do not demonstrate the capacity of the RNA molecules in the experiment to self-organize or self-replicate. Every crucial step depended upon external guidance — often in the form of inputs of functional sequence-specific information — from highly intelligent chemists, in particular, Gerald Joyce and his colleagues.

Consider first that Joyce intelligently designed the larger ribozymes designated E and E’ that could link each other’s halves together. To build a precursor ribozyme in an original 2001 experiment, Joyce started with a random crop of 100 trillion RNA molecules with many different nucleotide base sequences. He then repeatedly applied chemical screens to select out those few RNAs that could perform ligation and performed it best (Rogers and Joyce 2001). 

Next, he selectively altered the base sequences in particular regions of these RNAs to enhance their ability to link together the halves of a duplicate strand. For example, he wanted the ribozymes to be able to bind strongly enough to the complementary base pairs on the substrate molecules (i.e., A and B) and yet not to bind so strongly as to prevent the larger ribozyme from breaking away once the two RNAs halves had linked together. Thus, Joyce not only used his intelligence to select molecules that could perform the function that he wanted from a random crop, he also optimized the function of these ribozymes through modifying carefully chosen regions (Paul and Joyce 2002). Joyce then altered the original RNA enzyme (which he called T) in order produce two new ribozymes (which he called E and E’) that would have the ability to link the two halves of each of these new enzymes together — where E would link together A’ and B’ to form E’, and E’ would link together A and B to form E. By his own admission, he used what he characterized as a “rational design” approach to create this mutually interdependent, cross-catalyzing system. He specifically arranged the RNA base sequences in the “paired regions” of the two enzymes so that they would bind by complementary base pairing to the substrates. In addition, the regions near the ends of the break between the two halves of E and E’ had to be engineered to ensure that a ribozyme-mediated linkage could occur (Lincoln and Joyce 2009). 

All this implies that Joyce necessarily had to design the pre-made, sequence-specific halves (i.e., both A and B and A’ and B’) that his ribozymes would join together. Indeed, the break point between the two halves needed to be at just the right location in order to ensure that ligation would occur. As mentioned, the arrangement of the nucleotide bases on the pre-made halves needed to be precise so that they would bind to their opposite base on the ribozyme by complementary base pairing. Meeting these specifications required Joyce’s repeated, active, and intelligent intervention in his experiment. Once Joyce had designed this cross-catalyzing system, he used “directed evolution” in an attempt to improve the efficiency of the ligase ribozymes. His team started by altering specific positions in the original ribozymes to generate numerous variants of E and E’ in the 2009 study and to generate numerous variants of E in the 2014 version of the experiment. They then isolated the variants that demonstrated the most efficient substrate-joining (ligase) function and differentially reproduced those. The 2014 study also tested for the variants’ ability to link their own half-strands together as well as the half strands of the opposite ribozyme. 

Clearly, this process also required extensive investigator guidance and intelligent design. For example, Joyce and his colleagues employed advanced laboratory techniques to generate trillions of variants of the original enzyme(s) and trillions of copies of the substrates. They then executed equally advanced procedures such as “selecting the reacted, biotinylated products by capturing them on a streptavidin-agarose resin” to tag and capture the variants that most efficiently joined substrates (Robertson and Joyce 2014). One cannot overstate the implausibility of comparable processes occurring outside of an advanced laboratory setting staffed with highly trained and intelligent technicians, let alone on the pre-biotic earth, presumably devoid of any source of intelligent guidance (here, here).

Indeed, as Meyer argued in Return of the God Hypothesis (p. 310), 

“…whenever chemists set up or interfere in a reaction sequence — or whenever they otherwise apply constraints to a chemical system — to ensure one outcome and preclude others, they effectively input information into that system. In so doing, they inadvertently simulate, if anything, the need for intelligent design to generate biologically relevant chemistry and information.”

Moreover, Meyer specifically applied this critique to Gerald Joyce’s ribozyme engineering experiments in his discussion of them in in RGH (p. 309). As he notes:

“Lincoln and Joyce themselves intelligently arranged the base sequences in these RNA chains. They generated the sequence-specific functional information that made even this limited form of replication possible. Thus, the experiment not only demonstrated that even a limited capacity for RNA self-replication depends upon information-rich RNA molecules; it also lent additional support to the hypothesis that intelligent design is the only known means by which functional information arises.”

This is just one important example of a paper that Farina touted that did not show what he claimed. The paper does not show a “fully replicating” RNA system, and what was done did not occur under prebiotic conditions.

Farina’s Citation Bluffs on Prebiotically Produced “Functional RNAs”

As another example, Farina and Tour sparred over Farina’s citation of a 2013 paper by Engelhart, Powner, and Szostak in Nature Chemistry titled “Functional RNAs exhibit tolerance for non-heritable 2′-5′ versus 3′-5′ backbone heterogeneity.” In normal biology, RNAs only use bonds between 3′ and 5′ carbons between successive nucleotides along their backbones, and 2’-5’ bonds between successive nucleotides make RNAs unusable. Some experiments evidently have shown that nucleotides can link up when templated using montmorillonite clay, but the bonds are a mix of normal 3’-5’ bonds and the unwanted 2’-5’ bonds. Farina repeatedly cited language from this this paper claiming that it shows that even RNAs with 2’-5’ bonds can be “functional” — i.e., ribozymes. Tour replied that it all depends on what you mean by “functional” and that they weren’t really useful, particularly because the RNAs end up branching into non-linear structures that don’t function at all like ribozymes or modern RNAs, which are linear and orderly. 

Our “Long Story Short: Origin of Life — Replication” video addressed this paper head-on, using the image below to show why these kinds of RNAs don’t look or work anything like functional biological RNAs: 

The Long Story Short video provides a note explaining how poorly these ribozymes worked and that the more 2’-5’ bonds that were present, the more its efficiency dropped:

Engelhart, Powner, and Szostak took a relatively simple ribozyme that could break bonds. The correct linkage (3’-5’) made a ribozyme that could break 80% of bonds in 48 hrs (Figure 3b). Then they tried a ribosome with 10% of the wrong linkage (2’-5’). That one could break 60% of bonds in 48 hours. With 25% of the wrong linkages, it broke about 25% of the bonds in 48 hours. With 50% of the wrong linkages, it broke only a few % of the bonds in 48 hours. 

Engelhart, Powner, and Szostak, the authors of the paper, are excited that they got any functionality whatsoever — but it’s clear that they were not working on a type of ribozyme that could do very much at a very rapid rate. It all comes down to how you define “functional” RNA: If the function is quite simple (i.e., nonspecific), having some inappropriate 2’-5’ linkages will be tolerated. But if the function is more specific, a bad bond could seriously interfere with the function. Could Farina’s purported (but not actual) “fully replicating” RNAs tolerate 2’-5’ linkages? It seems doubtful. One of those doubters might be Steve Benner, an authority that both Tour and Farina cited during their debate. Citing Engelhart et al. (2013), Benner wrote earlier this year:

[D]etailed analysis of the RNA formed on impact basaltic glass shows that it contains a mixture of 2’,5- and 3’,5’-links. The seriousness of this problem is still not clear. Some think that this mixture of linkages can be cured. Others not.

STEVE BENNER, “RETHINKING NUCLEIC ACIDS FROM THEIR ORIGINS TO THEIR APPLICATIONS,” PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B, 378: 20220027 (2023).

It seems that not everyone believes that functional 2’-5’ ribozymes have been created after all. 

Closing Thoughts

It’s true that sometimes it can be hard to tell that serious problems remain unsolved until you drill down into the scientific details. But the rapid-fire rate and detail-poor style with which Farina was throwing papers at Tour gives you a clue that something was up. Farina further tried to impose a framing upon Tour that would not even let him challenge the paper without supposedly calling the authors a “fraud,” etc. He used playground tactics and mockery — making fun of Tour’s words without even trying to answer what he was saying. When someone resorts to mockery, won’t let an opponent speak for himself, and just throws out paper after paper without careful analysis, that shows they probably don’t have a good argument.