Revo Foods’ “THE FILET – Inspired By Salmon” salmon fillet may be the first 3D-printed food to hit store shelves. said that firm CEO Robin Simsa remarked, “With the milestone of industrial-scale 3D food printing, we are entering a creative food revolution, an era where food is being crafted exactly according to customer needs.”

Mycoprotein from filamentous fungi is used to make the salmon alternative and other meat substitutes. Vitamins and omega-3 fatty acids are in the product, like in animals. Is high in protein, at 9.5 grams per 100 grams, although less than conventional salmon.

Revo Foods and Mycorena developed 3D-printable mycoprotein. Years of research have led to laser-cooked cheesecakes and stacked lab-grown meats.

One reason for this push is because printed food alternatives may make food production more sustainable, which worries the fishing sector. Overfishing reduces fish populations in 34% of worldwide fish stocks.

Over 25% of worldwide greenhouse gas emissions come from food production, with 31% from livestock and fish farms and 18% from supply chain components including processing and shipping. According to Revo Foods’ website, vegan salmon fillet production consumes 77 to 86% less carbon dioxide and 95% less freshwater than conventional salmon harvesting and processing.

The salmon alternative’s sales potential is unknown. In order to succeed, Revo Foods believes that such goods must “recreate an authentic taste that appeals to the flexitarian market.”

The commercial distribution of 3D-printed food could change food production.

All diseases are based on proteins, natural molecules that perform vital cellular functions. Characterizing proteins can reveal disease mechanisms and ways to slow or reverse them, while creating proteins can lead to new drug classes.

The lab’s protein design process is computationally and human resource-intensive. It involves creating a protein structure that could perform a specific function in the body and then finding a protein sequence that could “fold” into that structure. To function, proteins must fold correctly into three-dimensional shapes.

Not everything has to be complicated.

Microsoft introduced EvoDiff, a general-purpose framework that generates “high-fidelity,” “diverse” proteins from protein sequences, this week. Unlike other protein-generating frameworks, EvoDiff doesn’t need target protein structure, eliminating the most laborious step.

Microsoft senior researcher Kevin Yang says EvoDiff, which is open source, could be used to create enzymes for new therapeutics, drug delivery, and industrial chemical reactions.

Yang, one of EvoDiff’s co-creators, told n an email interview that the platform will advance protein engineering beyond structure-function to sequence-first design. EvoDiff shows that ‘protein sequence is all you need’ to controllably design new proteins.

A 640-million-parameter model trained on data from all protein species and functional classes underpins EvoDiff. “Parameters” are the parts of an AI model learned from training data that define its skill at a problem, in this case protein generation. The model was trained using OpenFold sequence alignment data and UniRef50, a subset of UniProt, the UniProt consortium’s protein sequence and functional information database.

Modern image-generating models like Stable Diffusion and DALL-E 2 are diffusion models like EvoDiff. EvoDiff slowly subtracts noise from a protein made almost entirely of noise to move it closer to a protein sequence.

Beyond image generation, diffusion models are being used to design novel proteins like EvoDiff, create music, and synthesize speech.

“If there’s one thing to take away [from EvoDiff], I think it’s this idea that we can — and should — do protein generation over sequence because of the generality, scale, and modularity we can achieve,” Microsoft senior researcher Ava Amini, another co-contributor, said via email. “Our diffusion framework lets us do that and control how we design these proteins to meet functional goals.”

EvoDiff can create new proteins and fill protein design “gaps,” as Amini noted. A protein amino acid sequence that meets criteria can be generated by the model from a part that binds to another protein.

EvoDiff can synthesize “disordered proteins” that don’t fold into a three-dimensional structure because it designs proteins in “sequence space” rather than structure. Disordered proteins enhance or decrease protein activity in biology and disease, like normal proteins.

EvoDiff research isn’t peer-reviewed yet. Microsoft data scientist Sarah Alamdari says the framework needs “a lot more scaling work” before it can be used commercially.

“This is just a 640-million-parameter model, and we may see improved generation quality if we scale up to billions,” Alamdari emailed. WeAI emonstrated some coarse-grained strategies, but to achieve even finer control, we would want to condition EvoDiff on text, chemical information, or other ways to specify the desired function.”

Next, the EvoDiff team will test the model’s lab-generated proteins for viability. Those who are will start work on the next framework.

When we hear the word Velociraptor, we usually think about the clever girls from Jurassic Park/World. In my case, I think about Dinobot from Beast Wars, but that’s neither here nor there, because after you’re done reading this article, you won’t be able to get the following thought out of your head: Velociraptors are related to a dinosaur best described as a prehistoric swan. Good luck ever seeing ol’ sickle claw the same way again.

Say hello to the Halszkaraptor essuilliei (Halszka for short), a dinosaur recently discovered at Ukhaa Tolgod (part of the Djadochta Formation in the Gobi Desert in Mongolia) by a team of paleontologists led by Andreau Cau of the Geological Museum Capellini in Bologna, Italy. Halszka’s around 75 million years old, which means he was alive during the late Cretaceous period during what is known as the Campanian age. And if you’re wondering why he looks like a swan, that’s because, according to a 3D synchrotron analysis (a process that uses x-rays so powerful they can only be produced in facilities the size of football stadiums), he’s semi-aquatic. Doesn’t he just look adorable?

Halszka belongs to the suborder therapod, known for specimens such as Tyrannosaurus Rex, the Velociraptor, and the ostrich. Therapods are known for their efficacy on land, but until the Halszkaraptor’s discovery, scientists thought they were exclusive to solid ground. Sure, some therapods might have eaten fish from time to time, but Halszka is the only known therapod with aquatic tendencies.

“The first time I examined the specimen, I even questioned whether it was a genuine fossil,” explained Cau. “This unexpected mix of traits makes it difficult to place Halszka within traditional classifications.” Given the long, swan-like neck, dinky flippers, and sickle-shaped claws reminiscent of the Velociraptor, I can’t blame him for being confused. Zoologists went through the same problem when they examined the first known platypus back in 1799; who wouldn’t be confused by such disparate features? “When we look beyond fossil dinosaurs, we find most of Halszkaraptor‘s unusual features among aquatic reptiles and swimming birds,” Cau continued. “The peculiar morphology of Halszkaraptor fits best with that of an amphibious predator that was adapted to a combined terrestrial and aquatic ecology: a peculiar lifestyle that was previously unreported in these dinosaurs. Thanks to synchrotron tomography, we now demonstrate that raptorial dinosaurs not only ran and flew, but also swam!”

Halszka now proudly sits as the first of a new genus of amphibious dinosaurs, capable of using its legs to walk on land and swim through the water and with a posture likely similar to those of modern day ducks and swans. Since the Gobi Desert, especially the Djadoctha Formation, appears to be a hotbed of important paleontological finds, many of which are therapods related to Halszka, who knows how many other amphibious dinosaurs are waiting to be discovered? Halszka could either be one of many previously undiscovered swimming raptors or as unique as the Mesonychid; nature’s first and only attempt at a hoofed predator.

If you are interested in reading Cau’s paper on the Halszkaraptor essuilliei, you can read the article on Nature. However, if you do not have a subscription, you should either read the Science Daily article or Andreau Cau’s personal blog (it is in Italian but an English translation is readily available on the page).