Life on Earth would not exist as we know it, if not for the protein molecules that enable critical processes from photosynthesis and enzymatic degradation to sight and our immune system. And like most facets of the natural world, humanity has only just begun to discover the multitudes of protein types that actually exist. But rather scour the most inhospitable parts of the planet in search of novel microorganisms that might have a new flavor of organic molecule, Meta researchers have developed a first-of-its-kind metagenomic database, the ESM Metagenomic Atlas, that could accelerate existing protein-folding AI performance by 60x.

Metagenomics is just coincidentally named. It is a relatively new, but very real, scientific discipline that studies “the structure and function of entire nucleotide sequences isolated and analyzed from all the organisms (typically microbes) in a bulk sample.” Often used to identify the bacterial communities living on our skin or in the soil, these techniques are similar in function to gas chromatography, wherein you’re trying to identify what’s present in a given sample system.

Similar databases have been launched by the NCBI, the European Bioinformatics Institute, and Joint Genome Institute, and have already cataloged billions of newly uncovered protein shapes. What Meta is bringing to the table is “a new protein-folding approach that harnesses large language models to create the first comprehensive view of the structures of proteins in a metagenomics database at the scale of hundreds of millions of proteins,” according to a TK release from the company. The problem is that, while advances of genomics have revealed the sequences for slews of novel proteins, just knowing what those sequences are doesn’t actually tell us how they fit together into a functioning molecule and going figuring it out experimentally takes anywhere from a few months to a few years. Per molecule. Ain’t nobody got time for that.  

Robots can now talk to animals

By Callie Patteson

HUMANS are one step closer to talking to animals as new technologies are allowing artificial intelligence-enabled robots to speak with different species. 

Karen Bakker, a professor at the University of British Columbia, recently revealed this technology is being used to communicate with honeybees, dolphins and elephants and offered up a warning regarding the development. 

“Now, this raises a very serious ethical question, because the ability to speak to other species sounds intriguing and fascinating, but it could be used either to create a deeper sense of kinship, or a sense of dominion and manipulative ability to domesticate wild species that we’ve never as humans been able to previously control,” Bakker said in an interview published with Vox. 

She pointed to the use of artificial intelligence to communicate with honeybees in Germany. 

“A research team in Germany encoded honeybee signals into a robot that they sent into a hive,” Bakker said. 

“That robot is able to use the honeybees’ waggle dance communication to tell the honeybees to stop moving, and it’s able to tell those honeybees where to fly to for a specific nectar source.”

Kristen Fortney. Image/BioAge

BY JONATHAN SMITH

The development of longevity treatments is hampered by a lack of biomarkers and validated drug targets. BioAge’s co-founder and CEO, Kristen Fortney, explains how the firm is enlisting machine learning (ML), artificial intelligence (AI) and biobanks to fill in the gaps.

The quest for human longevity treatments is attracting big cash in the biotech industry. One of the most impressive investments entering the field was the $3 billion launch of the U.S. anti-aging company Altos Labs in January 2022.

However, efforts to extend our healthy lifespan are dogged by a lack of clear biomarkers that correlate with the aging process. There are a set of observed hallmarks of aging, such as the breakdown of cells, a lack of stem cells in tissues and unstable DNA, but the search for reliable drug targets to slow the aging process is difficult. 

In 2020, for example, the U.S. company Unity Biotechnology hit a major setback when its lead drug targeting aged, or “senescent,” cells failed to treat the age-related condition osteoarthritis in a phase 2 trial.

To overcome the challenges of developing longevity treatments, BioAge was launched in the U.S. in 2015. The firm raised a $90 million Series C round in late 2020 to finance the development of small molecule drug candidates for age-related conditions including anemia, muscle atrophy and COVID-19. BioAge also paired up with Age Lab AS in August 2022 to tap into the latter firm’s biobank — containing tissue samples collected from healthy humans over many years.

In an interview, BioAge’s co-founder and CEO, Kristen Fortney, told us how ML and AI in addition to biobank sampling can fuel the search for drug targets in longevity treatment.

By Joshua Stan

The civilization humans inhabit is filled with sounds that can’t be heard. Bats chitter and talk in ultrasonic; elephants growl infrared secrets to one another; and coastal ecosystems are aquatic clubs teeming with the cracks, hisses, as well as clicks of marine life. Mankind had no idea those noises existed for millennia. However, as technology advances, so does our ability to listen.

Drones, digital recorders, and artificial intelligence are already allowing humans to listen to the sounds of nature in new ways, altering the field of scientific inquiry and offering the intriguing potential that computers may eventually allow us to communicate with animals. Humans are one step closer to communicating with animals, thanks to new technologies that enable artificial intelligence-powered robots to converse with various species.

Karen Bakker, a University of British Columbia professor, recently disclosed that this innovation is being employed to speak with honeybees, dolphins, and elephants, and she issued a caution about the development.