CLICK HERE TO READ ON IGB WEBSITE In the quest to decipher the evolutionary relationships of extinct organisms from fossils, researchers often face challenges in discerning key features from weathered fossils, or with prioritizing characteristics of organisms for the most accurate placement within a phylogenetic tree. Enter neural networks, sophisticated algorithms that underlie today’s image recognition technology. While previous attempts to utilize neural networks in classifying extinct organisms within phylogenetic trees have struggled, a new study, recently published in PNAS Nexus, heralds a significant breakthrough. The model has been trained to recognize and rank organism features based on known phylogenetic information, and can accurately place new organisms, including those that are extinct, within the intricate branches of evolutionary trees.
The team includes Surangi Punyasena (CAIM), an associate professor of Plant Biology at the University of Illinois Urbana-Champaign, Shu Kong, an assistant professor of science and technology at the University of Macau, and Marc-Élie Adaimé, a graduate student in Punyasena’s lab and first author on the study. According to Adaimé, the reason neural networks have trouble accurately classifying extinct organisms as opposed to living ones is often a matter of how they are trained. “Most paleontological AI studies typically focus on straightforward classification tasks, such as distinguishing between different fossil types,” explained Adaimé. “This approach works well within the scope of clearly defined categories, but less so with data that doesn’t fit these categories. Think of a model that has only been trained to classify images of dogs or cats. If it were presented with an image of a snake, the model would try to categorize it as either a dog or cat because it’s limited to what it was trained on. Similarly, there was no method previously that included phylogeny a priori into the model, so models did not learn to make sense of the features in an evolutionary or phylogenetic context. The goal of our research was to create a new modeling approach that would be trained on images in a phylogenetic context.” To accurately position organisms within a phylogenetic framework, neural networks must be trained not only to discern defining traits of various organism classes but also to recognize phylogenetic synapomorphies—derived features shared between organisms due to their common ancestry. This enables the network to determine the placement of organisms within a phylogenetic tree. The team chose to apply their model to the classification of pollen and spores —a ubiquitous and ancient entity found throughout the fossil record, with earliest fossils dating back hundreds of millions of years. The researchers first gathered optical superresolution images of modern and fossil pollen that had been taken at the Carl R. Woese Institute for Genomic Biology Core Facility. They trained their model using micrograph images of 30 extant (living) Podocarpus species. During this process, the model identified features it deemed important for classifying the pollen into different classes. Subsequently, these features were inputted into a secondary model, along with established phylogenetic data on the species, which then reweighted the features based on their phylogenetic significance. This approach enabled the model to generate a phylogenetically informed distance function, applicable to new pollen images provided to the model. To validate the model's efficacy, the researchers tested it on micrograph specimens of extinct pollen from Panama, Peru, and Columbia. While the exact phylogenetic relationships were not definitively known, paleoecologists had previously placed the pollen within Podocarpus based on morphological traits and geographical distribution. Impressively, the neural network model mirrored the placements made by the paleoecologists for nearly all specimens, underscoring its capacity to leverage morphological features learned during training to accurately position extinct species within a phylogenetic context. Punyasena noted that her lab is collaborating with colleagues at the Smithsonian National Museum of Natural History and the Smithsonian Tropical Research Institute to expand this work and apply it to a broader set of fossil pollen data. “International continental drilling projects are currently producing unimaginable amounts of fossil plant material,” said Punyasena. “Fully leveraging these new data sources means changing the way that we analyze and interpret fossil pollen. As a community, we need to take advantage of advances in deep learning and computer vision. This work demonstrates that the amount of evolutionary information captured in pollen morphology had been previously underestimated. The history of a plant species is captured in its shape and form. Machine learning allows us to discover these novel phylogenetic traits.” The researchers plan to enhance their model's accuracy and adaptability by expanding the sample size of images used for training. Furthermore, they aim to ensure the model remains current by integrating emerging advancements in machine learning. Adaimé emphasizes the model's versatility beyond pollen classification, foreseeing its potential application in categorizing various fossil organisms. “Machine learning models can make it easier to find features that are informative, because the way machine learning models think is obviously very different from what the way humans think,” said Adaimé. “It's going to be able to find patterns that make sense but probably aren’t intuitive to humans. And the benefit of this approach isn’t just limited to pollen, we expect these models will be generalizable to classifying fossils of other organisms as well.” The study was funded by the National Center for Supercomputing Applications and the University of Illinois, and can be found at https://doi.org/10.1093/pnasnexus/pgad419
0 Comments
In the realm of renewable energy where solar, wind, and thermal sources take center stage, a new technology is quietly emerging: energy generation through evaporation. Though in its infancy, evaporation technology holds the potential to revolutionize the clean energy sector by providing an efficient, abundant, and cost-effective alternative to fossil fuels.
Xi Chen, a professor with the ASRC’s Nanoscience Initiative, and his transdisciplinary research team have secured a $650,000 NSF Convergence Accelerator Phase 1 grant as part of the program’s Track M: Bio-Inspired Design Innovations. The funding will support the development of water-responsive materials and generators. The generators use the actuation created by these materials to harness evaporation and produce clean, renewable energy. “Our aim of this year-long, Phase 1 project is to establish platforms for the design and manufacturing of water-responsive materials and develop preliminary prototypes and simulation models of evaporation energy harvesting devices.” said Chen, the project’s principal investigator. The research team will produce materials from two sources. One is peptidoglycan, a macromolecule that can found within bacterial cell walls. Peptidoglycan strongly reacts to humidity, and it has the highest power and energy density compared to other actuator materials, including artificial muscles. The other material is silk collected from silkworm cocoons, which can be made into large sheets or other structures. As the water in these materials evaporate, the generators autonomously convert evaporation energy into mechanical motion and electricity. One notable advantage of this technology is its capacity to function both day and night, solving the important “intermittency” problem in energy storage for solar and wind. The ambitious research effort aims to produce prototypes within the next year and conduct product demonstrations for organizations and companies by the third year. Spanning various scientific disciplines within the ASRC and encompassing policy and marketing expertise, the transdisciplinary team also includes researchers from The City College of New York, Hunter College, Columbia University, New York University, National Renewable Energy Laboratory (NREL), GE research, Cannon, Ginkgo Bioworks, and ISEE Systems. The team’s diverse expertise is aimed at garnering public support for new approaches to renewable energy technology, said Charles Vörösmarty, founding director of the ASRC’s Environmental Science Initiative and a co-principal investigator on the project. “When you’re working with new technology, the general public isn’t going to know how it works and what it can offer,” said Vörösmarty. “For example, the Department Of Energy doesn’t have an evaporation program yet because the technology is so new. It’s important to gather people on our team with different expertise, like those in policy and marketing, so we can better inform people about the potential results the technology offers and bring it from the lab to real life to make it truly transformational.” The adaptable design of the generators allows them to be tailored to the needs and available space of their installation location, offering an alternative clean energy source for areas where solar and wind might face limitations due to weather or terrain. “One technique cannot solve all of the energy issues we’re facing today,” said Chen. “But this will provide another choice for clean energy that might be a better fit for people depending on their location and weather.” CLICK HERE TO READ ON IGB WEBSITE Cape lions used to roam the Cape Flats grassland plains of South Africa, in what is now known as Western Cape Providence. When Europeans arrived in South Africa in the mid-1600s, Cape lions, along with many other African carnivores and herbivores, were hunted as agricultural practice to protect livestock and humans. By the mid-1800s, less than 200 years since European arrival, Cape lions had been hunted to extinction. European naturalists described the Cape lion as having a particularly black mane and as being morphologically distinct. However, alternative depictions and descriptions of Cape lions from Indigenous people report mixed or light mane coloration. To shed light on this discrepancy, a recent study published in the Journal of Heredity, led by a team of researchers from the University of Illinois Urbana-Champaign, compared the genetic diversity and distinctiveness of Cape lions to modern lions across 13 African countries. The team features researchers from the Carl R. Woese Institute for Genomic Biology, including postdoctoral researcher and first-author Alida de Flamingh, Professor of Anthropology Ripan Malhi (CIS co-leader/GSP/GNDP/IGOH), Professor of Animal Sciences Alfred Roca (EIRH/GNDP), and Associate Professor of Integrative Biology Julian Catchen (CIS/GNDP), along with biologists from Roosevelt University and the Field Museum.
“What’s interesting is that the scientific name of the Cape lion, Panthera leo melanochaitus, literally means black mane, but this description was based on a single specimen,” said Julian Kerbis Peterhans, an emeritus professor at Roosevelt University. “Historically, we see lots of examples of creatures that are large and attractive like lions, where everybody wants to claim that they’d discovered a new one, without taking into account variation in the population, or whether that species is even unique.” Earlier investigations focused on limited segments of the Cape lion genome, offering the first indication that these lions might not be as distinct as initially believed. However, this study represents the first comprehensive examination of the entire Cape lion genome in comparison to contemporary lion populations across Africa. The team gathered samples from two Cape lion skulls currently housed at the Field Museum. These skulls were initially showcased at the South African Institute in Cape Town (1828-1838) as integral components of taxidermy mounts. The well-documented history of the skulls allowed the researchers to contextualize the diversity of the Cape lions within a specific time frame. “Unlike most other Cape Lion specimens around the world, these specimens had a traceable history and geographic collection location, so they had a pedigree,” said Thomas Gnoske, a Field Museum biologist. “As such, it was a great opportunity and challenge to see what application of the newest genomic methods could tell us about these specimens.” The genomic data collected from the skulls was compared to 118 existing mitogenomes and nuclear genomes of 53 other lions across Africa. Using complimentary genomic analyses, they found that the genome of the Cape lions was diverse and demonstrated genomic links with other lions from both the southern and eastern parts of Africa. While the researchers acknowledge the limitation of having only two Cape lion samples, they underscored that the results indicate that genetic characteristics that Cape lions had are still present in historic and some contemporary populations of lions in these regions in Africa. “One of the most surprising things was that we found such high genetic diversity in the Cape lion population,” said de Flamingh. “Both skulls were from the same small area, yet they had quite different mitochondrial DNA lineages and nuclear genomes. It tells us that there were very genetically diverse lions living in the Cape before they were extirpated.” The researchers also found that the Cape lion genomes exhibited high heterozygosity, and lacked traits commonly associated with small populations and inbreeding — characteristics frequently observed in endangered species facing population decline. This unexpected absence of such traits in the Cape lion genomes is particularly noteworthy, considering how close the skulls’ collection was to the species' extinction. “Contemporary species that are critically endangered and at high risk of extinction, such as the rhino or black-footed ferret, often have really small effective population sizes, which leads to inbreeding and lack of heterozygosity,” explained de Flamingh. “The Cape lions didn’t have any of those genomic signatures. What this means is that the Cape lions were hunted so rapidly that their genomes didn't have time to accumulate the signatures of long-term small population size.” The richness observed in the Cape lion genome implies that these lions likely exhibited significant phenotypic variation, including diverse mane coloration. This aligns more closely with alternative descriptions and Indigenous perspectives of the species, which the researchers say emphasizes the importance of incorporating diverse knowledge systems in enhancing our understanding of the histories of species. For me, the big takeaway from this study does not specifically have to do with Cape lions,” said Malhi. “The information we gained from the genomic data and analysis didn't fit what was thought about Cape lions based on colonial descriptions. This study is good example showing that identifying type specimens using information from people who are not originally from that area can result in ignoring diversity in a population that is important for understanding evolution.” The team suggests that this discovery provides insights for shaping future conservation strategies particularly for contemporary lion species in Africa. The results emphasize the importance of trans-country parks and heightened genetic connectivity between populations across Africa in order to maintain genetic diversity and flow. “Working with museums, such as the Field Museum, is an exciting opportunity to apply ancient DNA analyses to better understand human-animal interactions,” said de Flamingh. “I think it's an area that’s going to be studied more and more as our genetic technology continues to advance.” The study was funded by the USAID Wildlife TRAPS Project, USDA, NSF, and the University of Illinois. It can be found at https://doi.org/10.1093/jhered/esad081. |