MTR

BaseFold leverages Basecamp Research's purpose-built foundational dataset to significantly increase prediction accuracy of large, complex protein structures and small molecule interactions — it is up to six times more accurate than AlphaFold2 and offers up to a three-fold improvement in small molecule docking More reliable 3D structure predictions for larger and more complex proteins is poised to greatly accelerate AI-based drug discovery efforts LONDON, March 12, 2024 /PRNewswire/ -- Basecamp Research, a world leader in artificial intelligence (AI)-based design of proteins and other biological systems, today announced the launch of BaseFold, its new deep learning model that predicts 3D structures of large, complex proteins more accurately than other AI-powered tools, including the industry gold standard, AlphaFold2. These data were recently published in bioRxiv. Continue Reading Visual comparison of the difference in structural prediction performance of AlphaFold2 (orange) against BaseFold (cyan) in the CASP15 and CAMEO competitions. Exemplified here with protein targets T1113 (bacteriophage T7 polymerase inhibitor, left) and 8SSD (methionine synthase, right), BaseFold’s predictions are much closer to the laboratory-validated structures (beige). The white arrows highlight areas where AlphaFold2’s predictions are significantly inaccurate. BaseFold was created by augmenting the AlphaFold2 model, which predicts the 3D structure of a protein based on its amino acid sequence, with BaseGraph. BaseGraph is Basecamp Research's purpose-built foundational dataset for biological AI, collected via access and benefit-sharing partnerships with over 25 biodiversity-rich countries. The published accuracy improvements are just a starting point, as BaseFold is continuously improving week over week as Basecamp Research scales its global network of biodiversity partnerships. Furthermore, Basecamp Research will be working with NVIDIA to optimise and productionise BaseFold for NVIDIA BioNeMo, a generative AI platform for drug discovery. The scientific benchmark for determining protein structure is still via slow and time-consuming experimental methods such as X-ray crystallography. However, AlphaFold2's development in 2020 provided a breakthrough for the use of AI across biotechnology, giving scientists confidence in AI-based structural predictions. A wide array of structure prediction models have since followed AlphaFold2, most notably CollabFold, ESMFold, OpenFold and RoseTTAFold. However, the performance of these models is highly dependent on their training data; all are trained on public protein databases that are widely seen as unfit for biotech's AI era. These public training datasets are small, unreliable and heavily biased toward proteins from laboratory model organisms. The sequence data captured in these public databases is estimated to represent less than 0.000001% of life on Earth. These data limitations mean that existing AI tools work well for predicting the structures of smaller, simpler proteins that are well-represented in public datasets but often struggle beyond that, creating major problems for those using AI to develop complex new medicines. AlphaFold2 draws heavily from the public MGnify database, known for having issues with incomplete sequences, which can impact the quality of structures predicted for larger proteins. Basecamp Research's BaseFold tackles the next big computational challenge, which is to achieve crystallography-level accuracy for larger, more complex proteins, especially those underrepresented in existing protein sequence databases. To do this, BaseFold extracts orders of magnitude more meaningful evolutionary information from over 6 billion relationships in BaseGraph. Replete with extensive genomic context and comprehensive metadata, training algorithms on BaseGraph has been shown to yield significant advances in the performance of a wide range of biological AI models, including AlphaFold2 as presented here. In this preprint, Basecamp Research scientists evaluated BaseFold's performance in predicting the structure of various proteins selected from the CASP15 (Critical Assessment of Structure Prediction) competition and CAMEO (Continuous Automated Model EvaluatiOn) community project. Publication Result Highlights Basecamp Research's purpose-built foundational dataset allowed BaseFold to improve the accuracy of AlphaFold2's predicted structures by up to 6-fold. The team demonstrated an up to 3-fold improvement in modelling accuracy for small molecule interactions with protein targets. BaseFold unlocks more reliable 3D structure predictions and small molecule docking for larger and more complex proteins than ever before, particularly those that are underrepresented in public datasets. This step change is poised to greatly accelerate drug discovery efforts, where understanding these interactions will allow for more advanced therapeutics molecules to be developed using AI. "We have redesigned and rebuilt the entire data acquisition process, making us the first team ever to collect and annotate biodiversity data with the same quality as human clinical genetic data — all purpose-built for the AI era," said Dr. Phil Lorenz, CTO of Basecamp Research. "BaseGraph, the most diverse and comprehensive dataset of its kind, is the core driver of our advances in AI. The results of this publication prove that more diverse, representative genomics data allows for step-change algorithm improvements without the need for extensive lab-in-the-loop infrastructure. Our database is growing every week, and as a result, BaseFold is improving every week, too." "AlphaFold is one of the most useful AI tools in drug discovery, and for good reason. It enables researchers to better predict how medicines may interact with proteins in the body, shaving off years of work. However, AlphaFold still has significant room for improvement – particularly when being used to predict large, complex and underrepresented proteins, which are often the most critical for the development of new therapeutics. Even just a few percentage points of error can have major implications in accurately predicting protein-molecule interactions," said Dr. Glen Gowers, co-founder of Basecamp Research. "We know that when it comes to AI, the best data produces the best outcomes, and it's rewarding to know that the new, purpose-built foundational dataset that we have built is already having widespread implications for drug development and human health," Dr. Gowers added. "We're not stopping here, though – we are continuing to scale our biodiversity partnerships and apply this data advantage across more and more biological AI models." The full preprint can be found here: About Basecamp Research Basecamp Research is a market leader in mapping biodiversity for AI-based design of biological systems. We match and refine novel proteins for our partners' exact industrial, therapeutic or diagnostic applications using BaseGraph™, a new generation of AI design that is powered by the first-ever high-resolution map of global genetic biodiversity. Understanding the full genetic, evolutionary, and environmental context of each protein allows Basecamp Research to design tailored proteins for specific applications without the need for expensive and time-consuming directed evolution campaigns. We're a team of explorers, scientists and policy experts driven by our ambition to protect and learn from nature's diversity, whilst delivering life-changing breakthroughs to those who need them most. For more information, visit . For media and other inquiries, please contact [email protected], 07867 488769 Photo - Logo - SOURCE Basecamp Research

The algae P. antarctica has two forms of the enzyme that makes the amino acid methionine, one needing B12, and one that is slower, but doesn't need it. This means it has the ability to adapt and survive with low B12 availability. The presence of the MetE gene in P. antarctica gives the algae the ability to adapt to lower vitamin B12 availability, giving it a potential advantage to bloom in the early austral spring when bacterial production is low. P. antarctica takes in the CO2 and releases oxygen through photosynthesis. Understanding its ability to grow in environments with low vitamin B12 availability can help climate modelers make more accurate predictions. Vitamin B12 deficiency in people can cause a slew of health problems and even become fatal. Until now, the same deficiencies were thought to impact certain types of algae, as well. A new study examined the algae Phaeocystis antarctica's (P. antarctica) exposure to a matrix of iron and vitamin B12 conditions. Results show that this algae has the ability to survive without B12, something that computer analysis of genome sequences had incorrectly indicated. The alga, native to the Southern Ocean, starts as a single-cell that can transform into millimeter scale colonies. The research published in PNAS, "Flexible B12 ecophysiology of Phaeocystis antarctica due to a fusion B12-independent methionine synthase with widespread homologues," conducted by MIT, WHOI, J.C. Venter Institute, and Scripps Institution of Oceanography (UCSD), found that unlike other keystone polar phytoplankton, P. antarctica can survive with or without vitamin B12. "Vitamin B12 is really important to the algae's metabolism and because it allows them to make a key amino acid more efficiently," said Makoto Saito, one of the study's co-authors and senior scientist at the Woods Hole Oceanographic Institution (WHOI). "When you can't get vitamin B12, life has ways to make those amino acids more slowly, causing them to grow slower as well. In this case, there's two forms of the enzyme that makes the amino acid methionine, one needing B12, and one that is much slower, but doesn't need B12. This means P. antarctica has the ability to adapt and survive with low B12 availability." Researchers came to their conclusion by studying P. antarctica's proteins in a lab culture, and also searching for key proteins in field samples. During their observation, they found the algae to have a B12-independent methionine synthase fusion protein (MetE). The MetE gene isn't new, but was previously believed not to have been possessed by P. antarctica. MetE gives the algae the flexibility to adapt to low vitamin B12 availability. "This study suggests that the reality is more complex. For most algae, maintaining a flexible metabolism for B12 is beneficial, given how scarce the vitamin's supply is in seawater," said Deepa Rao, lead researcher of the study and former MIT postdoc." Having this flexibility enables them to make essential amino acids, even when they can't obtain enough of the vitamin from the environment. Implying that the classification of algae as B12-requiring or not might be too simplistic" Antarctica, which lives at the base of the food web, has been thought to be entirely controlled by iron nutrition. The discovery of the MetE gene also indicates vitamin B12 likely plays a factor. Because of its presence in P. antarctica, the adaptability of the algae gives it a potential advantage to bloom in the early austral spring when the bacteria that produce B12, are scarcer. This discovery also has implications for climate change. The Southern Ocean, where P. antarctica is found, plays a significant role in the Earth's carbon cycle. P. antarctica takes in the CO2 and releases oxygen through photosynthesis. "As our global climate warms, there's increasing amounts of iron entering the coastal Southern Ocean from melting glaciers," Saito said. "Predicting what the next limiting thing after iron is important, and B12 appears to be one of them. Climate modelers want to know how much algae is growing in the ocean in order to get predictions right and they've parameterized iron, but haven't included B12 in those models yet." "We are particularly interested in knowing more about the extent of strain level diversity. It will be interesting to see if B12 independent strains have a competitive advantage in a warmer Southern Ocean," said co-author of the study Andy Allen, a joint professor at the J. Craig Venter Institute and the Scripps Institution of Oceanography at the University of California, San Diego. "Since there is a cost to B12 independence in terms of metabolic efficiency, an important question is whether or not strains that require B12 might become reliant on B12 producing bacteria." The discovery that P. antarctica has the ability to adapt to minimal vitamin B12 availability turns out to be true for many other species of algae that were also assumed to be strict B12 users previously. The findings from this study will pave the way for future research related to the carbon cycle and how different types of algae survive in the Southern Ocean's cold and harsh environment.