Wastewater-based genomic surveillance has emerged as a powerful tool for population-level viral monitoring, offering comprehensive insights into circulating viral variants across entire communities. However, this approach faces significant computational challenges stemming from high sequencing noise, low viral coverage, fragmented reads, and the complete absence of labeled variant annotations. Traditional reference-based variant calling pipelines struggle with novel mutations and require extensive computational resources. We present a comprehensive framework for unsupervised viral variant detection using Vector-Quantized Variational Autoencoders (VQ-VAE) that learns discrete codebooks of genomic patterns from k-mer tokenized sequences without requiring reference genomes or variant labels. Our approach extends the base VQ-VAE architecture with masked reconstruction pretraining for robustness to missing data and contrastive learning for highly discriminative embeddings. Evaluated on SARS-CoV-2 wastewater sequencing data comprising approximately 100,000 reads, our VQ-VAE achieves 99.52% mean token-level accuracy and 56.33% exact sequence match rate while maintaining 19.73% codebook utilization (101 of 512 codes active), demonstrating efficient discrete representation learning. Contrastive fine-tuning with different projection dimensions yields substantial clustering improvements: 64-dimensional embeddings achieve +35% Silhouette score improvement (0.31 to 0.42), while 128-dimensional embeddings achieve +42% improvement (0.31 to 0.44), clearly demonstrating the impact of embedding dimensionality on variant discrimination capability. Our reference-free framework provides a scalable, interpretable approach to genomic surveillance with direct applications to public health monitoring.

We pretrain METAGENE-1, a 7-billion-parameter autoregressive transformer model, which we refer to as a metagenomic foundation model, on a novel corpus of diverse metagenomic DNA and RNA sequences comprising over 1.5 trillion base pairs. This dataset is sourced from a large collection of human wastewater samples, processed and sequenced using deep metagenomic (next-generation) sequencing methods. Unlike genomic models that focus on individual genomes or curated sets of specific species, the aim of METAGENE-1 is to capture the full distribution of genomic information present within this wastewater, to aid in tasks relevant to pandemic monitoring and pathogen detection. We carry out byte-pair encoding (BPE) tokenization on our dataset, tailored for metagenomic sequences, and then pretrain our model. In this paper, we first detail the pretraining dataset, tokenization strategy, and model architecture, highlighting the considerations and design choices that enable the effective modeling of metagenomic data. We then show results of pretraining this model on our metagenomic dataset, providing details about our losses, system metrics, and training stability over the course of pretraining. Finally, we demonstrate the performance of METAGENE-1, which achieves state-of-the-art results on a set of genomic benchmarks and new evaluations focused on human-pathogen detection and genomic sequence embedding, showcasing its potential for public health applications in pandemic monitoring, biosurveillance, and early detection of emerging health threats.

Arkansas is sitting on a 150 billion'hidden treasure' trove of lithium that could meet the global demand for EV batteries by 2030. The US Geological Survey (USGS) found between five and 19 million tons of lithium in the Smackover Formation, which is nine times the amount needed to meet the ongoing electric vehicle demand in the US by the end of the decade. The metal is a necessary component for batteries used in EVs and can be extracted from the brine wastewater from the same mines that produce oil and gas. 'Lithium is a critical mineral for the energy transition, and the potential for increased U.S. production to replace imports has implications for employment, manufacturing and supply-chain resilience,' USGS Director David Applegate said. 'This study illustrates the value of science in addressing economically important issues.'

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. U.S. Ambassador to Japan Rahm Emanuel accused China on Friday of using "economic coercion" against Japan by banning imports of Japanese seafood in response to the release of treated wastewater from the damaged Fukushima nuclear plant into the ocean, while Chinese boats continue to fish off Japan's coasts. "Economic coercion is the most persistent and pernicious tool in their economic toolbox," Emanuel said in a speech Friday in Tokyo, calling China's ban on Japanese seafood the latest example. China is the biggest market for Japanese seafood, and the ban has badly hurt Japan's fishing industry.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. At a small section of the Fukushima Daiichi nuclear plant's central control room, the treated water transfer switch is on. A graph on a computer monitor nearby shows a steady decrease of water levels as treated radioactive wastewater is diluted and released into the Pacific Ocean. In the coastal area of the plant, two seawater pumps are in action, gushing torrents of seawater through sky blue pipes into the big header where the treated water, which comes down through a much thinner black pipe from the hilltop tanks, is diluted hundreds of times before the release.

Fusing artificial intelligence with mathematical optimization will dramatically increase the "brainpower" for the task at hand, whether it's optimizing flight patterns or bringing energy and food to underserved areas. That's the word from the academic researchers who are part of a new interdisciplinary institute that aims to integrate the two fields. The National AI Institute for Advances in Optimization (AI4OPT) is led by a multidisciplinary team from six U.S. universities, including computer science and civil, environmental, electrical, and computer engineering professors. The combined methods will foster no less than a "paradigm shift" in optimization, said Pascal Van Hentenryck, professor of industrial and systems engineering at Georgia Tech and institute lead. According to Hentenryck, tackling problems at the scale and complexity faced by society today requires a fusion of optimization and machine learning, with the two technologies working hand-in-hand.

Tiny robots made using pollen could one day be used to clean contaminated water. Waste water from some factories contains mercury, a metal that can cause illness if consumed. There are techniques to remove mercury in water treatment plants, but they are time consuming and expensive. Martin Pumera at the University of Chemistry and Technology, Prague, in the Czech Republic, and his colleagues are working on a low-cost alternative.

We hear plenty these days about breakthroughs in green energy, robotics and communications. But as everyday technologies go, water management is virtually invisible to the general public. One organization that's working to change that is Imagine H2O, a startup accelerator based in San Francisco. A nonprofit, it provides support to emerging companies working on water problems, helping them find investors and customers. Every year, Imagine H2O hosts a competition to nurture a class of promising water entrepreneurs.

The scene around the flooded Whitehill Yeo pit in Devon, UK, resembles a lunar landscape. Until it was abandoned just a few years ago, an endless stream of diesel trucks carried china clay out of the mine seven days a week. But don't be fooled by the silence: this is very much an active site. It's just that all the excavation is happening deep beneath the placid waters. This is a test bed, the first, for a new type of mining by underwater robots.

EcoLexicon is a multilingual terminological knowledge base (TKB) on the environment. It is currently being converted into a domain-specific ontology, however, ontological properties are modelled according to surface semantics. For this reason, we are integrating our TKB in the form of a “satellite ontology” into FunGramKB, a multipurpose knowledge base specifically designed for natural language understanding. We explain how the dynamism of environmental concepts can benefit from a formal description in meaning postulates and their inclusion in FunGramKB Cognicon scripts. This would lead to the automatic generation of flexible conceptual networks and definitional templates across different contexts.