Scientific discovery in the age of artificial intelligence.

Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, helping scientists to generate hypotheses, design experiments, collect and interpret large datasets, and gain insights that might not have been possible using traditional scientific methods alone. Here we examine breakthroughs over the past decade that include self-supervised learning, which allows models to be trained on vast amounts of unlabelled data, and geometric deep learning, which leverages knowledge about the structure of scientific data to enhance model accuracy and efficiency. Generative AI methods can create designs, such as small-molecule drugs and proteins, by analysing diverse data modalities, including images and sequences. We discuss how these methods can help scientists throughout the scientific process and the central issues that remain despite such advances. Both developers and users of AI toolsneed a better understanding of when such approaches need improvement, and challenges posed by poor data quality and stewardship remain. These issues cut across scientific disciplines and require developing foundational algorithmic approaches that can contribute to scientific understanding or acquire it autonomously, making them critical areas of focus for AI innovation.

Reserve design to optimize functional connectivity and animal density.

Ecological distance-based spatial capture-recapture models (SCR) are a promising approach for simultaneously estimating animal density and connectivity, both of which affect spatial population processes and ultimately species persistence. We explored how SCR models can be integrated into reserve-design frameworks that explicitly acknowledge both the spatial distribution of individuals and their space use resulting from landscape structure. We formulated the design of wildlife reserves as a budget-constrained optimization problem and conducted a simulation to explore 3 different SCR-informed optimization objectives that prioritized different conservation goals by maximizing the number of protected individuals, reserve connectivity, and density-weighted connectivity. We also studied the effect on our 3 objectives of enforcing that the space-use requirements of individuals be met by the reserve for individuals to be considered conserved (referred to as home-range constraints). Maximizing local population density resulted in fragmented reserves that would likely not aid long-term population persistence, and maximizing the connectivity objective yielded reserves that protected the fewest individuals. However, maximizing density-weighted connectivity or preemptively imposing home-range constraints on reserve design yielded reserves of largely spatially compact sets of parcels covering high-density areas in the landscape with high functional connectivity between them. Our results quantify the extent to which reserve design is constrained by individual home-range requirements and highlight that accounting for individual space use in the objective and constraints can help in the design of reserves that balance abundance and connectivity in a biologically relevant manner.

Diseño de Reservas para Optimizar la Conectividad Funcional y la Densidad Animal Resumen Los modelos de captura-recaptura espacial (CRE) basados en distancias ecológicas son un método prometedor para estimar la densidad animal y la conectividad, las cuales afectan los procesos poblacionales espaciales y, en última instancia, la persistencia de las especies. Exploramos cómo se puede integrar a los modelos CRE en los marcos de diseño de reserva que explícitamente reconocen tanto la distribución espacial de los individuos como su uso del espacio resultante de la estructura del paisaje. Formulamos el diseño de reservas de vida silvestre como un problema de optimización de presupuesto limitado y realizamos una simulación para explorar 3 diferentes objetivos de optimización informados por CRE que priorizaron diferentes metas de conservación mediante la maximización del número de individuos protegidos; la conectividad de la reserva y la conectividad ponderada por la densidad. También estudiamos el efecto sobre nuestros objetivos de hacer que los requerimientos individuales de uso de espacio fuesen satisfechos por la reserva de manera que se pudiese considerar que los individuos estaban protegidos (referidos como restricciones de rango de hogar). La maximización de la densidad de la población local resultó en reservas fragmentadas que probablemente no contribuyan a la persistencia de la población a largo plazo, mientras que la maximización de la conectividad produjo reservas que protegían al menor número de individuos. Sin embargo, la maximización de la conectividad ponderada por la densidad o la imposición preventiva de restricciones de rango de hogar en el diseño de reservas produjo reservas compuestas por conjuntos de parcelas mayormente compactas espacialmente que cubrían áreas de densidad alta en el paisaje con alta conectividad funcional entre ellas. Nuestros resultados cuantifican la extensión a la cual el diseño de reservas esta limitado por los requerimientos de rango de hogar individuales y resaltan que la consideración del uso de espacio individual en el objetivo y limitaciones puede ayudar al diseño de reservas que equilibren la abundancia y la conectividad de manera biológicamente relevante.

Trade-offs and efficiencies in optimal budget-constrained multispecies corridor networks.

Conservation biologists recognize that a system of isolated protected areas will be necessary but insufficient to meet biodiversity objectives. Current approaches to connecting core conservation areas through corridors consider optimal corridor placement based on a single optimization goal: commonly, maximizing the movement for a target species across a network of protected areas. We show that designing corridors for single species based on purely ecological criteria leads to extremely expensive linkages that are suboptimal for multispecies connectivity objectives. Similarly, acquiring the least-expensive linkages leads to ecologically poor solutions. We developed algorithms for optimizing corridors for multispecies use given a specific budget. We applied our approach in western Montana to demonstrate how the solutions may be used to evaluate trade-offs in connectivity for 2 species with different habitat requirements, different core areas, and different conservation values under different budgets. We evaluated corridors that were optimal for each species individually and for both species jointly. Incorporating a budget constraint and jointly optimizing for both species resulted in corridors that were close to the individual species movement-potential optima but with substantial cost savings. Our approach produced corridors that were within 14% and 11% of the best possible corridor connectivity for grizzly bears (Ursus arctos) and wolverines (Gulo gulo), respectively, and saved 75% of the cost. Similarly, joint optimization under a combined budget resulted in improved connectivity for both species relative to splitting the budget in 2 to optimize for each species individually. Our results demonstrate economies of scale and complementarities conservation planners can achieve by optimizing corridor designs for financial costs and for multiple species connectivity jointly. We believe that our approach will facilitate corridor conservation by reducing acquisition costs and by allowing derived corridors to more closely reflect conservation priorities.

Delivery of Splice Switching Oligonucleotides by Amphiphilic Chitosan-Based Nanoparticles.

Splice switching oligonucleotides (SSOs) are a class of single-stranded antisense oligonucleotides (ssONs) being used as gene therapeutics and demonstrating great therapeutic potential. The availability of biodegradable and biocompatible delivery vectors that could improve delivery efficiencies, reduce dosage, and, in parallel, reduce toxicity concerns could be advantageous for clinical translation. In this work we explored the use of quaternized amphiphilic chitosan-based vectors in nanocomplex formation and delivery of splice switching oligonucleotides (SSO) into cells, while providing insights regarding cellular uptake of such complexes. Results show that the chitosan amphiphilic character is important when dealing with SSOs, greatly improving colloidal stability under serum conditions, as analyzed by dynamic light scattering, and enhancing cellular association. Nanocomplexes were found to follow an endolysosomal route with a long lysosome residence time. Conjugation of a hydrophobic moiety, stearic acid, to quaternized chitosan was a necessary condition to achieve transfection, as an unmodified quaternary chitosan was completely ineffective. We thus demonstrate that amphiphilic quaternized chitosan is a biomaterial that holds promise and warrants further development as a platform for SSO delivery strategies.

Deep learning with citizen science data enables estimation of species diversity and composition at continental extents.

Effective solutions to conserve biodiversity require accurate community- and species-level information at relevant, actionable scales and across entire species' distributions. However, data and methodological constraints have limited our ability to provide such information in robust ways. Herein we employ a Deep-Reasoning Network implementation of the Deep Multivariate Probit Model (DMVP-DRNets), an end-to-end deep neural network framework, to exploit large observational and environmental data sets together and estimate landscape-scale species diversity and composition at continental extents. We present results from a novel year-round analysis of North American avifauna using data from over nine million eBird checklists and 72 environmental covariates. We highlight the utility of our information by identifying critical areas of high species diversity for a single group of conservation concern, the North American wood warblers, while capturing spatiotemporal variation in species' environmental associations and interspecific interactions. In so doing, we demonstrate the type of accurate, high-resolution information on biodiversity that deep learning approaches such as DMVP-DRNets can provide and that is needed to inform ecological research and conservation decision-making at multiple scales.

Deeper habitats and cooler temperatures moderate a climate-driven seagrass disease.

Eelgrass creates critical coastal habitats worldwide and fulfills essential ecosystem functions as a foundation seagrass. Climate warming and disease threaten eelgrass, causing mass mortalities and cascading ecological impacts. Subtidal meadows are deeper than intertidal and may also provide refuge from the temperature-sensitive seagrass wasting disease. From cross-boundary surveys of 5761 eelgrass leaves from Alaska to Washington and assisted with a machine-language algorithm, we measured outbreak conditions. Across summers 2017 and 2018, disease prevalence was 16% lower for subtidal than intertidal leaves; in both tidal zones, disease risk was lower for plants in cooler conditions. Even in subtidal meadows, which are more environmentally stable and sheltered from temperature and other stressors common for intertidal eelgrass, we observed high disease levels, with half of the sites exceeding 50% prevalence. Models predicted reduced disease prevalence and severity under cooler conditions, confirming a strong interaction between disease and temperature. At both tidal zones, prevalence was lower in more dense eelgrass meadows, suggesting disease is suppressed in healthy, higher density meadows. These results underscore the value of subtidal eelgrass and meadows in cooler locations as refugia, indicate that cooling can suppress disease, and have implications for eelgrass conservation and management under future climate change scenarios. This article is part of the theme issue 'Infectious disease ecology and evolution in a changing world'.

Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings.

Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec's ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.

Reducing adverse impacts of Amazon hydropower expansion.

Proposed hydropower dams at more than 350 sites throughout the Amazon require strategic evaluation of trade-offs between the numerous ecosystem services provided by Earth's largest and most biodiverse river basin. These services are spatially variable, hence collective impacts of newly built dams depend strongly on their configuration. We use multiobjective optimization to identify portfolios of sites that simultaneously minimize impacts on river flow, river connectivity, sediment transport, fish diversity, and greenhouse gas emissions while achieving energy production goals. We find that uncoordinated, dam-by-dam hydropower expansion has resulted in forgone ecosystem service benefits. Minimizing further damage from hydropower development requires considering diverse environmental impacts across the entire basin, as well as cooperation among Amazonian nations. Our findings offer a transferable model for the evaluation of hydropower expansion in transboundary basins.

Data-Driven Modeling of the Cellular Pharmacokinetics of Degradable Chitosan-Based Nanoparticles.

Nanoparticle drug delivery vehicles introduce multiple pharmacokinetic processes, with the delivery, accumulation, and stability of the therapeutic molecule influenced by nanoscale processes. Therefore, considering the complexity of the multiple interactions, the use of data-driven models has critical importance in understanding the interplay between controlling processes. We demonstrate data simulation techniques to reproduce the time-dependent dose of trimethyl chitosan nanoparticles in an ND7/23 neuronal cell line, used as an in vitro model of native peripheral sensory neurons. Derived analytical expressions of the mean dose per cell accurately capture the pharmacokinetics by including a declining delivery rate and an intracellular particle degradation process. Comparison with experiment indicates a supply time constant, τ = 2 h. and a degradation rate constant, b = 0.71 h-1. Modeling the dose heterogeneity uses simulated data distributions, with time dependence incorporated by transforming data-bin values. The simulations mimic the dynamic nature of cell-to-cell dose variation and explain the observed trend of increasing numbers of high-dose cells at early time points, followed by a shift in distribution peak to lower dose between 4 to 8 h and a static dose profile beyond 8 h.

Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams.

Autonomous experimentation enabled by artificial intelligence offers a new paradigm for accelerating scientific discovery. Nonequilibrium materials synthesis is emblematic of complex, resource-intensive experimentation whose acceleration would be a watershed for materials discovery. We demonstrate accelerated exploration of metastable materials through hierarchical autonomous experimentation governed by the Scientific Autonomous Reasoning Agent (SARA). SARA integrates robotic materials synthesis using lateral gradient laser spike annealing and optical characterization along with a hierarchy of AI methods to map out processing phase diagrams. Efficient exploration of the multidimensional parameter space is achieved with nested active learning cycles built upon advanced machine learning models that incorporate the underlying physics of the experiments and end-to-end uncertainty quantification. We demonstrate SARA's performance by autonomously mapping synthesis phase boundaries for the Bi2O3 system, leading to orders-of-magnitude acceleration in the establishment of a synthesis phase diagram that includes conditions for stabilizing δ-Bi2O3 at room temperature, a critical development for electrochemical technologies.

Optical Identification of Materials Transformations in Oxide Thin Films.

Recent advances in high-throughput experimentation for combinatorial studies have accelerated the discovery and analysis of materials across a wide range of compositions and synthesis conditions. However, many of the more powerful characterization methods are limited by speed, cost, availability, and/or resolution. To make efficient use of these methods, there is value in developing approaches for identifying critical compositions and conditions to be used as a priori knowledge for follow-up characterization with high-precision techniques, such as micrometer-scale synchrotron-based X-ray diffraction (XRD). Here, we demonstrate the use of optical microscopy and reflectance spectroscopy to identify likely phase-change boundaries in thin film libraries. These methods are used to delineate possible metastable phase boundaries following lateral-gradient laser spike annealing (lg-LSA) of oxide materials. The set of boundaries are then compared with definitive determinations of structural transformations obtained using high-resolution XRD. We demonstrate that the optical methods detect more than 95% of the structural transformations in a composition-gradient La-Mn-O library and a Ga2O3 sample, both subject to an extensive set of lg-LSA anneals. Our results provide quantitative support for the value of optically detected transformations as a priori data to guide subsequent structural characterization, ultimately accelerating and enhancing the efficient implementation of micrometer-resolution XRD experiments.

Molecular Recognition Force Spectroscopy for Probing Cell Targeted Nanoparticles In Vitro.

In the development and design of cell targeted nanoparticle-based systems the density of targeting moieties plays a fundamental role in allowing maximal cell-specific interaction. Here, we describe the use of molecular recognition force spectroscopy as a valuable tool for the characterization and optimization of targeted nanoparticles toward attaining cell-specific interaction. By tailoring the density of targeting moieties at the nanoparticle surface, one can correlate the unbinding event probability between nanoparticles tethered to an atomic force microscopy tip and cells to the nanoparticle vectoring capacity. This novel approach allows for a rapid and cost-effective design of targeted nanomedicines reducing the need for long and tedious in vitro tests.

Reducing greenhouse gas emissions of Amazon hydropower with strategic dam planning.

Hundreds of dams have been proposed throughout the Amazon basin, one of the world's largest untapped hydropower frontiers. While hydropower is a potentially clean source of renewable energy, some projects produce high greenhouse gas (GHG) emissions per unit electricity generated (carbon intensity). Here we show how carbon intensities of proposed Amazon upland dams (median = 39 kg CO2eq MWh-1, 100-year horizon) are often comparable with solar and wind energy, whereas some lowland dams (median = 133 kg CO2eq MWh-1) may exceed carbon intensities of fossil-fuel power plants. Based on 158 existing and 351 proposed dams, we present a multi-objective optimization framework showing that low-carbon expansion of Amazon hydropower relies on strategic planning, which is generally linked to placing dams in higher elevations and smaller streams. Ultimately, basin-scale dam planning that considers GHG emissions along with social and ecological externalities will be decisive for sustainable energy development where new hydropower is contemplated.

Atomic Force Microscopy as a Tool to Assess the Specificity of Targeted Nanoparticles in Biological Models of High Complexity.

The ability to design nanoparticle delivery systems capable of selectively target their payloads to specific cell populations is still a major caveat in nanomedicine. One of the main hurdles is the fact that each nanoparticle formulation needs to be precisely tuned to match the specificities of the target cell and route of administration. In this work, molecular recognition force spectroscopy (MRFS) is presented as a tool to evaluate the specificity of neuron-targeted trimethyl chitosan nanoparticles to neuronal cell populations in biological samples of different complexity. The use of atomic force microscopy tips functionalized with targeted or non-targeted nanoparticles made it possible to assess the specific interaction of each formulation with determined cell surface receptors in a precise fashion. More importantly, the combination of MRFS with fluorescent microscopy allowed to probe the nanoparticles vectoring capacity in models of high complexity, such as primary mixed cultures, as well as specific subcellular regions in histological tissues. Overall, this work contributes for the establishment of MRFS as a powerful alternative technique to animal testing in vector design and opens new avenues for the development of advanced targeted nanomedicines.

BDNF gene delivery mediated by neuron-targeted nanoparticles is neuroprotective in peripheral nerve injury.

Neuron-targeted gene delivery is a promising strategy to treat peripheral neuropathies. Here we propose the use of polymeric nanoparticles based on thiolated trimethyl chitosan (TMCSH) to mediate targeted gene delivery to peripheral neurons upon a peripheral and minimally invasive intramuscular administration. Nanoparticles were grafted with the non-toxic carboxylic fragment of the tetanus neurotoxin (HC) to allow neuron targeting and were explored to deliver a plasmid DNA encoding for the brain-derived neurotrophic factor (BDNF) in a peripheral nerve injury model. The TMCSH-HC/BDNF nanoparticle treatment promoted the release and significant expression of BDNF in neural tissues, which resulted in an enhanced functional recovery after injury as compared to control treatments (vehicle and non-targeted nanoparticles), associated with an improvement in key pro-regenerative events, namely, the increased expression of neurofilament and growth-associated protein GAP-43 in the injured nerves. Moreover, the targeted nanoparticle treatment was correlated with a significantly higher density of myelinated axons in the distal stump of injured nerves, as well as with preservation of unmyelinated axon density as compared with controls and a protective role in injury-denervated muscles, preventing them from denervation. These results highlight the potential of TMCSH-HC nanoparticles as non-viral gene carriers to deliver therapeutic genes into the peripheral neurons and thus, pave the way for their use as an effective therapeutic intervention for peripheral neuropathies.

Automated Phase Mapping with AgileFD and its Application to Light Absorber Discovery in the V-Mn-Nb Oxide System.

Rapid construction of phase diagrams is a central tenet of combinatorial materials science with accelerated materials discovery efforts often hampered by challenges in interpreting combinatorial X-ray diffraction data sets, which we address by developing AgileFD, an artificial intelligence algorithm that enables rapid phase mapping from a combinatorial library of X-ray diffraction patterns. AgileFD models alloying-based peak shifting through a novel expansion of convolutional nonnegative matrix factorization, which not only improves the identification of constituent phases but also maps their concentration and lattice parameter as a function of composition. By incorporating Gibbs' phase rule into the algorithm, physically meaningful phase maps are obtained with unsupervised operation, and more refined solutions are attained by injecting expert knowledge of the system. The algorithm is demonstrated through investigation of the V-Mn-Nb oxide system where decomposition of eight oxide phases, including two with substantial alloying, provides the first phase map for this pseudoternary system. This phase map enables interpretation of high-throughput band gap data, leading to the discovery of new solar light absorbers and the alloying-based tuning of the direct-allowed band gap energy of MnV2O6. The open-source family of AgileFD algorithms can be implemented into a broad range of high throughput workflows to accelerate materials discovery.

Microfluidic-based platform to mimic the in vivo peripheral administration of neurotropic nanoparticles.

AIM: Propose a nanoparticle for neuron-targeted retrograde gene delivery and describe a microfluidic-based culture system to provide insight into vector performance and safety. METHODS: Using compartmentalized neuron cultures we dissected nanoparticle bioactivity upon delivery taking advantage of (quantitative) bioimaging tools. RESULTS: Targeted and nontargeted nanoparticles were internalized at axon terminals and retrogradely transported to cell bodies at similar average velocities but the former have shown an axonal flux 2.7-times superior to nontargeted nanoparticles, suggesting an improved cargo-transportation efficiency. The peripheral administration of nanoparticles to axon terminals is nontoxic as compared with their direct administration to the cell body or whole neuron. CONCLUSION: A neuron-targeted nanoparticle system was put forward. Microfluidic-based neuron cultures are proposed as a powerful tool to investigate nanoparticle bio-performance.