Explore the vast range of titles available.

Insect pests significantly impact global agricultural productivity and crop quality. Effective integrated pest management strategies require the identification of insects, including beneficial and harmful insects. Automated identification of insects under real-world conditions presents several challenges, including the need to handle intraspecies dissimilarity and interspecies similarity, life-cycle stages, camouflage, diverse imaging conditions, and variability in insect orientation. An end-to-end approach for training deep-learning models, InsectNet, is proposed to address these challenges. Our approach has the following key features: (i) uses a large dataset of insect images collected through citizen science along with label-free self-supervised learning to train a global model, (ii) fine-tuning this global model using smaller, expert-verified regional datasets to create a local insect identification model, (iii) which provides high prediction accuracy even for species with small sample sizes, (iv) is designed to enhance model trustworthiness, and (v) democratizes access through streamlined machine learning operations. This global-to-local model strategy offers a more scalable and economically viable solution for implementing advanced insect identification systems across diverse agricultural ecosystems. We report accurate identification (>96% accuracy) of numerous agriculturally and ecologically relevant insect species, including pollinators, parasitoids, predators, and harmful insects. InsectNet provides fine-grained insect species identification, works effectively in challenging backgrounds, and avoids making predictions when uncertain, increasing its utility and trustworthiness. The model and associated workflows are available through a web-based portal accessible through a computer or mobile device. We envision InsectNet to complement existing approaches, and be part of a growing suite of AI technologies for addressing agricultural challenges.

The rapid global loss of biodiversity, particularly among insects, represents an urgent ecological crisis. Current methods for insect species discovery are manual, slow, and severely constrained by taxonomic expertise, hindering timely conservation actions. We introduce TerraIncognita, a dynamic benchmark designed to evaluate state-of-the-art multimodal models for the challenging problem of identifying unknown, potentially undescribed insect species from image data. Our benchmark dataset combines a mix of expertly annotated images of insect species likely known to frontier AI models, and images of rare and poorly known species, for which few/no publicly available images exist. These images were collected from underexplored biodiversity hotspots, realistically mimicking open-world discovery scenarios faced by ecologists. The benchmark assesses models' proficiency in hierarchical taxonomic classification, their capability to detect and abstain from out-of-distribution (OOD) samples representing novel species, and their ability to generate explanations aligned with expert taxonomic knowledge. Notably, top-performing models achieve over 90\\% F1 at the Order level on known species, but drop below 2\\% at the Species level, highlighting the sharp difficulty gradient from coarse to fine taxonomic prediction (Order \\(\\) Family \\(\\) Genus \\(\\) Species). TerraIncognita will be updated regularly, and by committing to quarterly dataset expansions (of both known and novel species), will provide an evolving platform for longitudinal benchmarking of frontier AI methods. All TerraIncognita data, results, and future updates are available https://baskargroup.github.io/TerraIncognita/here.

We introduce BioTrove, the largest publicly accessible dataset designed to advance AI applications in biodiversity. Curated from the iNaturalist platform and vetted to include only research-grade data, BioTrove contains 161.9 million images, offering unprecedented scale and diversity from three primary kingdoms: Animalia (\"animals\"), Fungi (\"fungi\"), and Plantae (\"plants\"), spanning approximately 366.6K species. Each image is annotated with scientific names, taxonomic hierarchies, and common names, providing rich metadata to support accurate AI model development across diverse species and ecosystems. We demonstrate the value of BioTrove by releasing a suite of CLIP models trained using a subset of 40 million captioned images, known as BioTrove-Train. This subset focuses on seven categories within the dataset that are underrepresented in standard image recognition models, selected for their critical role in biodiversity and agriculture: Aves (\"birds\"), Arachnida (\"spiders/ticks/mites\"), Insecta (\"insects\"), Plantae (\"plants\"), Fungi (\"fungi\"), Mollusca (\"snails\"), and Reptilia (\"snakes/lizards\"). To support rigorous assessment, we introduce several new benchmarks and report model accuracy for zero-shot learning across life stages, rare species, confounding species, and multiple taxonomic levels. We anticipate that BioTrove will spur the development of AI models capable of supporting digital tools for pest control, crop monitoring, biodiversity assessment, and environmental conservation. These advancements are crucial for ensuring food security, preserving ecosystems, and mitigating the impacts of climate change. BioTrove is publicly available, easily accessible, and ready for immediate use.

We introduce Arboretum, the largest publicly accessible dataset designed to advance AI for biodiversity applications. This dataset, curated from the iNaturalist community science platform and vetted by domain experts to ensure accuracy, includes 134.6 million images, surpassing existing datasets in scale by an order of magnitude. The dataset encompasses image-language paired data for a diverse set of species from birds (Aves), spiders/ticks/mites (Arachnida), insects (Insecta), plants (Plantae), fungus/mushrooms (Fungi), snails (Mollusca), and snakes/lizards (Reptilia), making it a valuable resource for multimodal vision-language AI models for biodiversity assessment and agriculture research. Each image is annotated with scientific names, taxonomic details, and common names, enhancing the robustness of AI model training. We showcase the value of Arboretum by releasing a suite of CLIP models trained using a subset of 40 million captioned images. We introduce several new benchmarks for rigorous assessment, report accuracy for zero-shot learning, and evaluations across life stages, rare species, confounding species, and various levels of the taxonomic hierarchy. We anticipate that Arboretum will spur the development of AI models that can enable a variety of digital tools ranging from pest control strategies, crop monitoring, and worldwide biodiversity assessment and environmental conservation. These advancements are critical for ensuring food security, preserving ecosystems, and mitigating the impacts of climate change. Arboretum is publicly available, easily accessible, and ready for immediate use. Please see the https://baskargroup.github.io/Arboretum/project website for links to our data, models, and code.

Insect-pests significantly impact global agricultural productivity and quality. Effective management involves identifying the full insect community, including beneficial insects and harmful pests, to develop and implement integrated pest management strategies. Automated identification of insects under real-world conditions presents several challenges, including differentiating similar-looking species, intra-species dissimilarity and inter-species similarity, several life cycle stages, camouflage, diverse imaging conditions, and variability in insect orientation. A deep-learning model, InsectNet, is proposed to address these challenges. InsectNet is endowed with five key features: (a) utilization of a large dataset of insect images collected through citizen science; (b) label-free self-supervised learning for large models; (c) improving prediction accuracy for species with a small sample size; (d) enhancing model trustworthiness; and (e) democratizing access through streamlined MLOps. This approach allows accurate identification (>96% accuracy) of over 2500 insect species, including pollinator (e.g., butterflies, bees), parasitoid (e.g., some wasps and flies), predator species (e.g., lady beetles, mantises, dragonflies) and harmful pest species (e.g., armyworms, cutworms, grasshoppers, stink bugs). InsectNet can identify invasive species, provide fine-grained insect species identification, and work effectively in challenging backgrounds. It also can abstain from making predictions when uncertain, facilitating seamless human intervention and making it a practical and trustworthy tool. InsectNet can guide citizen science data collection, especially for invasive species where early detection is crucial. Similar approaches may transform other agricultural challenges like disease detection and underscore the importance of data collection, particularly through citizen science efforts..

Early identification of weeds is essential for effective management and control, and there is growing interest in automating the process using computer vision techniques coupled with AI methods. However, challenges associated with training AI-based weed identification models, such as limited expert-verified data and complexity and variability in morphological features, have hindered progress. To address these issues, we present WeedNet, the first global-scale weed identification model capable of recognizing an extensive set of weed species, including noxious and invasive plant species. WeedNet is an end-to-end real-time weed identification pipeline and uses self-supervised learning, fine-tuning, and enhanced trustworthiness strategies. WeedNet achieved 91.02% accuracy across 1,593 weed species, with 41% species achieving 100% accuracy. Using a fine-tuning strategy and a Global-to-Local approach, the local Iowa WeedNet model achieved an overall accuracy of 97.38% for 85 Iowa weeds, most classes exceeded a 90% mean accuracy per class. Testing across intra-species dissimilarity (developmental stages) and inter-species similarity (look-alike species) suggests that diversity in the images collected, spanning all the growth stages and distinguishable plant characteristics, is crucial in driving model performance. The generalizability and adaptability of the Global WeedNet model enable it to function as a foundational model, with the Global-to-Local strategy allowing fine-tuning for region-specific weed communities. Additional validation of drone- and ground-rover-based images highlights the potential of WeedNet for integration into robotic platforms. Furthermore, integration with AI for conversational use provides intelligent agricultural and ecological conservation consulting tools for farmers, agronomists, researchers, land managers, and government agencies across diverse landscapes.

As the first-line drug to treat ulcerative colitis (UC), long-term use of glucocorticoids (GCs) produces severe toxic and side effects. Local administration as enema can increase the local GCs concentrations and reduce systemic exposure to high oral doses by directly delivering GCs to the inflammation site in the distal colorectum. However, UC patients are often accompanied by diarrhea, leading to the short colonic residence time of GCs and failure to exert their function fully. A kind of mucoadhesive nanoparticles (NPs) loading different dexamethasone derivatives (DDs) were developed, which could attach to the positively charged inflammatory colonic mucosa through electrostatic adsorption after administered by enema, thereby improving the local concentration and achieving effective targeted therapy for UC. Two DDs, dexamethasone hemisuccinate and dexamethasone phosphate, were synthesized. In NPs preparation, The core PEI-DDs NPs were built by the electrostatic adsorption of DDs and the cationic polymer polyethyleneimine (PEI). Then, the natural polyanionic polysaccharide sodium alginate (SA) was electronically coated around NPs to construct the final SA-PEI-DDs NPs, followed by the in vitro stability and release tests, in vitro and in vivo colonic mucosal adhesion tests. In the in vivo anti-UC test, the experimental colitis mice were induced by 2,4,6-trinitrobenzenesulfonic acid. The body weight and disease activity index changes were measured, and the myeloperoxidase activity, pro-inflammatory cytokines concentration, and hematoxylin and eosin staining were also investigated to evaluate the therapeutic effect of NPs. The structures of two DDs were demonstrated by H-NMR and MS. Both NPs were negatively charged and achieved high loading efficiency of DDs, while their particle sizes were significantly different. NPs showed good stability and sustained release properties in the simulated colonic environment. Moreover, the negative charge on the of NPs surface made them easier to adhere to the positively charged inflammatory colonic mucosa, thereby enhancing the enrichment and retention of DDS in the colitis site. Furthermore, the NPs exhibited better therapeutic effects than free Dex on the experimental colitis mice induced by TNBS through the enema rectal. These results indicated the mucoadhesive NPs as a kind of novel nano-enema showed great potential to achieve efficient treatment on UC.

The M1/M2 polarization of intestinal macrophages exerts an essential function in the pathogenesis of ulcerative colitis (UC), which can be adjusted to alleviate the UC symptoms. A kind of pH-sensitive lipid calcium phosphate core-shell nanoparticles (NPs), co-loading with dexamethasone (Dex) and its water-soluble salts, dexamethasone sodium phosphate (Dsp), was constructed to comprehensively regulate macrophages in different states towards the M2 phenotype to promote anti-inflammatory effects. Dex and Dsp were loaded in the outer lipid shell and inner lipid calcium phosphate (Cap) core of the L CaP NPs, respectively. Then, the morphology of NPs and methods for determining drug concentration were investigated, followed by in vitro protein adsorption, stability, and release tests. Cell experiments evaluated the cytotoxicity, cellular uptake, and macrophage polarization induction ability of NPs. The in vivo distribution and anti-inflammatory effect of NPs were evaluated through a 2,4,6-trinitrobenzene sulfonic acid (TNBS)-induced BALB/c mice ulcerative colitis model. The L CaP NPs showed a particle size of about 200 nm and achieved considerable loading amounts of Dex and Dsp. The in vitro and in vivo studies revealed that in the acidic UC microenvironment, the cationic lipid shell of L CaP underwent protonated dissociation to release Dex first for creating a microenvironment conducive to M2 polarization. Then, the exposed CaP core was further engulfed by M1 macrophages to release Dsp to restrict the pro-inflammatory cytokines production by inhibiting the activation and function of the nuclear factor kappa-B (NF-κB) through activating the GC receptor and the NF kappa B inhibitor α (I-κBα), respectively, ultimately reversing the M1 polarization to promote the anti-inflammatory therapy. The L CaP NPs accomplished the sequential release of Dex and Dsp to the UC site and the inflammatory M1 macrophages at this site, promoting the regulation of macrophage polarization to accelerate the remission of UC symptoms.

Dermal adipose tissue (also known as dermal white adipose tissue and herein referred to as dWAT) has been the focus of much discussion in recent years. However, dWAT remains poorly characterized. The fate of the mature dermal adipocytes and the origin of the rapidly reappearing dermal adipocytes at different stages remain unclear. Here, we isolated dermal adipocytes and characterized dermal fat at the cellular and molecular level. Together with dWAT's dynamic responses to external stimuli, we established that dermal adipocytes are a distinct class of white adipocytes with high plasticity. By combining pulse-chase lineage tracing and single-cell RNA sequencing, we observed that mature dermal adipocytes undergo dedifferentiation and redifferentiation under physiological and pathophysiological conditions. Upon various challenges, the dedifferentiated cells proliferate and redifferentiate into adipocytes. In addition, manipulation of dWAT highlighted an important role for mature dermal adipocytes for hair cycling and wound healing. Altogether, these observations unravel a surprising plasticity of dermal adipocytes and provide an explanation for the dynamic changes in dWAT mass that occur under physiological and pathophysiological conditions, and highlight the important contributions of dWAT toward maintaining skin homeostasis.

Colon cancer is one of the most common malignancies and the treatments for colon cancer have been developed substantially in the last decades, but there is still a great clinical need to explore new treatment regimens due to the undesirable prognosis. In this investigation, we demonstrated the anti-proliferative and apoptosis-inducing activities of resveratrol (Res) in human colon cancer cells, and the possible mechanisms underlying these effects. We used crystal violet staining, flow cytometry and western blotting to validate the anti-proliferative and apoptosis-inducing effects of Res on HCT116 cells. A xenograft tumor model was used to confirm the anti-proliferative effects of Res. We employed polymerase chain reaction, western blotting, recombinant adenovirus and luciferase reporter assay to explore the possible mechanism(s) of action. We found that Res inhibits significantly the proliferation and promotes apoptosis in HCT116 cells, as well as inhibits the xenograft tumor growth of colon cancer. Res upregulates the expression of phosphatase and tensin homolog (PTEN) and decreases the phosphorylation of Akt1/2. The exogenous expression of PTEN inhibits the PI3K/Akt signal and promotes the anti-proliferative effects of Res in HCT116 cells, while knockdown of PTEN increases PI3K/Akt signal but reduces the anti-proliferative function of Res. The protein and mRNA expression of β-catenin are all decreased by Res concentration-dependently. Thus, our findings strongly suggest that the anti-proliferative effects of Res in human colon cancer cells may be mediated by regulating separately the PTEN/PI3K/Akt and Wnt/β-catenin signaling.