Explore the vast range of titles available.

Histopathology is essential for disease diagnosis and treatment decision-making. Recent advances in artificial intelligence (AI) have enabled the development of pathology foundation models that learn rich visual representations from large-scale whole-slide images (WSIs). However, existing models are often trained on disparate datasets using varying strategies, leading to inconsistent performance and limited generalizability. Here, we introduce ELF (Ensemble Learning of Foundation models), a novel framework that integrates five state-of-the-art pathology foundation models to generate unified slide-level representations. Trained on 53,699 WSIs spanning 20 anatomical sites, ELF leverages ensemble learning to capture complementary information from diverse models while maintaining high data efficiency. Unlike traditional tile-level models, ELF's slide-level architecture is particularly advantageous in clinical contexts where data are limited, such as therapeutic response prediction. We evaluated ELF across a wide range of clinical applications, including disease classification, biomarker detection, and response prediction to major anticancer therapies, cytotoxic chemotherapy, targeted therapy, and immunotherapy, across multiple cancer types. ELF consistently outperformed all constituent foundation models and existing slide-level models, demonstrating superior accuracy and robustness. Our results highlight the power of ensemble learning for pathology foundation models and suggest ELF as a scalable and generalizable solution for advancing AI-assisted precision oncology.

The NLRP3 inflammasome is a critical component of the innate immune system that mediates caspase-1 activation and the secretion of proinflammatory cytokines IL-1β/IL-18 in response to microbial infection and cellular damage. However, the aberrant activation of the NLRP3 inflammasome has been linked with several inflammatory disorders, which include cryopyrin-associated periodic syndromes, Alzheimer's disease, diabetes, and atherosclerosis. The NLRP3 inflammasome is activated by diverse stimuli, and multiple molecular and cellular events, including ionic flux, mitochondrial dysfunction, and the production of reactive oxygen species, and lysosomal damage have been shown to trigger its activation. How NLRP3 responds to those signaling events and initiates the assembly of the NLRP3 inflammasome is not fully understood. In this review, we summarize our current understanding of the mechanisms of NLRP3 inflammasome activation by multiple signaling events, and its regulation by post-translational modifications and interacting partners of NLRP3.

Single-cell assay for transposase-accessible chromatin using sequencing (scATAC) shows great promise for studying cellular heterogeneity in epigenetic landscapes, but there remain important challenges in the analysis of scATAC data due to the inherent high dimensionality and sparsity. Here we introduce scBasset, a sequence-based convolutional neural network method to model scATAC data. We show that by leveraging the DNA sequence information underlying accessibility peaks and the expressiveness of a neural network model, scBasset achieves state-of-the-art performance across a variety of tasks on scATAC and single-cell multiome datasets, including cell clustering, scATAC profile denoising, data integration across assays and transcription factor activity inference. Using a sequence-based deep neural network, scBasset facilitates various tasks of single-cell ATAC-seq analysis in a unified framework.

Sequence-based machine-learning models trained on genomics data improve genetic variant interpretation by providing functional predictions describing their impact on the cis -regulatory code. However, current tools do not predict RNA-seq expression profiles because of modeling challenges. Here, we introduce Borzoi, a model that learns to predict cell-type-specific and tissue-specific RNA-seq coverage from DNA sequence. Using statistics derived from Borzoi’s predicted coverage, we isolate and accurately score DNA variant effects across multiple layers of regulation, including transcription, splicing and polyadenylation. Evaluated on quantitative trait loci, Borzoi is competitive with and often outperforms state-of-the-art models trained on individual regulatory functions. By applying attribution methods to the derived statistics, we extract cis -regulatory motifs driving RNA expression and post-transcriptional regulation in normal tissues. The wide availability of RNA-seq data across species, conditions and assays profiling specific aspects of regulation emphasizes the potential of this approach to decipher the mapping from DNA sequence to regulatory function. Borzoi adapts the Enformer sequence-to-expression model to directly predict RNA-seq coverage, enabling the in-silico analysis of variant effects across multiple layers of gene regulation.

Low-dimensional perovskites have—in view of their high radiative recombination rates—shown great promise in achieving high luminescence brightness and colour saturation. Here we investigate the effect of electron–phonon interactions on the luminescence of single crystals of two-dimensional perovskites, showing that reducing these interactions can lead to bright blue emission in two-dimensional perovskites. Resonance Raman spectra and deformation potential analysis show that strong electron–phonon interactions result in fast non-radiative decay, and that this lowers the photoluminescence quantum yield (PLQY). Neutron scattering, solid-state NMR measurements of spin–lattice relaxation, density functional theory simulations and experimental atomic displacement measurements reveal that molecular motion is slowest, and rigidity greatest, in the brightest emitter. By varying the molecular configuration of the ligands, we show that a PLQY up to 79% and linewidth of 20 nm can be reached by controlling crystal rigidity and electron–phonon interactions. Designing crystal structures with electron–phonon interactions in mind offers a previously underexplored avenue to improve optoelectronic materials' performance.

Background DNA sequence deep learning models can accurately predict epigenetic and transcriptional profiles, enabling analysis of gene regulation and genetic variant effects. While large-scale models like Enformer and Borzoi are trained on abundant data, they cannot cover all cell states and assays, necessitating training new model to analyze gene regulation in novel contexts. However, training models from scratch for new datasets is computationally expensive. Results In this study, we systematically develop and evaluate a transfer learning framework based on parameter-efficient fine-tuning for supervised regulatory sequence models. Using the state-of-the-art model Borzoi, our framework enables accurate model transfer while significantly reducing runtime and memory requirements. Across bulk and single cell RNA-seq datasets, the transferred models effectively predict held-out gene expression changes, identify regulatory drivers in perturbation conditions, and predict cell-type-specific variant effects. We further demonstrate that transferring Borzoi to relevant cell types facilitates mechanistic interpretation of fine-mapped GWAS variants. Conclusions Our framework offers a scalable and practical solution for extending large sequence models to novel biological contexts, enabling mechanistic insight into gene regulation and variant effects.

Life cycle assessment (LCA) has been used to understand the carbon and energy implications of manufacturing and using cross-laminated timber (CLT), an emerging and sustainable alternative to concrete and steel. However, previous LCAs of CLT are static analyses without considering the complex interactions between the CLT manufacturing and forest systems, which are dynamic and largely affected by the variations in forest management, CLT manufacturing, and end-of-life options. This study fills this gap by developing a dynamic life-cycle modeling framework for a cradle-to-grave CLT manufacturing system across 100 years in the Southeastern United States. The framework integrates process-based simulations of CLT manufacturing and forest growth as well as Monte Carlo simulation to address uncertainty. On a 1-ha forest land basis, the net greenhouse gas (GHG) emissions range from −954 to −1445 metric tonne CO2 eq. for a high forest productivity scenario compared to −609 to −919 metric tonne CO2 eq. for a low forest productivity scenario. All scenarios showed significant GHG emissions from forest residues decay, demonstrating the strong needs to consider forest management and their dynamic impacts in LCAs of CLT or other durable wood products (DWP). The results show that using mill residues for energy recovery has lower fossil-based GHG (59%-61% reduction) than selling residues for producing DWP, but increases the net GHG emissions due to the instantaneous release of biogenic carbon in residues. In addition, the results were converted to a 1 m3 basis with a cradle-to-gate system boundary to be compared with literature. The results, 113-375 kg CO2 eq. m−3 across all scenarios for fossil-based GHG emissions, were consistent with previous studies. Those findings highlight the needs of system-level management to maximize the potential benefits of CLT. This work is an attributional LCA, but the presented results lay a foundation for future consequential LCAs for specific CLT buildings or commercial forest management systems.

The process wherein dividing cells exhaust proliferative capacity and enter into replicative senescence has become a prominent model for cellular aging in vitro. Despite decades of study, this cellular state is not fully understood in culture and even much less so during aging. Here, we revisit Leonard Hayflick’s original observation of replicative senescence in WI-38 human lung fibroblasts equipped with a battery of modern techniques including RNA-seq, single-cell RNA-seq, proteomics, metabolomics, and ATAC-seq. We find evidence that the transition to a senescent state manifests early, increases gradually, and corresponds to a concomitant global increase in DNA accessibility in nucleolar and lamin associated domains. Furthermore, we demonstrate that senescent WI-38 cells acquire a striking resemblance to myofibroblasts in a process similar to the epithelial to mesenchymal transition (EMT) that is regulated by t YAP1/TEAD1 and TGF-β2. Lastly, we show that verteporfin inhibition of YAP1/TEAD1 activity in aged WI-38 cells robustly attenuates this gene expression program.

The prevalence of obesity has led to a surge of interest in understanding the detailed mechanisms underlying adipocyte development. Many protein-coding genes, mRNAs, and microRNAs have been implicated in adipocyte development, but the global expression patterns and functional contributions of long noncoding RNA (lncRNA) during adipogenesis have not been explored. Here we profiled the transcriptome of primary brown and white adipocytes, preadipocytes, and cultured adipocytes and identified 175 lncRNAs that are specifically regulated during adipogenesis. Many lncRNAs are adipose-enriched, strongly induced during adipogenesis, and bound at their promoters by key transcription factors such as peroxisome proliferator-activated receptor γ (PPARγ) and CCAAT/enhancer-binding protein α (CEBPα). RNAi-mediated loss of function screens identified functional lncRNAs with varying impact on adipogenesis. Collectively, we have identified numerous lncRNAs that are functionally required for proper adipogenesis.