Nature Biomedical Engineering最新文献

Immune rejection caused by mismatches in human leucocyte antigens (HLAs) remains a major obstacle to the success of allogeneic cell therapies. Current strategies for the generation of ‘universal’ immune-compatible cells, particularly the editing of HLA class I (HLA-I) genes or the modulation of proteins that inhibit natural killer cells, often result in genomic instability or cellular cytotoxicity. Here we show that a β₂-microglobulin super-enhancer (B2M-SE) that is responsive to interferon-γ is a critical regulator of the expression of HLA-I on mesenchymal stromal cells (MSCs). Targeted epigenetic repression of B2M-SE in MSCs reduced the surface expression of HLA-I below the threshold required to activate allogenic T cells while maintaining levels sufficient to evade cytotoxicity mediated by natural killer cells. In a humanized mouse model, the epigenetically edited MSCs demonstrated improved survival by evading the immune system, allowing them to exert enhanced therapeutic effects on LPS-induced acute lung injury. Targeted epigenetic repression of B2M-SE may facilitate the development of off-the-shelf cell sources for allogeneic cell therapy.

Chimeric antigen receptor (CAR) T cells targeting receptors on tumour cells have had limited success in patients with glioblastoma. Here we report the development and therapeutic performance of CAR constructs leveraging protein binders computationally designed de novo to have high affinity for the epidermal growth factor receptor (EGFR) or the tumour-associated antigen CD276, which are overexpressed in glioblastoma. With respect to T cells with a CAR using an antibody-derived single-chain variable fragment as antigen-binding domain, the designed binders on CAR T cells promoted the proliferation of the cells, the secretion of cytotoxic cytokines and their resistance to cell exhaustion, and improved antitumour performance in vitro and in vivo. Moreover, CARs with the binders exhibited higher surface expression and greater resistance to degradation, as indicated by bulk and single-cell transcriptional profiling of the cells. The de novo design of binding domains for specific tumour antigens may potentiate the antitumour efficacy of CAR T cell therapies for other solid cancers.

Tabular data—rows of samples and columns of sample features—are ubiquitously used across disciplines. Yet the tabular representation makes it difficult to discover underlying associations in the data and thus hinders their analysis and the discovery of useful patterns. Here we report a broadly applicable strategy for unravelling intertwined relationships in tabular data by reconfiguring each data sample into a spatially semantic 2D topographic map, which we refer to as TabMap. A TabMap preserves the original feature values as pixel intensities, with the relationships among the features spatially encoded in the map (the strength of two inter-related features correlates with their distance on the map). TabMap makes it possible to apply 2D convolutional neural networks to extract association patterns in the data to aid data analysis, and offers interpretability by ranking features according to importance. We show the superior predictive performance of TabMap by applying it to 12 datasets across a wide range of biomedical applications, including disease diagnosis, human activity recognition, microbial identification and the analysis of quantitative structure–activity relationships.

The application of machine learning to tasks involving volumetric biomedical imaging is constrained by the limited availability of annotated datasets of three-dimensional (3D) scans for model training. Here we report a deep-learning model pre-trained on 2D scans (for which annotated data are relatively abundant) that accurately predicts disease-risk factors from 3D medical-scan modalities. The model, which we named SLIViT (for ‘slice integration by vision transformer’), preprocesses a given volumetric scan into 2D images, extracts their feature map and integrates it into a single prediction. We evaluated the model in eight different learning tasks, including classification and regression for six datasets involving four volumetric imaging modalities (computed tomography, magnetic resonance imaging, optical coherence tomography and ultrasound). SLIViT consistently outperformed domain-specific state-of-the-art models and was typically as accurate as clinical specialists who had spent considerable time manually annotating the analysed scans. Automating diagnosis tasks involving volumetric scans may save valuable clinician hours, reduce data acquisition costs and duration, and help expedite medical research and clinical applications.

The clinical assessment of microvascular pathologies (in diabetes and in inflammatory skin diseases, for example) requires the visualization of superficial vascular anatomy. Photoacoustic tomography (PAT) scanners based on an all-optical Fabry–Perot ultrasound sensor can provide highly detailed 3D microvascular images, but minutes-long acquisition times have precluded their clinical use. Here we show that scan times can be reduced to a few seconds and even hundreds of milliseconds by parallelizing the optical architecture of the sensor readout, by using excitation lasers with high pulse-repetition frequencies and by exploiting compressed sensing. A PAT scanner with such fast acquisition minimizes motion-related artefacts and allows for the volumetric visualization of individual arterioles, venules, venous valves and millimetre-scale arteries and veins to depths approaching 15 mm, as well as for dynamic 3D images of time-varying tissue perfusion and other haemodynamic events. In exploratory case studies, we used the scanner to visualize and quantify microvascular changes associated with peripheral vascular disease, skin inflammation and rheumatoid arthritis. Fast all-optical PAT may prove useful in cardiovascular medicine, oncology, dermatology and rheumatology.