Nature Biomedical Engineering

Tumour-associated neutrophils can exert antitumour effects but can also assume a pro-tumoural phenotype in the immunosuppressive tumour microenvironment. Here we show that neutrophils can be polarized towards the antitumour phenotype by discoidal polymer micrometric 'patches' that adhere to the neutrophils' surfaces without being internalized. Intravenously administered micropatch-loaded neutrophils accumulated in the spleen and in tumour-draining lymph nodes, and activated splenic natural killer cells and T cells, increasing the accumulation of dendritic cells and natural killer cells...

In vitro systems that accurately model in vivo conditions in the gastrointestinal tract may aid the development of oral drugs with greater bioavailability. Here we show that the interaction profiles between drugs and intestinal drug transporters can be obtained by modulating transporter expression in intact porcine tissue explants via the ultrasound-mediated delivery of small interfering RNAs and that the interaction profiles can be classified via a random forest model trained on the drug-transporter relationships...

The broader clinical use of bispecific T cell engagers for inducing anti-tumour toxicity is hindered by their on-target off-tumour toxicity and the associated neurotoxicity and cytokine-release syndrome. Here we show that the off-tumour toxicity of a supramolecular bispecific T cell engager binding to the T cell co-receptor CD3 and to the human epidermal growth factor receptor 2 on breast tumour cells can be halted by disengaging the T cells from the tumour cells via the infusion of the small-molecule drug amantadine, which disassembles the supramolecular aggregate...

The blood-brain barrier (BBB) restricts the systemic delivery of messenger RNAs (mRNAs) into diseased neurons. Although leucocyte-derived extracellular vesicles (EVs) can cross the BBB at inflammatory sites, it is difficult to efficiently load long mRNAs into the EVs and to enhance their neuronal uptake. Here we show that the packaging of mRNA into leucocyte-derived EVs and the endocytosis of the EVs by neurons can be enhanced by engineering leucocytes to produce EVs that incorporate retrovirus-like mRNA-packaging capsids...

No abstract text is available yet for this article.

No abstract text is available yet for this article.

No abstract text is available yet for this article.

No abstract text is available yet for this article.

No abstract text is available yet for this article.

No abstract text is available yet for this article.

No abstract text is available yet for this article.

No abstract text is available yet for this article.

Modelling the spatiotemporal dynamics in the activity of neural populations while also enabling their flexible inference is hindered by the complexity and noisiness of neural observations. Here we show that the lower-dimensional nonlinear latent factors and latent structures can be computationally modelled in a manner that allows for flexible inference causally, non-causally and in the presence of missing neural observations. To enable flexible inference, we developed a neural network that separates the model into jointly trained manifold and dynamic latent factors such that nonlinearity is captured through the manifold factors and the dynamics can be modelled in tractable linear form on this nonlinear manifold...

It is typically assumed that large networks of neurons exhibit a large repertoire of nonlinear behaviours. Here we challenge this assumption by leveraging mathematical models derived from measurements of local field potentials via intracranial electroencephalography and of whole-brain blood-oxygen-level-dependent brain activity via functional magnetic resonance imaging. We used state-of-the-art linear and nonlinear families of models to describe spontaneous resting-state activity of 700 participants in the Human Connectome Project and 122 participants in the Restoring Active Memory project...

Large-scale genomic data are well suited to analysis by deep learning algorithms. However, for many genomic datasets, labels are at the level of the sample rather than for individual genomic measures. Machine learning models leveraging these datasets generate predictions by using statically encoded measures that are then aggregated at the sample level. Here we show that a single weakly supervised end-to-end multiple-instance-learning model with multi-headed attention can be trained to encode and aggregate the local sequence context or genomic position of somatic mutations, hence allowing for the modelling of the importance of individual measures for sample-level classification and thus providing enhanced explainability...

No abstract text is available yet for this article.

No abstract text is available yet for this article.

The inferences of most machine-learning models powering medical artificial intelligence are difficult to interpret. Here we report a general framework for model auditing that combines insights from medical experts with a highly expressive form of explainable artificial intelligence. Specifically, we leveraged the expertise of dermatologists for the clinical task of differentiating melanomas from melanoma 'lookalikes' on the basis of dermoscopic and clinical images of the skin, and the power of generative models to render 'counterfactual' images to understand the 'reasoning' processes of five medical-image classifiers...

No abstract text is available yet for this article.

No abstract text is available yet for this article.