MOTIVATION: Multi-omics integration can improve cancer diagnosis and prognosis, but current models are limited by extreme dimensionality, redundant raw-feature similarities, missing assays, and incomplete pathway priors. We ask whether biologically meaningful patient manifolds can be learned directly from high-dimensional multi-omics data without heuristic graph construction or fixed knowledge-base constraints. RESULTS: We present OmicsTransformer, an end-to-end framework that projects each omics modality into latent patches, enforces masked semantic consistency through an Exponential Cosine Consistency Loss, models global patch dependencies with a Transformer encoder, and fuses modalities by sample-specific uncertainty. Across eight diagnostic and prognostic cohorts, OmicsTransformer achieved strong performance, including 89.4% accuracy for TCGA-BRCA subtyping and 90.6% area under the receiver operating characteristic curve (AUC) for TCGA-LGG grading. It improved recurrence prediction over the pathway-restricted DeepKEGG baseline by approximately 21.5 percentage points in accuracy (ACC) on TCGA-LIHC and 11.1 percentage points in ACC on TCGA-BLCA. Variance-weighted attribution with ensemble stability selection recovered reproducible cross-modal biomarker cores and non-canonical progression drivers. AVAILABILITY AND IMPLEMENTATION: Source code and datasets are freely available at https://github.com/FFJXX/OmicTransformer and https://doi.org/10.6084/m9.figshare.31523905. OmicsTransformer is implemented in PyTorch.

To solve the problem of sparse images in real‐world drowning datasets, this study aims to create an intelligent system that can generate a large number of drowning datasets by optimizing AI image generation algorithms. The system will gradually be used to make up for the shortage of rare real‐world drowning datasets based on the CamTra (camera tracking) System. This method is not only based on traditional AI image generation steps but also optimizes the engine framework to create more drowning datasets. For the key elements of drowning, on the one hand, different filters, especially blue and green filters, will be added to distinguish color differences between underwater and above water. On the other hand, the framework structure of the generative adversarial network (GAN), variational autoencoder (VAE), and diffusion model will be optimized to further reduce system computation. Meanwhile, the detection of drowning swimmers in the system will become clearer. It can greatly improve the performance and efficiency of drowning monitoring algorithms. The artificially generated drowning dataset generated by AI can describe different real‐world drowning processes and perfectly adapt to different emergencies. This method is also applicable to dangerous behaviors that are difficult to record.

Robots with active variable stiffness (VS) capabilities can potentially achieve safer interactions with humans and better adaptabilities to uncertainties in complex environments. Currently, the conventional jamming or phase-change-based VS mechanisms simultaneously act on the stiffnesses of the robotic joint in all axes, making it difficult to achieve decoupled stiffness programming in different directions/axes. To overcome this challenge, a bio-inspired stiffness-programmable robotic flexible joint (SPRFJ) based on the electro-adhesive (EA) clutches is proposed. By programming the ON/OFF states of the EA clutches on different surfaces around the SPRFJ, customization of stiffness profiles in different directions/axes can be realized, and therefore, the load-bearing capacity and flexibility of the robotic arm can be adjusted. A SPRFJ prototype consisting of four EA clutch units is developed, and through extensive experiments, we demonstrate that it can achieve a stiffness change of 21 times and can withstand resisting forces up to 13.41 N at 1 kV. The reliable multi-directional stiffness programmability of the SPRFJ is shown via extensive tests. Demonstrations on stable position locking at different angles and free movements while carrying payloads are conducted to showcase its application in soft robotics. This SPRFJ developed in this work processes the potential in industrial robots, search-and-rescue missions, and space explorations.

Virtual reality (VR) technology has enormous applications in education, entertainment, and healthcare. Haptic feedback can significantly enhance the immersive experience in VR. However, most commercial hand/fingertip wearable VR haptic devices rely on bulky rigid structures, which are limited in the offered stimuli and cause fatigue. This study introduces a novel soft wearable fingertip device, T-Touch, that provides both thermal and multi-frequency haptic feedback for more realistic VR experiences. A flexible electrohydraulic actuator (EHA) is adopted for multi-frequency mechanical stimuli, and a flexible thermoelectric array (Flex-TEA) is utilized for distinct thermal stimuli. The EHA and Flex-TEA can be independently controlled to activate simultaneously or independently, thereby rendering ON/OFF contact stimuli, vibrations, controlled temperature stimuli, or any combination of the three modalities. Our T-Touch device features a compact form factor of 35 mm × 25 mm × 22 mm and weighs only ∼8 g. It can generate mechanical stimuli with the maximum stroke of ∼1 mm, a force of 0.47 N, at a bandwidth >10 Hz, and can render precise thermal stimuli in the range of 20 to 40 °C. The main performance of the EHA and Flex-TEA modules is characterized in extensive experiments and the effects of the key design and actuation parameters are investigated to optimise performance. Preliminary user tests verify the efficacy of our T-Touch design in immersive VR applications.

Pouch motors continue to attract research attention owing to their simple fabrication process, low cost, and excellent energy density. Existing pouch motors based on the liquid-gas phase transition (LGPT) principle exhibit significant stroke and force outputs but suffer from slow responses. Pouch motors that rely on the electrohydraulic actuation (EHA) demonstrate rapid responses and broad bandwidths, yet their stroke/force outputs remain limited. This paper presents a novel thermal-electrostatic dual-modal soft pouch motor (TES-SPM) that synergistically combines the advantages of LGPT and EHA. The output performance of the TES-SPM in both the LGPT and EHA modes is characterized by extensive experiments. The effects of key parameters including the liquid volumes and actuation voltage/current amplitudes are also investigated in experiments. In the EHA mode, the TES-SPM can exert a stroke of 2.5 mm within a rapid ~ 0.06 s, while in the LGPT mode, it is able to exhibit a maximum stroke of 22.8 mm and a blocking force of ~ 80 N. A novel folding fan-inspired actuator and accordion-inspired soft gripper based on the serially attached TES-SPM units are developed to demonstrate the potentials of soft robotic applications. The TES-SPM designed in this paper is envisioned to have promising applications in industrial soft grippers and wearable assistive devices.

Metagenomic data plays a crucial role in analyzing the relationship between microbes and diseases. However, the limited number of samples, high dimensionality, and sparsity of metagenomic data pose significant challenges for the application of deep learning in data classification and prediction. Previous studies have shown that utilizing the phylogenetic tree structure to transform metagenomic abundance data into a 2D matrix input for convolutional neural networks (CNNs) improves classification performance. Inspired by the success of a Permutable MLP-like architecture in visual recognition, we propose Metagenomic Permutator (MetaP), which applied the Permutable MLP-like network structure to capture the phylogenetic information of microbes within the 2D matrix formed by phylogenetic tree. Our experiments demonstrate that our model achieved competitive performance compared to other deep neural networks and traditional machine learning, and has good prospects for multi-classification and large sample sizes. Furthermore, we utilize the SHAP (SHapley Additive exPlanations) method to interpret our model predictions, identifying the microbial features that are associated with diseases.

BACKGROUND: Benefiting from big data, powerful computation and new algorithmic techniques, we have been witnessing the renaissance of deep learning, particularly the combination of natural language processing (NLP) and deep neural networks. The advent of electronic medical records (EMRs) has not only changed the format of medical records but also helped users to obtain information faster. However, there are many challenges regarding researching directly using Chinese EMRs, such as low quality, huge quantity, imbalance, semi-structure and non-structure, particularly the high density of the Chinese language compared with English. Therefore, effective word segmentation, word representation and model architecture are the core technologies in the literature on Chinese EMRs. RESULTS: In this paper, we propose a deep learning framework to study intelligent diagnosis using Chinese EMR data, which incorporates a convolutional neural network (CNN) into an EMR classification application. The novelty of this paper is reflected in the following: (1) We construct a pediatric medical dictionary based on Chinese EMRs. (2) Word2vec adopted in word embedding is used to achieve the semantic description of the content of Chinese EMRs. (3) A fine-tuning CNN model is constructed to feed the pediatric diagnosis with Chinese EMR data. Our results on real-world pediatric Chinese EMRs demonstrate that the average accuracy and F1-score of the CNN models are up to 81%, which indicates the effectiveness of the CNN model for the classification of EMRs. Particularly, a fine-tuning one-layer CNN performs best among all CNNs, recurrent neural network (RNN) (long short-term memory, gated recurrent unit) and CNN-RNN models, and the average accuracy and F1-score are both up to 83%. CONCLUSION: The CNN framework that includes word segmentation, word embedding and model training can serve as an intelligent auxiliary diagnosis tool for pediatricians. Particularly, a fine-tuning one-layer CNN performs well, which indicates that word order does not appear to have a useful effect on our Chinese EMRs.