Metasurface can manipulate electromagnetic (EM) waves flexibly, which provides the basis for functional integration. Recently, the efficient machine‐learning‐assisted methods have attracted intensive attentions in multifunctional metasurfaces design. However, the conventional machine‐learning‐assisted metasurfaces design is to fit the internal relationship in the form of black box, which ignores the underlying physical logic, resulting in the increased complexity of machine learning architecture with the parameters increasing. In order to adapt to the multiparameter optimization in multifunctional metasurfaces design, we propose a multiplexing neural network (MNN) based on decoupling at the physical layer to simplify both the structural parameters and the network architecture. The four interacting parameters are simplified into four independently regulated parameters so that the facile design of four functions can be realized only by multiplexing a simple neural network. For verification, four functions of scattering, anomalous reflection, focusing, and hologram are integrated in the same metasurface aperture by MNN. Performances of the metasurface are fully demonstrated by simulation and measurement. Importantly, this work paves the way for the bidirectional simplification of machine learning and metasurface design via physical inspiration, which provides an integrated design method of multifunctional metasurfaces and can be potentially applied to satellite communications and other fields.

Measuring the semantic similarity between Gene Ontology (GO) terms is a fundamental step in numerous functional bioinformatics applications. To fully exploit the metadata of GO terms, word embedding-based methods have been proposed recently to map GO terms to low-dimensional feature vectors. However, these representation methods commonly overlook the key information hidden in the whole GO structure and the relationship between GO terms. In this paper, we propose a novel representation model for GO terms, named GT2Vec, which jointly considers the GO graph structure obtained by graph contrastive learning and the semantic description of GO terms based on BERT encoders. Our method is evaluated on a protein similarity task on a collection of benchmark datasets. The experimental results demonstrate the effectiveness of using a joint encoding graph structure and textual node descriptors to learn vector representations for GO terms.

MOTIVATION: The capability to predict the potential drug binding affinity against a protein target has always been a fundamental challenge in silico drug discovery. The traditional experiments in vitro and in vivo are costly and time-consuming which need to search over large compound space. Recent years have witnessed significant success on deep learning-based models for drug-target binding affinity prediction task. RESULTS: Following the recent success of the Transformer model, we propose a multigranularity protein-ligand interaction (MGPLI) model, which adopts the Transformer encoders to represent the character-level features and fragment-level features, modeling the possible interaction between residues and atoms or their segments. In addition, we use the convolutional neural network to extract higher-level features based on transformer encoder outputs and a highway layer to fuse the protein and drug features. We evaluate MGPLI on different protein-ligand interaction datasets and show the improvement of prediction performance compared to state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: The model scripts are available at https://github.com/IILab-Resource/MGDTA.git.