Dopamine plays a crucial role in regulating various brain functions, making the development of highly sensitive detection methods and precise quantitative analysis. techniques of great significance. However, realizing highly selective and sensitive detection of dopamine in complex biological environments remains a challenge. Here, we prepared 3D crumpled Ti3C2Tx structures loaded with Pt nanoparticles (Pt/Na- Ti3C2Tx) by wet chemical reduction and ion intercalation. The synergistic coupling between Pt nanoparticles and MXene support facilitates efficient electron transfer between dopamine and the electrode surface, thereby improving the sensing performance of dopamine. Furthermore, this wrinkled structure not only enhances the specific surface area by inhibiting the stacking of layered Ti3C2Tx nanosheets, but also effectively prevents the agglomeration of nanoparticles. The experimental results showed that Pt/Na-Ti3C2Tx possessed a wide linear range (0.1-100 μM), a low detection limit (0.029 μM), and a high sensitivity (0.556 μAμM^-1cm^-2). This work proposes an innovative strategy for achieving highly sensitive dopamine detection while advancing the utilization of MXene-based nanocomposites in electrochemical sensor development.

Flexible strain sensors are essential in fields such as medicine, sports, robotics, and virtual reality but face challenges in achieving excellent sensing performance and accurate multi-directional detection simultaneously. To address this issue, we have developed a spider-web structured multi-directional flexible strain sensor using Ti₃C₂Tₓ (MXene) conductive ink and 3D printing technology. Combined with a multi-class, multi-output neural network model algorithm, the sensor achieves signal decoupling from the sensor array, allowing for precise detection of strain direction and intensity. It exhibits good sensitivity (gauge factor ~ 26.3), a moderate sensing range (0-10%), and high reliability (1000 stretching cycles). Using neural network algorithms, a four-unit spider-web sensor array achieves approximately 97% accuracy in identifying strain intensity and direction within the 0-10% strain range under various surface stimuli. Additionally, it can track complex human motions, demonstrating significant potential in applications such as motion monitoring and human-machine interaction.

Single-atom catalysts (SACs) attract widespread attention in heterogeneous catalysis due to their maximum atomic utilization efficiency and unique physical and chemical properties. However, their applications in chemical sensing keep huge potential but remain unclear. Herein, a Ni-N₄-C SAC was synthesized for the trace detection of dopamine (DA) and uric acid (UA). The Ni-N₄-C SAC exhibited superior sensing performance compared to the Ni clusters. The detection range for DA and UA were 0.05–75 µM and 5–90 µM with detection limits of 0.027 and 0.82 µM, respectively. Density functional theory (DFT) computations indicate that Ni-N₄-C has a lower reaction barrier during electrochemical process, indicating that the atomic Ni sites possess higher intrinsic activity than Ni clusters. Moreover, DA and UA show strong potential dependency on the Ni-N₄-C catalyst, indicating its applicability for their concurrent detection. This work extends the application of SACs in chemical sensing.

Herein we proposed a data-driven high-throughput principle to screen high-performance single-atom materials for hydrogen evolution reaction (HER) and hydrogen sensing by combing the theoretical computations and a topology-based multi-scale convolution kernel machine learning algorithm. After the rational training by 25 groups of data and prediction of all 168 groups of single-atom materials for HER and sensing, respectively, a high prediction accuracy (> 0.931 R² score) was achieved by our model. Results show that the promising HER catalysts include Pt atoms in C₄ and Sc atoms in C₁N₃ coordination environment. Moreover, Y atoms in C₄ coordination environment and Cd atoms in C₂N₂-ortho coordination environment were predicted with great potential as hydrogen sensing materials. This method provides a way to accelerate the discovery of innovative materials by avoiding the time-consuming empirical principles in experiments.

Currently, the machine learning (ML)-based scanning transmission electron microscopy (STEM) analysis is limited in the simulative stage, its application in experimental STEM is needed but challenging. Herein, we built up a universal model to analyze the vacancy defects and single atoms accurately and rapidly in experimental STEM images using a full convolution network. In our model, the unavoidable interference factors of noise, aberration, and carbon contamination were fully considered during the training, which were difficult to be considered in the past. Even toward the simultaneous identification of various vacancy types and low-contrast single atoms in the low-quality STEM images, our model showed rapid process speed (45 images per second) and high accuracy (> 95%). This work represents an improvement in experimental STEM image analysis by ML.