Data-balanced transformer for accelerated ionizable lipid nanoparticles screening in mRNA delivery.

Despite the widespread use of ionizable lipid nanoparticles (LNPs) in clinical applications for messenger RNA (mRNA) delivery, the mRNA drug delivery system faces an efficient challenge in the screening of LNPs. Traditional screening methods often require a substantial amount of experimental time and incur high research and development costs. To accelerate the early development stage of LNPs, we propose TransLNP, a transformer-based transfection prediction model designed to aid in the selection of LNPs for mRNA drug delivery systems. TransLNP uses two types of molecular information to perceive the relationship between structure and transfection efficiency: coarse-grained atomic sequence information and fine-grained atomic spatial relationship information. Due to the scarcity of existing LNPs experimental data, we find that pretraining the molecular model is crucial for better understanding the task of predicting LNPs properties, which is achieved through reconstructing atomic 3D coordinates and masking atom predictions. In addition, the issue of data imbalance is particularly prominent in the real-world exploration of LNPs. We introduce the BalMol block to solve this problem by smoothing the distribution of labels and molecular features. Our approach outperforms state-of-the-art works in transfection property prediction under both random and scaffold data splitting. Additionally, we establish a relationship between molecular structural similarity and transfection differences, selecting 4267 pairs of molecular transfection cliffs, which are pairs of molecules that exhibit high structural similarity but significant differences in transfection efficiency, thereby revealing the primary source of prediction errors. The code, model and data are made publicly available at https://github.com/wklix/TransLNP.

SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation.

Liver occupying lesions can profoundly impact an individual's health and well-being. To assist physicians in the diagnosis and treatment of abnormal areas in the liver, we propose a novel network named SEU2-Net by introducing the channel attention mechanism into U2-Net for accurate and automatic liver occupying lesion segmentation. We design the Residual U-block with Squeeze-and-Excitation (SE-RSU), which is to add the Squeeze-and-Excitation (SE) attention mechanism at the residual connections of the Residual U-blocks (RSU, the component unit of U2-Net). SEU2-Net not only retains the advantages of U2-Net in capturing contextual information at multiple scales, but can also adaptively recalibrate channel feature responses to emphasize useful feature information according to the channel attention mechanism. In addition, we present a new abdominal CT dataset for liver occupying lesion segmentation from Peking University First Hospital's clinical data (PUFH dataset). We evaluate the proposed method and compare it with eight deep learning networks on the PUFH and the Liver Tumor Segmentation Challenge (LiTS) datasets. The experimental results show that SEU2-Net has state-of-the-art performance and good robustness in liver occupying lesions segmentation.

[Application of multiple empirical kernel mapping ensemble classifier based on self-paced learning in ultrasound-based computer-aided diagnosis for breast cancer].

Both feature representation and classifier performance are important factors that determine the performance of computer-aided diagnosis (CAD) systems. In order to improve the performance of ultrasound-based CAD for breast cancers, a novel multiple empirical kernel mapping (MEKM) exclusivity regularized machine (ERM) ensemble classifier algorithm based on self-paced learning (SPL) is proposed, which simultaneously promotes the performance of both feature representation and the classifier. The proposed algorithm first generates multiple groups of features by MEKM to enhance the ability of feature representation, which also work as the kernel transform in multiple support vector machines embedded in ERM. The SPL strategy is then adopted to adaptively select samples from easy to hard so as to gradually train the ERM classifier model with improved performance. This algorithm is verified on a B-mode ultrasound dataset and an elastography ultrasound dataset, respectively. The results show that the classification accuracy, sensitivity and specificity on B-mode ultrasound are (86.36±6.45)%, (88.15±7.12)%, and (84.52±9.38)%, respectively, and the classification accuracy, sensitivity and specificity on elastography ultrasound are (85.97±3.75)%, (85.93±6.09)%, and (86.03±5.88)%, respectively. It indicates that the proposed algorithm can effectively improve the performance of ultrasound-based CAD for breast cancers with the potential for application.

Gold nano-flowers (Au NFs) modified screen-printed carbon electrode electrochemical biosensor for label-free and quantitative detection of glycated hemoglobin.

Glycated hemoglobin (HbA1c) represents the average glucose level over the past three months and has been considered as the most important biomarker for the diagnosis of Type Ⅱ diabetes (T2D). Herein, a label-free and quantitative electrochemical biosensor based on 4-mercaptophenylboronic acid (4-MPBA) modified gold nano-flowers (Au NFs) substrate was developed for the determination of HbA1c. Under optimal conditions, the linear dynamic ranges of HbA1c (5 µg/mL - 1000 µg/mL) and HbA1c% (2%-20%) by cyclic voltammetry were achieved. The electrochemical biosensor showed great detection specificity towards HbA1c and relatively stability after storage at 4 °C. This method could also be applied in human serum system which holds great potential to be applied to monitor real blood samples of diabetes patients. In human serum system, the recovery rate could reach 103.8% and 99.0%. It could achieve fast detection, the total analysis time was less than 65 min, and the detection time was less than 10 s. Moreover, in terms of fabrication process, operation procedure, detection time and cost, this technique was superior to the current HbA1c detection methods suggesting great promise for the practical clinical use in the future.

Gaussian numerical analysis and terahertz spectroscopic measurement of homocysteine.

Homocysteine is an amino acid related to metabolism in human vivo, which is closely related to cardiovascular disease, senile dementia, bone fracture, et al. Currently, the usual medical test methods for homocysteine include high performance liquid chromatography (HPLC), fluorescence polarization immunoassay (FPIA) and enzyme-linked immunosorbent assay (ELISA), which are time-consuming or expensive. In this paper, we first analyze the vibration and rotation of homocysteine molecules by using density functional theory, and then we ensure that the theoretical absorption peaks are located in the range of the terahertz spectrum. Then, based on the terahertz time-domain spectroscopy system, we measured the absorption spectrum of homocysteine under different concentrations. It is found that as the detection of the concentration, the terahertz results present higher accuracy than that of the laser Raman spectrum, which can be used as the reference for the evaluation of pathological stage. These results are of great significance for the exact and quick diagnosis of homocysteine-related diseases in clinical medicine.

[A video communication system for telemedicine].

In this paper, point to point video communication system based on internet is deeply studied. Meanwhile the application system designed practically is introduced. It is emphasized that video compression coding based on low bit rate stream with ITU-T H. 263 agreement and related international standards is realized.