Coronary heart disease is the most common heart disease, it can induce myocardial infarction, and the cause of the disease has a lot to do with life and eating habits. The results of a large number of epidemiological studies at home and abroad show that the incidence of coronary heart disease has an obvious familial tendency. However, little is known about the genetic factors of coronary heart disease. Although genome-wide association analysis and gene knockout experiments have found some genes related to coronary heart disease, there are still a large number of genes potentially related to coronary heart disease that have not been discovered. If it is confirmed by biological experimental means, the time and money cost is too high. Therefore, it is urgent to identify genes related to coronary heart disease on a large scale by computational means, so as to conduct targeted biological experimental verification. This paper proposes a deep learning method based on biological networks for the identification of coronary heart disease-related genes. We constructed gene interaction networks and extracted gene expression levels in different tissues as features. Through the association information and expression characteristics between genes, we constructed a model of coronary heart disease-related genes. Through cross-validation, we found that our proposed GCN-GENE that has AUC as 0.75 and AUPR as 0.78, which is more accurate than other methods and is a reliable method for predicting coronary heart disease-related genes.

Drug repurposing is an approach to identify new medical indications of approved drugs. This work presents a graph neural network drug repurposing model, which we refer to as GDRnet, to efficiently screen a large database of approved drugs and predict the possible treatment for novel diseases. We pose drug repurposing as a link prediction problem in a multi-layered heterogeneous network with about 1.4 million edges capturing complex interactions between nearly 42,000 nodes representing drugs, diseases, genes, and human anatomies. GDRnet has an encoder-decoder architecture, which is trained in an end-to-end manner to generate scores for drug-disease pairs under test. We demonstrate the efficacy of the proposed model on real datasets as compared to other state-of-the-art baseline methods. For a majority of the diseases, GDRnet ranks the actual treatment drug in the top 15. Furthermore, we apply GDRnet on a coronavirus disease (COVID-19) dataset and show that many drugs from the predicted list are being studied for their efficacy against the disease.

Additively manufactured lattice structures enable the design of tissue scaffolds with tailored mechanical properties, which can be implemented in porous biomaterials. The adaptation of bone to physiological loads results in anisotropic bone tissue properties which are optimized for site-specific loads; therefore, some bone sites are stiffer and stronger along the principal load direction compared to other orientations. In this work, a semi-analytical model was developed for the design of transversely isotropic lattice structures that can mimic the anisotropy characteristics of different types of bone tissue. Several design possibilities were explored, and a particular unit cell, which was best suited for additive manufacturing was further analyzed. The design of the unit cell was parameterized and in-silico analysis was performed via Finite Element Analysis. The structures were manufactured additively in metal and tested under compressive loads in different orientations. Finite element analysis showed good correlation with the semi-analytical model, especially for elastic constants with low relative densities. The anisotropy measured experimentally showed a variable accuracy, highlighting the deviations from designs to additively manufactured parts. Overall, the proposed model enables to exploit the anisotropy of lattice structures to design lighter scaffolds with higher porosity and increased permeability by aligning the scaffold with the principal direction of the load.

Medical image segmentation is a crucial step in Computer-Aided Diagnosis systems, where accurate segmentation is vital for perfect disease diagnoses. This paper proposes a multilevel thresholding technique for 2D and 3D medical image segmentation using Otsu and Kapur's entropy methods as fitness functions to determine the optimum threshold values. The proposed algorithm applies the hybridization concept between the recent Coronavirus Optimization Algorithm (COVIDOA) and Harris Hawks Optimization Algorithm (HHOA) to benefit from both algorithms' strengths and overcome their limitations. The improved performance of the proposed algorithm over COVIDOA and HHOA algorithms is demonstrated by solving 5 test problems from IEEE CEC 2019 benchmark problems. Medical image segmentation is tested using two groups of images, including 2D medical images and volumetric (3D) medical images, to demonstrate its superior performance. The utilized test images are from different modalities such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and X-ray images. The proposed algorithm is compared with seven well-known metaheuristic algorithms, where the performance is evaluated using four different metrics, including the best fitness values, Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Normalized Correlation Coefficient (NCC). The experimental results demonstrate the superior performance of the proposed algorithm in terms of convergence to the global optimum and making a good balance between exploration and exploitation properties. Moreover, the quality of the segmented images using the proposed algorithm at different threshold levels is better than the other methods according to PSNR, SSIM, and NCC values. Additionally, the Wilcoxon rank-sum test is conducted to prove the statistical significance of the proposed algorithm.

In the last decade, deep neural networks have been widely applied to medical image segmentation, achieving good results in computer-aided diagnosis tasks etc. However, the task of segmenting highly complex, low-contrast images of organs and tissues with high accuracy still faces great challenges. To better address this challenge, this paper proposes a novel model SWTRU (Star-shaped Window Transformer Reinforced U-Net) by combining the U-Net network which plays well in the image segmentation field, and the Transformer which possesses a powerful ability to capture global contexts. Unlike the previous methods that import the Transformer into U-Net, an improved Star-shaped Window Transformer is introduced into the decoder of the SWTRU to enhance the decision-making capability of the whole method. The SWTRU uses a redesigned multi-scale skip-connection model, which retains the inductive bias of the original FCN structure for images while obtaining fine-grained features and coarse-grained semantic information. Our method also presents the FFIM (Filtering Feature Integration Mechanism) to integration and dimensionality reduction of the fused multi-layered features, which reduces the computation. Our SWTRU yields 0.972 DICE on CHLISC for liver and tumor segmentation, 0.897 DICE on LGG for glioma segmentation, and 0.904 DICE on ISIC2018 for skin diseases' segmentation, achieves substantial improvements over the current SoTA across 9 different medical image segment methods. SWTRU can combine feature mapping from different scales, high-level semantics, and global contextual relationships, this architecture is effective in the medical image segmentation. The experimental findings indicate that SWTRU produces superior performance on the medical image segmentation tasks.

Automatic recognition and accurate quantitative analysis of rodent behavior play an important role in brain neuroscience, pharmacological and toxicological. Currently, most behavior recognition systems used in experiments mainly focus on the indirect measurements of animal movement trajectories, while neglecting the changes of animal body pose that can indicate more psychological factors. Thus, this paper developed and validated an hourglass network-based behavioral quantification system (HNBQ), which uses a combination of body pose and movement parameters to quantify the activity of mice in an enclosed experimental chamber. In addition, The HNBQ was employed to record behavioral abnormalities of head scanning in the presence of food gradients in open field test (OFT). The results proved that the HNBQ in the new object recognition (NOR) experiment was highly correlated with the scores of manual observers during the latent exploration period and the cumulative exploration time. Moreover, in the OFT, HNBQ was able to capture the subtle differences in head scanning behavior of mice in the gradient experimental groups. Satisfactory results support that the combination of body pose and motor parameters can regard as a new alternative approach for quantification of animal behavior in laboratory.