Identification of the Shared Gene Signatures and Biological Mechanisms in Hyperplastic Enlarged Lobular Units and Breast Cancer.

Breast cancer is a common cancer worldwide. Hyperplastic enlarged lobular units (HELUs) are common changes in the breasts of adult women. HELUs may be closely related to the occurrence and development of breast cancer. In this study, genes that are commonly contained in the expression profiles of the genomes of the two diseases and have significant differences in expression before and after the respective diseases were identified. Various enrichment analyses were performed according to the expression levels of these differentially expressed genes. Furthermore, LASSO regression analysis was performed on the differentially expressed genes to identify genes significantly related to survival. The optimal risk model for the survival of patients with breast cancer was established, and the accuracy of the model was verified on multiple data sets. A gene combination containing 17 genes was ultimately determined to be an independent prognostic factor. Kaplan‒Meier survival analysis demonstrated the good performance of this risk model. The study found that Shared Gene Signatures and Biological Mechanisms in Hyperplastic Enlarged Lobular Units and Breast Cancer, screened 17 important Shared Gene Signatures of Hyperplastic Enlarged Lobular Units which are closely related to the survival of breast cancer patients through machine learning, and established a prognosis model with high-accuracy, which is worthy of further exploration.

CNN-Siam: multimodal siamese CNN-based deep learning approach for drug‒drug interaction prediction.

BACKGROUND: Drug‒drug interactions (DDIs) are reactions between two or more drugs, i.e., possible situations that occur when two or more drugs are used simultaneously. DDIs act as an important link in both drug development and clinical treatment. Since it is not possible to study the interactions of such a large number of drugs using experimental means, a computer-based deep learning solution is always worth investigating. We propose a deep learning-based model that uses twin convolutional neural networks to learn representations from multimodal drug data and to make predictions about the possible types of drug effects. RESULTS: In this paper, we propose a novel convolutional neural network algorithm using a Siamese network architecture called CNN-Siam. CNN-Siam uses a convolutional neural network (CNN) as a backbone network in the form of a twin network architecture to learn the feature representation of drug pairs from multimodal data of drugs (including chemical substructures, targets and enzymes). Moreover, this network is used to predict the types of drug interactions with the best optimization algorithms available (RAdam and LookAhead). The experimental data show that the CNN-Siam achieves an area under the precision-recall (AUPR) curve score of 0.96 on the benchmark dataset and a correct rate of 92%. These results are significant improvements compared to the state-of-the-art method (from 86 to 92%) and demonstrate the robustness of the CNN-Siam and the superiority of the new optimization algorithm through ablation experiments. CONCLUSION: The experimental results show that our multimodal siamese convolutional neural network can accurately predict DDIs, and the Siamese network architecture is able to learn the feature representation of drug pairs better than individual networks. CNN-Siam outperforms other state-of-the-art algorithms with the combination of data enhancement and better optimizers. But at the same time, CNN-Siam has some drawbacks, longer training time, generalization needs to be improved, and poorer classification results on some classes.

Homology modeling and molecular docking simulation of martentoxin as a specific inhibitor of the BK channel.

Background: Large conductance calcium-activated potassium channel (BK channel) is gated by both voltage and calcium ions and is widely distributed in excitable and nonexcitable cells. BK channel plays an important role in epilepsy and other diseases, but BK channel subtype-specific drugs are still extremely rare. Martentoxin was previously isolated from the venom of members of Scorpionidae and shown to be composed of 37 amino acids. Research has shown that the pharmacological selectivity of martentoxin to the BK channel is higher than that to other potassium channels. Therefore, it is of great significance to study the mechanism of interaction between martentoxin and BK channels. Methods: The three-dimensional structure of BK channel pore region was constructed by homologous modeling method, and the key amino acid sites of BK channel interaction with martentoxin were analyzed by protein-protein docking, molecular dynamic simulation and virtual alanine mutation. Results: Based on homologous modeling of BK channel pore structure and protein-protein docking analysis, Phe1, Lys28 and Arg35 of martentoxin were found to be key amino acids in toxin BK channel interaction. Conclusions: This study reveals the structural basis of martentoxin interaction with BK channel. These results will contribute to the design of BK channel specific blockers based on the structure of martentoxin.