Protein phosphorylation is one of the most critical post-translational modifications of proteins in eukaryotes, which is essential for a variety of biological processes. Plenty of attempts have been made to improve the performance of computational predictors for phosphorylation site prediction. However, most of them are based on extra domain knowledge or feature selection. In this article, we present a novel deep learning-based predictor, named TransPhos, which is constructed using a transformer encoder and densely connected convolutional neural network blocks, for predicting phosphorylation sites. Data experiments are conducted on the datasets of PPA (version 3.0) and Phospho. ELM. The experimental results show that our TransPhos performs better than several deep learning models, including Convolutional Neural Networks (CNN), Long-term and short-term memory networks (LSTM), Recurrent neural networks (RNN) and Fully connected neural networks (FCNN), and some state-of-the-art deep learning-based prediction tools, including GPS2.1, NetPhos, PPRED, Musite, PhosphoSVM, SKIPHOS, and DeepPhos. Our model achieves a good performance on the training datasets of Serine (S), Threonine (T), and Tyrosine (Y), with AUC values of 0.8579, 0.8335, and 0.6953 using 10-fold cross-validation tests, respectively, and demonstrates that the presented TransPhos tool considerably outperforms competing predictors in general protein phosphorylation site prediction.

There is a strong need to eliminate batch-specific differences when integrating single-cell RNA-sequencing (scRNA-seq) datasets generated under different experimental conditions for downstream task analysis. Existing batch correction methods usually transform different batches of cells into one preselected “anchor” batch or a low-dimensional embedding space, and cannot take full advantage of useful information from multiple sources. We present a novel framework, called IMGG, i.e., integrating multiple single-cell datasets through connected graphs and generative adversarial networks (GAN) to eliminate nonbiological differences between different batches. Compared with current methods, IMGG shows excellent performance on a variety of evaluation metrics, and the IMGG-corrected gene expression data incorporate features from multiple batches, allowing for downstream tasks such as differential gene expression analysis.

No abstract

No abstract

This paper takes a self-designed crab-like robot special-shaped rod as the research object. To solve the problem that the actual gait does not conform to the theory encountered in the debugging stage, the following operations are carried out: after static analysis, the problem is that the special-shaped rod is complex and stressed. It is complicated, and the resulting deformation is too large, resulting in a decrease in the movement stability of the overall mechanism. To improve the stability of the mechanism, SolidWorks was used to complete the construction of the crab-like robot model, and ANSYS Workbench was used to perform static analysis and topology optimization on the special-shaped rod, so as to obtain the preliminary optimization results. On this basis, to better improve the stability of the mechanism, the secondary optimization of the special-shaped rod is carried out. The static analysis is carried out again and the obtained results are compared with the original design. The deformation of the special-shaped rod during the movement process is reduced by 13%. Under the premise of structural rigidity, the weight is reduced by 44. 73% and the stress distribution is more uniform. The above analysis results show that after the analysis and processing of the above methods, the special-shaped rod structure is further optimized, the stability of the overall structure is improved, and the effect of green design is achieved at the same time.