Clustering and cell type classification are a vital step of analyzing scRNA-seq data to reveal the complexity of the tissue (e.g. the number of cell types and the transcription characteristics of the respective cell type). Recently, deep learning-based single-cell clustering algorithms become popular since they integrate the dimensionality reduction with clustering. But these methods still have unstable clustering effects for the scRNA-seq datasets with high dropouts or noise. In this study, a novel single-cell RNA-seq deep embedding clustering via convolutional autoencoder embedding and soft K-means (scCAEs) is proposed by simultaneously learning the feature representation and clustering. It integrates the deep learning with convolutional autoencoder to characterize scRNA-seq data and proposes a regularized soft K-means algorithm to cluster cell populations in a learned latent space. Next, a novel constraint is introduced to the clustering objective function to iteratively optimize the clustering results, and more importantly, it is theoretically proved that this objective function optimization ensures the convergence. Moreover, it adds the reconstruction loss to the objective function combining the dimensionality reduction with clustering to find a more suitable embedding space for clustering. The proposed method is validated on a variety of datasets, in which the number of clusters in the mentioned datasets ranges from 4 to 46, and the number of cells ranges from 90 to 30 302. The experimental results show that scCAEs is superior to other state-of-the-art methods on the mentioned datasets, and it also keeps the satisfying compatibility and robustness. In addition, for single-cell datasets with the batch effects, scCAEs can ensure the cell separation while removing batch effects.

Motivation: Protein–protein interaction (PPI) networks and transcriptional regulatory networks are critical in regulating cells and their signaling. A thorough understanding of PPIs can provide more insights into cellular physiology at normal and disease states. Although numerous methods have been proposed to predict PPIs, it is still challenging for interaction prediction between unknown proteins. In this study, a novel neural network named AFTGAN was constructed to predict multi-type PPIs. Regarding feature input, ESM-1b embedding containing much biological information for proteins was added as a protein sequence feature besides amino acid co-occurrence similarity and one-hot coding. An ensemble network was also constructed based on a transformer encoder containing an AFT module (performing the weight operation on vital protein sequence feature information) and graph attention network (extracting the relational features of protein pairs) for the part of the network framework.Results: The experimental results showed that the Micro-F1 of the AFTGAN based on three partitioning schemes (BFS, DFS and the random mode) on the SHS27K and SHS148K datasets was 0.685, 0.711 and 0.867, as well as 0.745, 0.819 and 0.920, respectively, all higher than that of other popular methods. In addition, the experimental comparisons confirmed the performance superiority of the proposed model for predicting PPIs of unknown proteins on the STRING dataset.Availability and implementation: The source code is publicly available at https://github.com/1075793472/AFTGAN.Supplementary information: Supplementary data are available at Bioinformatics online.

Residue‐residue contact prediction has become an increasingly important tool for modeling the three‐dimensional structure of a protein when no homologous structure is available. Ultradeep residual neural network (ResNet) has become the most popular method for making contact predictions because it captures the contextual information between residues. In this paper, we propose a novel deep neural network framework for contact prediction which combines ResNet and DenseNet. This framework uses 1D ResNet to process sequential features, and besides PSSM, SS3, and solvent accessibility, we have introduced a new feature, position‐specific frequency matrix (PSFM), as an input. Using ResNet’s residual module and identity mapping, it can effectively process sequential features after which the outer concatenation function is used for sequential and pairwise features. Prediction accuracy is improved following a final processing step using the dense connection of DenseNet. The prediction accuracy of the protein contact map shows that our method is more effective than other popular methods due to the new network architecture and the added feature input.

Complexes formed by proteins binding to RNAs are essential in biological processes, and can also be useful for identifying causal disease variants, gene expression regulation and translation. Protein-RNA interactions identified in vivo can be affected by experimental condition, noise, and some bias, while in vitro experiments yield clearer signals. Therefore, accurately inferring RNA-protein binding models from in vitro data, to predict bound and unbound RNA transcripts in vivo, has become a key challenge. We constructed RDense, a novel deep neural network model. Using existing RNA sequences and secondary structure information, we introduced the pairwise probability feature extracted from the RNA secondary structure as the input. The bidirectional long and short memory neural network (Bi-LSTM) and densely connected convolutional neural networks (DenseNet) were then combined to learn protein-RNA binding preferences. We found that our prediction of in vitro binding was better than all current methods with a significant improvement in model accuracy. In addition, there was also some improvement when in vitro data-trained RNA binding models were used to predict in vivo binding. In summary, we have introduced new pairwise probability feature of RNA to improve the robustness of the model. By comparing the Deepbind and DLPRB methods based on CNN, our method combines the strength of Bi-LSTM and DenseNet, with better performance in accuracy and scalability of prediction.