CapsProm: a capsule network for promoter prediction

PmiProPred: A novel method towards plant miRNA promoter prediction based on CNN-transformer network and convolutional block attention mechanism

It is crucial to understand the transcription mechanisms of miRNAs, especially considering the presence of peptides encoded by miRNAs. Since promoters function as the switch for gene transcription, precisely identifying these regions is essential for fully annotating miRNA transcripts. Nonetheless, existing computational methods still have room for improvement in the characterization of promoter regions. Here, we present PmiProPred, an advanced tool designed for predicting plant miRNA promoters from a wide spectrum of genomes. It consists of two core components: multi-stream deep feature extraction (MsDFE) and multi-stream deep feature refinement (MsDFR). The MsDFE utilizes Transformer and CNN to gather multi-view features, while the MsDFR focuses on aligning and refining them using channel and spatial attention mechanisms. Ultimately, a multi-layer perceptron is employed to accomplish the miRNA promoter identification task. Across three independent testing datasets, PmiProPred achieves accuracies of 94.630 %, 96.659 %, and 92.480 %, respectively, substantially surpassing the latest methods. Additionally, PmiProPred is employed to identify potential core promoters in the upstream 2-kb regions of intergenic miRNAs in five plant species. We further conduct cis-regulatory elements mining on the predicted promoters and perform an in-depth analysis of the identified motifs. Altogether, PmiProPred is a robust and effective tool for discovering plant miRNA promoters.

CapsNet-TIS: Predicting translation initiation site based on multi-feature fusion and improved capsule network

Genes are the basic units of protein synthesis in organisms, and accurately identifying the translation initiation site (TIS) of genes is crucial for understanding the regulation, transcription, and translation processes of genes. However, the existing models cannot adequately extract the feature information in TIS sequences, and they also inadequately capture the complex hierarchical relationships among features. Therefore, a novel predictor named CapsNet-TIS is proposed in this paper. CapsNet-TIS first fully extracts the TIS sequence information using four encoding methods, including One-hot encoding, physical structure property (PSP) encoding, nucleotide chemical property (NCP) encoding, and nucleotide density (ND) encoding. Next, multi-scale convolutional neural networks are used to perform feature fusion of the encoded features to enhance the comprehensiveness of the feature representation. Finally, the fused features are classified using capsule network as the main network of the classification model to capture the complex hierarchical relationships among the features. Moreover, we improve the capsule network by introducing residual block, channel attention, and BiLSTM to enhance the model's feature extraction and sequence data modeling capabilities. In this paper, the performance of CapsNet-TIS is evaluated using TIS datasets from four species: human, mouse, bovine, and fruit fly, and the effectiveness of each part is demonstrated by performing ablation experiments. By comparing the experimental results with models proposed by other researchers, the results demonstrate the superior performance of CapsNet-TIS.

SAPPHIRE.CNN: Implementation of dRNA-seq-driven, species-specific promoter prediction using convolutional neural networks

Data availability is a consistent bottleneck for the development of bacterial species-specific promoter prediction software. In this work we leverage genome-wide promoter datasets generated with dRNA-seq in the Gram-negative bacteria Pseudomonas aeruginosa and Salmonella enterica for promoter prediction. Convolutional neural networks are presented as an optimal architecture for model training and are further modified and tailored for promoter prediction. The resulting predictors reach high binary accuracies (95% and 94.9%) on test sets and outperform each other when predicting promoters in their associated species. SAPPHIRE.CNN is available online and can also be downloaded to run locally. Our results indicate a dependency of binary promoter classification on an organism’s GC content and a decreased performance of our classifiers on genera they were not trained for, further supporting the need for dedicated, species-specific promoter classification tools.