Subcellular localization of messenger RNAs (mRNAs), as a prevalent mechanism, gives precise and efficient control for the translation process. There is mounting evidence for the important roles of this process in a variety of cellular events. Computational methods for mRNA subcellular localization prediction provide a useful approach for studying mRNA functions. However, few computational methods were designed for mRNA subcellular localization prediction and their performance have room for improvement. Especially, there is still no available tool to predict for mRNAs that have multiple localization annotations. In this paper, we propose a multi-head self-attention method, DM3Loc, for multi-label mRNA subcellular localization prediction. Evaluation results show that DM3Loc outperforms existing methods and tools in general. Furthermore, DM3Loc has the interpretation ability to analyze RNA-binding protein motifs and key signals on mRNAs for subcellular localization. Our analyses found hundreds of instances of mRNA isoform-specific subcellular localizations and many significantly enriched gene functions for mRNAs in different subcellular localizations.

G2PDeep is an open-access web server, which provides a deep-learning framework for quantitative phenotype prediction and discovery of genomics markers. It uses zygosity or single nucleotide polymorphism (SNP) information from plants and animals as the input to predict quantitative phenotype of interest and genomic markers associated with phenotype. It provides a one-stop-shop platform for researchers to create deep-learning models through an interactive web interface and train these models with uploaded data, using high-performance computing resources plugged at the backend. G2PDeep also provides a series of informative interfaces to monitor the training process and compare the performance among the trained models. The trained models can then be deployed automatically. The quantitative phenotype and genomic markers are predicted using a user-selected trained model and the results are visualized. Our state-of-the-art model has been benchmarked and demonstrated competitive performance in quantitative phenotype predictions by other researchers. In addition, the server integrates the soybean nested association mapping (SoyNAM) dataset with five phenotypes, including grain yield, height, moisture, oil, and protein. A publicly available dataset for seed protein and oil content has also been integrated into the server. The G2PDeep server is publicly available at http://g2pdeep.org. The Python-based deep-learning model is available at https://github.com/shuaizengMU/G2PDeep_model.

No abstract

In the biomedical literature, gene pathways are frequently included. Many high-quality gene pathways are illustrated in the form of visuals and text, making them valuable study tools for biological processes and precision medicine. Pathway maps and literature texts provide researchers with access to a huge number of new biological treatments. For general usage, these pathway maps should be logically ordered, coordinated, and converted into a computer-readable format. Currently, keeping up with the rapid increase of the literature requires laborious extraction of information from a publication at a time. A gene pathway map recognition system is devised and implemented in this study. Based on the pathway map and relevant information supplied by users, the system extracts gene identity and gene interaction information, and the automated extraction from pathway maps is efficient. Furthermore, the tool offers users with a full view of a certain illness's pathway, which is useful for researchers and can speed up the research process in a variety of biomedical applications. This thesis first explains the project's goal and provides the background information. The project's design ideas are then presented, as well as an analysis of the system and introductions to related platforms. After that, the system's implementations are described one by one, together with the deployment and testing processes. Finally, potential improvements and future work are discussed.