Prediction of RNA subcellular localization: Learning from heterogeneous data sources

Abstract

Summary RNA subcellular localization has recently emerged as a widespread phenomenon, which may apply to the majority of RNAs. The two main sources of data for characterization of RNA localization are sequence features and microscopy images, such as obtained from single-molecule fluorescent in situ hybridization-based techniques. Although such imaging data are ideal for characterization of RNA distribution, these techniques remain costly, time-consuming, and technically challenging. Given these limitations, imaging data exist only for a limited number of RNAs. We argue that the field of RNA localization would greatly benefit from complementary techniques able to characterize location of RNA. Here we discuss the importance of RNA localization and the current methodology in the field, followed by an introduction on prediction of location of molecules. We then suggest a machine learning approach based on the integration between imaging localization data and sequence-based data to assist in characterization of RNA localization on a transcriptome level.

Spatial Transcriptomics-correlated Electron Microscopy

“…The current revolution in the generation of large volume EM datasets calls for new strategies for the annotation of cells. Currently, the cell identities in EM datasets are mostly manually annotated in an unintentionally biased way 21, 22 . Large variations between manual annotations limits the application of deep-learning approaches for automation.…”

Recent Advances in the Prediction of Subcellular Localization of Proteins and Related Topics

“…Similarly, Shen et al reports their critical evaluation of web-based tools for protein subcellular localization ( Shen et al, 2020 ), though they seem to mainly focus on Gene Ontology-based predictors, which are basically out of the scope of this review. Although the prediction of subcellular localization of RNA molecules is also out of the scope, it is important to establish reliable data sources for training the prediction models ( Cui et al, 2022 ) and how to integrate heterologous resources is an important issue ( Savulescu et al, 2021 ).…”

EL-RMLocNet: An explainable LSTM network for RNA-associated multi-compartment localization prediction

“…It provides the basis for spatial differences in shape, structure, and function of a variety of cells in order to ensure that each cell exhibits a unique form of polarization [20] , [21] . Characterizing RNA subcellular localization is essential for thorough categorization of different cell types and cell states [22] . In addition to facilitating a deep understanding of molecular and cellular biology, knowledge of RNA subcellular localization is also beneficial for the development of heterogeneous biomedical applications [22] .…”

“…Characterizing RNA subcellular localization is essential for thorough categorization of different cell types and cell states [22] . In addition to facilitating a deep understanding of molecular and cellular biology, knowledge of RNA subcellular localization is also beneficial for the development of heterogeneous biomedical applications [22] . Like subcellular localization of messenger RNAs (mRNAs) assists to identify and treat Huntington’s disease by eliminating active mRNAs of disease specific gene in nucleus and cytoplasm [23] .…”

“…A number of wet-lab experimental techniques based on single-molecule fluorescent in situ hybridization [25] , epifluorescent [26] , and confocal microscopic approaches [26] have been used to determine the subcellular localization of RNAs. However, such approaches are expensive, time consuming, and are not suitable for large scale characterisation of subcellular localization of diverse RNA classes across multiple species [22] . Considering the efficiency and robustness of computational approaches shown in various fields such as Natural Language Processing [27] and Bioinformatics [28] , to date, a number of Artificial Intelligence based RNA associated subcellular localization predictors have been developed which are summarized in Table 1 .…”