Computational methods for protein localization prediction

Protein subcellular localization prediction tools

Protein subcellular localization prediction is of great significance in bioinformatics and biological research. Most of the proteins do not have experimentally determined localization information, computational prediction methods and tools have been acting as an active research area for more than two decades now. Knowledge of the subcellular location of a protein provides valuable information about its functionalities, the functioning of the cell, and other possible interactions with proteins. Fast, reliable, and accurate predictors provides platforms to harness the abundance of sequence data to predict subcellular locations accordingly. During the last decade, there has been a considerable amount of research effort aimed at developing subcellular localization predictors. This paper reviews recent subcellular localization prediction tools in the Eukaryotic, Prokaryotic, and Virus-based categories followed by a detailed analysis. Each predictor is discussed based on its main features, strengths, weaknesses, algorithms used, prediction techniques, and analysis. This review is supported by prediction tools taxonomies that highlight their rele- vant area and examples for uncomplicated categorization and ease of understandability. These taxonomies help users find suitable tools according to their needs. Furthermore, recent research gaps and challenges are discussed to cover areas that need the utmost attention. This survey provides an in-depth analysis of the most recent prediction tools to facilitate readers and can be considered a quick guide for researchers to identify and explore the recent literature advancements.

SCLpred-ECL: Subcellular Localization Prediction by Deep N-to-1 Convolutional Neural Networks

The subcellular location of a protein provides valuable insights to bioinformaticians in terms of drug designs and discovery, genomics, and various other aspects of medical research. Experimental methods for protein subcellular localization determination are time-consuming and expensive, whereas computational methods, if accurate, would represent a much more efficient alternative. This article introduces an ab initio protein subcellular localization predictor based on an ensemble of Deep N-to-1 Convolutional Neural Networks. Our predictor is trained and tested on strict redundancy-reduced datasets and achieves 63% accuracy for the diverse number of classes. This predictor is a step towards bridging the gap between a protein sequence and the protein's function. It can potentially provide information about protein-protein interaction to facilitate drug design and processes like vaccine production that are essential to disease prevention.

Genome-wide identification and expression profiling of the ABI5 gene family in foxtail millet (Setaria italica)

BACKGROUND

ABA Insensitive 5 (ABI5) is a basic leucine zipper transcription factor that crucially influences plant growth, development, and stress response. However, there is minimal research on the ABI5 family in foxtail millet.

RESULTS

In this study, 16 ABI5 genes were identified in foxtail millet, and their sequence composition, gene structures, cis-acting elements, chromosome positions, and gene replication events were analyzed. To more thoroughly evaluate the developmental mechanisms of the SiABI5 family during evolution, we selected three dicotyledons (S. lycopersicum, A. thaliana, F. tataricum) and three (Z. mays, O. sativa, S. bicolor) specific representative monocotyledons associated with foxtail millet for comparative homology mapping. The results showed that foxtail millet ABI5 genes had the best homology with maize. A promoter sequence analysis showed that the SiABI5s contain numerous cis-acting elements related to hormone and stress responses, indicating that the regulation of SiABI5 expression was complex. The expression responses of 16 genes in different tissues, seed germination, and ear development were analyzed. A total of six representative genes were targeted from five subfamilies to characterize their gene expression responses to four different abiotic stresses. Overexpression of SiABI5.12 confers tolerance to osmotic stress in transgenic Arabidopsis thaliana, which demonstrated the function of SiABI5 responded to abiotic stress.

CONCLUSIONS

In summary, our research results comprehensively characterized the SiABI5 family and can provide a valuable reference for demonstrating the role of SiABI5s in regulating abiotic stress responses in foxtail millet.

OsGSTU34, a Bz2-like anthocyanin-related glutathione transferase transporter, is essential for rice (Oryza sativa L.) organs coloration

Anthocyanins are a flavonoid compound known as one of the most important chromogenic substances. They play several functions, including health promotion and sustaining plants during adverse conditions. They are synthesized at the endoplasmic reticulum and sequestered in the vacuole. In this work, we generated knock-out lines of OsGSTU34, a glutathione transporter's tau gene family, with no transgene line and off-target through CRISPR/Cas9 mutagenesis and highlighted the loss of pigmentation in rice flowers, leaves, stems, shoots, and caryopsis. The anthocyanin quantification in the wild-type BLWT and mutant line BLG34-8 caryopsis showed that cyanidin-3-O-glucoside (C3G) and peonidin-3-O-glucoside (P3G) were almost undetectable in the mutant line. A tandem mass tag (TMT) labeling proteomic analysis was conducted to elucidate the proteomic changes in the BLWT and BLG34-8. The result revealed that 1175 proteins were altered, including 408 that were down-regulated and 767 that were upregulated. The accumulation of the OsGSTU34-related protein (Q8L576), along with several anthocyanin-related proteins, was down-regulated. The enrichment analysis showed that the down-regulated proteins were enriched in different pathways, among which the phenylpropanoid biosynthesis pathway, flavonoid biosynthesis metabolites, and anthocyanin biosynthesis pathway. Protein interaction network prediction revealed that glutathione-S-transferase (Q8L576) was connected to the proteins involved in the flavonoid and anthocyanin biosynthesis pathways, such as flavanone 3-dioxygenase 1 (Q7XM21), leucoanthocyanidin dioxygenase 1 (Q93VC3), 4-coumarate-CoA ligase 2 (Q42982), phenylalanine ammonia-lyase (P14717), chalcone synthase 1 (Q2R3A1), and 4-coumarate-CoA ligase 5 (Q6ZAC1). However, the expression of the most important anthocyanin biosynthesis gene was not altered, suggesting that only the transport mechanism was affected. Our findings highlight new insight into the anthocyanin pigmentation in black rice and provide new perspectives for future research.

B-Cell Epitope Prediction for Antipeptide Paratopes with the HAPTIC2/HEPTAD User Toolkit (HUT)

B-cell epitope prediction is key to developing peptide-based vaccines and immunodiagnostics along with antibodies for prophylactic, therapeutic and/or diagnostic use. This entails estimating paratope binding affinity for variable-length peptidic sequences subject to constraints on both paratope accessibility and antigen conformational flexibility, as described herein for the HAPTIC2/HEPTAD User Toolkit (HUT). HUT comprises the Heuristic Affinity Prediction Tool for Immune Complexes 2 (HAPTIC2), the HAPTIC2-like Epitope Prediction Tool for Antigen with Disulfide (HEPTAD) and the HAPTIC2/HEPTAD Input Preprocessor (HIP). HIP enables tagging of residues (e.g., in hydrophobic blobs, ordered regions and glycosylation motifs) for exclusion from downstream analyses by HAPTIC2 and HEPTAD. HAPTIC2 estimates paratope binding affinity for disulfide-free disordered peptidic antigens (by analogy between flexible-ligand docking and protein folding), from terms attributed to compaction (in view of sequence length, charge and temperature-dependent polyproline-II helical propensity), collapse (disfavored by residue bulkiness) and contact (with glycine and proline regarded as polar residues that hydrogen bond with paratopes). HEPTAD analyzes antigen sequences that each contain two cysteine residues for which the impact of disulfide pairing is estimated as a correction to the free-energy penalty of compaction. All of HUT is freely accessible online ( https://freeshell.de/~badong/hut.htm ).

CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

We present CELL-E 2, a novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and vice versa). Protein localization is a challenging problem that requires integrating sequence and image information, which most existing methods ignore. CELL-E 2 extends the work of CELL-E, not only capturing the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling de novo protein design. We train and finetune CELL-E 2 on two large-scale datasets of human proteins. We also demonstrate how to use CELL-E 2 to create hundreds of novel nuclear localization signals (NLS). Results and interactive demos are featured at https://bohuanglab.github.io/CELL-E_2/.

DeepSP: A Deep Learning Framework for Spatial Proteomics

The study of protein subcellular localization (PSL) is a fundamental step toward understanding the mechanism of protein function. The recent development of mass spectrometry (MS)-based spatial proteomics to quantify the distribution of proteins across subcellular fractions provides us a high-throughput approach to predict unknown PSLs based on known PSLs. However, the accuracy of PSL annotations in spatial proteomics is limited by the performance of existing PSL predictors based on traditional machine learning algorithms. In this study, we present a novel deep learning framework named DeepSP for PSL prediction of an MS-based spatial proteomics data set. DeepSP constructs the new feature map of a difference matrix by capturing detailed changes between different subcellular fractions of protein occupancy profiles and uses the convolutional block attention module to improve the prediction performance of PSL. DeepSP achieved significant improvement in accuracy and robustness for PSL prediction in independent test sets and unknown PSL prediction compared to current state-of-the-art machine learning predictors. As an efficient and robust framework for PSL prediction, DeepSP is expected to facilitate spatial proteomics studies and contributes to the elucidation of protein functions and the regulation of biological processes.

MULocDeep web service for protein localization prediction and visualization at subcellular and suborganellar levels

Predicting protein localization and understanding its mechanisms are critical in biology and pathology. In this context, we propose a new web application of MULocDeep with improved performance, result interpretation, and visualization. By transferring the original model into species-specific models, MULocDeep achieved competitive prediction performance at the subcellular level against other state-of-the-art methods. It uniquely provides a comprehensive localization prediction at the suborganellar level. Besides prediction, our web service quantifies the contribution of single amino acids to localization for individual proteins; for a group of proteins, common motifs or potential targeting-related regions can be derived. Furthermore, the visualizations of targeting mechanism analyses can be downloaded for publication-ready figures. The MULocDeep web service is available at https://www.mu-loc.org/.

Increasing the Efficiency of the Accumulation of Recombinant Proteins in Plant Cells: The Role of Transport Signal Peptides

The problem with increasing the yield of recombinant proteins is resolvable using different approaches, including the transport of a target protein to cell compartments with a low protease activity. In the cell, protein targeting involves short-signal peptide sequences recognized by intracellular protein transport systems. The main systems of the protein transport across membranes of the endoplasmic reticulum and endosymbiotic organelles are reviewed here, as are the major types and structure of the signal sequences targeting proteins to the endoplasmic reticulum and its derivatives, to plastids, and to mitochondria. The role of protein targeting to certain cell organelles depending on specific features of recombinant proteins and the effect of this targeting on the protein yield are discussed, in addition to the main directions of the search for signal sequences based on their primary structure. This knowledge makes it possible not only to predict a protein localization in the cell but also to reveal the most efficient sequences with potential biotechnological utility.

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

Prediction of subcellular localization of proteins from their amino acid sequences has a long history in bioinformatics and is still actively developing, incorporating the latest advances in machine learning and proteomics. Notably, deep learning-based methods for natural language processing have made great contributions. Here, we review recent advances in the field as well as its related fields, such as subcellular proteomics and the prediction/recognition of subcellular localization from image data.

Elucidation of the conformational dynamics and assembly of Argonaute−RNA complexes by distinct yet coordinated actions of the supplementary microRNA

Argonaute (AGO) proteins, the core of RNA-induced silencing complex, are guided by microRNAs (miRNAs) to recognize target RNA for repression. The miRNA–target RNA recognition forms initially through pairing at the seed region while the additional supplementary pairing can enhance target recognition and compensate for seed mismatch. The extension of miRNA lengths can strengthen the target affinity when pairing both in the seed and supplementary regions. However, the mechanism underlying the effect of the supplementary pairing on the conformational dynamics and the assembly of AGO–RNA complex remains poorly understood. To address this, we performed large-scale molecular dynamics simulations of AGO–RNA complexes with different pairing patterns and miRNA lengths. The results reveal that the additional supplementary pairing can not only strengthen the interaction between miRNA and target RNA, but also induce the increased plasticity of the PAZ domain and enhance the domain connectivity among the PAZ, PIWI, N domains of the AGO protein. The strong community network between these domains tightens the mouth of the supplementary chamber of AGO protein, which prevents the escape of target RNA from the complex and shields it from solvent water attack. Importantly, the inner stronger matching pairs between the miRNA and target RNA can compensate for weaker mismatches at the edge of supplementary region. These findings provide guidance for the design of miRNA mimics and anti-miRNAs for both clinical and experimental use and open the way for further engineering of AGO proteins as a new tool in the field of gene regulation.