Mislocalization-related disease gene discovery using gene expression based computational protein localization prediction

Anti-Osteoclast Effect of Exportin-1 Inhibitor Eltanexor on Osteoporosis Depends on Nuclear Accumulation of IκBα–NF-κB p65 Complex

Osteoporosis affects around 200 million people globally, with menopausal women accounting for the bulk of cases. In the occurrence and development of osteoporosis, a key role is played by osteoclasts. Excessive osteoclast-mediated bone resorption activity reduces bone mass and increases bone fragility, resulting in osteoporosis. Thus, considerable demand exists for designing effective osteoporosis treatments based on targeting osteoclasts. Eltanexor (Elt; KPT-8602) is a selective nuclear-export inhibitor that covalently binds to and blocks the function of the nuclear-export protein exportin-1 (XPO1), which controls the nucleus-to-cytoplasm transfer of certain critical proteins related to growth regulation and tumor suppression, such as p53, IκBα [nuclear factor-κB (NF-κB) inhibitor α] and FOXO1; among these proteins, IκBα, a critical component of the NF-κB signaling pathway that primarily governs NF-κB activation and transcription. How Elt treatment affects osteoclasts remains poorly elucidated. Elt inhibited the growth and activity of RANKL-induced osteoclasts in vitro in a dose-dependent manner, and Elt exerted no cell-killing effect within the effective inhibitory concentration. Mechanistically, Elt was found to trap IκBα in the nucleus and thus protect IκBα from proteasome degradation, which resulted in the blocking of the translocation of IκBα and NF-κB p65 and the consequent inhibition of NF-κB activity. The suppression of NF-κB activity, in turn, inhibited the activity of two transcription factors (NFATc1 and c-Fos) essential for osteoclast formation and led to the downregulation of genes and proteins related to bone resorption. Our study thus provides a newly identified mechanism for targeting in the treatment of osteoporosis.

Multiple Protein Subcellular Locations Prediction Based on Deep Convolutional Neural Networks with Self-Attention Mechanism

As an important research field in bioinformatics, protein subcellular location prediction is critical to reveal the protein functions and provide insightful information for disease diagnosis and drug development. Predicting protein subcellular locations remains a challenging task due to the difficulty of finding representative features and robust classifiers. Many feature fusion methods have been widely applied to tackle the above issues. However, they still suffer from accuracy loss due to feature redundancy. Furthermore, multiple protein subcellular locations prediction is more complicated since it is fundamentally a multi-label classification problem. The traditional binary classifiers or even multi-class classifiers cannot achieve satisfactory results. This paper proposes a novel method for protein subcellular location prediction with both single and multiple sites based on deep convolutional neural networks. Specifically, we first obtain the integrated features by simultaneously considering the pseudo amino acid, amino acid index distribution, and physicochemical property. We then adopt deep convolutional neural networks to extract high-dimensional features from the fused feature, removing the redundant preliminary features and gaining better representations of the raw sequences. Moreover, we use the self-attention mechanism and a customized loss function to ensure that the model is more inclined to positive data. In addition, we use random k-label sets to reduce the number of prediction labels. Meanwhile, we employ a hybrid strategy of over-sampling and under-sampling to tackle the data imbalance problem. We compare our model with three representative classification alternatives. The experiment results show that our model achieves the best performance in terms of accuracy, demonstrating the efficacy of the proposed model.

Incorporating label correlations into deep neural networks to classify protein subcellular location patterns in immunohistochemistry images

Analysis of protein subcellular localization is a critical part of proteomics. In recent years, as both the number and quality of microscopic images are increasing rapidly, many automated methods, especially convolutional neural networks (CNN), have been developed to predict protein subcellular location(s) based on bioimages, but their performance always suffers from some inherent properties of the problem. First, many microscopic images have non-informative or noisy sections, like unstained stroma and unspecific background, which affect the extraction of protein expression information. Second, the patterns of protein subcellular localization are very complex, as a lot of proteins locate in more than one compartment. In this study, we propose a new label-correlation enhanced deep neural network, laceDNN, to classify the subcellular locations of multi-label proteins from immunohistochemistry images. The model uses small representative patches as input to alleviate the image noise issue, and its backbone is a hybrid architecture of CNN and recurrent neural network, where the former network extracts representative image features and the latter learns the organelle dependency relationships. Our experimental results indicate that the proposed model can improve the performance of multi-label protein subcellular classification.

DPPN-SVM: Computational Identification of Mis-Localized Proteins in Cancers by Integrating Differential Gene Expressions With Dynamic Protein-Protein Interaction Networks

Eukaryotic cells contain numerous components, which are known as subcellular compartments or subcellular organelles. Proteins must be sorted to proper subcellular compartments to carry out their molecular functions. Mis-localized proteins are related to various cancers. Identifying mis-localized proteins is important in understanding the pathology of cancers and in developing therapies. However, experimental methods, which are used to determine protein subcellular locations, are always costly and time-consuming. We tried to identify cancer-related mis-localized proteins in three different cancers using computational approaches. By integrating gene expression profiles and dynamic protein-protein interaction networks, we established DPPN-SVM (Dynamic Protein-Protein Network with Support Vector Machine), a predictive model using the SVM classifier with diffusion kernels. With this predictive model, we identified a number of mis-localized proteins. Since we introduced the dynamic protein-protein network, which has never been considered in existing works, our model is capable of identifying more mis-localized proteins than existing studies. As far as we know, this is the first study to incorporate dynamic protein-protein interaction network in identifying mis-localized proteins in cancers.

Self-evoluting framework of deep convolutional neural network for multilocus protein subcellular localization

In the present paper, deep convolutional neural network (DCNN) is applied to multilocus protein subcellular localization as it is more suitable for multi-class classification. There are two main problems with this application. First, the appropriate features for correlation between multiple sites are hard to find. Second, the classifier structure is difficult to determine as it is greatly affected by the distribution of classified data. To solve these problems, a self-evoluting framework using DCNNs for multilocus protein subcellular localization is proposed. It has three characteristics that the previous algorithms do not. The first is that it combines the ant colony algorithm with the DCNN to form a self-evoluting algorithm for multilocus protein subcellular localization. The second is that it randomly groups subcellular sites using a limited random k-labelsets multi-label classification method. It also solves complex problems in a divide-and-conquer approach and proposes a flexible expansion model. The third is that it realizes the random selection feature extraction method in the positioning process and avoids the defects in individual feature extraction methods. The algorithm in the present paper is tested on the human database, and the overall correct rate is 67.17%, which is higher than that for the stacked self-encoder (SAE), support vector machine (SVM), random forest classifier (RF), or single deep convolutional neural network.Graphical abstract The algorithm mentioned in the present paper mainly includes four parts. They are protein sequence data preprocessing, integrated DCNN model construction, finding optimal DCNN combination by ant colony optimization, and protein subcellular localization for sequences. These parts are sequential relationships and the data obtained in the previous part is the basis for the latter part of the function. In the part of data preprocessing, the limited RAkEL multi-label classification method is used to randomly group subcellular sites. At the same time, the feature fusion of protein sequences is carried out by using multiple feature extraction methods. Each combination including features and sites information corresponds to a DCNN model. In the part of finding optimal DCNN combination by ant colony optimization, the main purpose is to find the best combination of DCNN models through the global optimization ability of the ant colony algorithm. The positioning of sequences is mainly to obtain multilocus subcellular localization by the optimal model combination.

Histological Analysis, Bioinformatics Profile, and Expression of Methylenetetrahydrofolate Reductase (MTHFR) in Bovine Testes

Simple Summary

To date, several genes have been sequenced but their corresponding protein characteristics remain unknown. This study highlights the histological structure of bovine (yellow-cattle and yak) testes as a build-up to exploring the bioinformatics profile and expression characteristics of methylenetetrahydrofolate reductase (MTHFR) in bovine testes. Our findings suggest that yellow-cattle testis have similar anatomical characteristics with that of yak, except for the weight or size, for which that of yellow-cattle is significantly higher or greater than yak. We also found that the secondary and 3D protein structures of MTHFR were similar to that of humans, with differences in the number of nucleotides, amino acids, and some physico-chemical characteristics. Moreover, MTHFR mRNA expression was higher in adult yellow-cattle and yak compared to their juvenile ones, however, its protein expression was higher but not statistically significant in adult yellow-cattle and yak compared to the juvenile ones. This provides a basis for further investigations into the regulatory function of MTHFR in bovine testes.

Abstract

Methylenetetrahydrofolate reductase (MTHFR), an enzyme expressed in mammalian testes, exerts a direct effect on spermatogenesis; however, its protein characteristics in bovine testes remain unknown. Here, we analysed bovine testicular structure, MTHFR bioinformatics profile, mRNA, and protein expression characteristics in yellow-cattle (y-c) and yak testis using histological procedures, bioinformatics analysis, qRT-PCR, and western blot. Testes from 13 bovines, ≤2 years juvenile (y-c, n = 3; yak, n = 3) and ≥3 years adult (y-c, n = 3; yak, n = 4) were collected and analysed. Anatomical characteristics of testis in y-c and yak were similar except the weight or size for which that of y-c was significantly higher or greater than yak. In y-c, an open reading frame (ORF) for 2600 nucleotides sequence, encoding 655 amino acids showed high homology with zebu cattle (99.51%) and wild yak (98.68%). Secondary and 3D protein structures were similar to that of humans with differences in the number of nucleotides, amino acids, and some physico-chemical characteristics. MTHFR mRNA expression in y-c and yak were significantly higher in adult testes compared with juvenile ones. However, its protein expression was higher, but not statistically significant, in adult y-c and yak compared to the juvenile ones. The highlights and inferences of these and other findings are discussed.

Learning complex subcellular distribution patterns of proteins via analysis of immunohistochemistry images

MOTIVATION

Systematic and comprehensive analysis of protein subcellular location as a critical part of proteomics ('location proteomics') has been studied for many years, but annotating protein subcellular locations and understanding variation of the location patterns across various cell types and states is still challenging.

RESULTS

In this work, we used immunohistochemistry images from the Human Protein Atlas as the source of subcellular location information, and built classification models for the complex protein spatial distribution in normal and cancerous tissues. The models can automatically estimate the fractions of protein in different subcellular locations, and can help to quantify the changes of protein distribution from normal to cancer tissues. In addition, we examined the extent to which different annotated protein pathways and complexes showed similarity in the locations of their member proteins, and then predicted new potential proteins for these networks.

AVAILABILITY AND IMPLEMENTATION

The dataset and code are available at: www.csbio.sjtu.edu.cn/bioinf/complexsubcellularpatterns.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Evaluation and Interpretation of Transcriptome Data Underlying Heterogeneous Chronic Obstructive Pulmonary Disease

Chronic obstructive pulmonary disease (COPD) is a type of progressive lung disease, featured by airflow obstruction. Recently, a comprehensive analysis of the transcriptome in lung tissue of COPD patients was performed, but the heterogeneity of the sample was not seriously considered in characterizing the mechanistic dysregulation of COPD. Here, we established a new transcriptome analysis pipeline using a deconvolution process to reduce the heterogeneity and clearly identified that these transcriptome data originated from the mild or moderate stage of COPD patients. Differentially expressed or co-expressed genes in the protein interaction subnetworks were linked with mitochondrial dysfunction and the immune response, as expected. Computational protein localization prediction revealed that 19 proteins showing changes in subcellular localization were mostly related to mitochondria, suggesting that mislocalization of mitochondria-targeting proteins plays an important role in COPD pathology. Our extensive evaluation of COPD transcriptome data could provide guidelines for analyzing heterogeneous gene expression profiles and classifying potential candidate genes that are responsible for the pathogenesis of COPD.

Alternatively spliced MEFV transcript lacking exon 2 and its protein isoform pyrin-2d implies an epigenetic regulation of the gene in inflammatory cell culture models

The function of gene body DNA methylation in alternative splicing, and its relation to disease pathogenesis is not fully elucidated. The gene for familial Mediterranean fever (MEFV) encodes the pyrin protein and contains a 998 bp CpG island, covering the second exon, which is differentially methylated in FMF patients compared to healthy controls. Our further observation of increased exon 2-spliced MEFV transcript in leukocytes of FMF patients provoked us to test the role of exon methylation in alternative splicing using inflammatory cell culture models. First, in vitro exon methylation triggered an increased level of exon 2 exclusion using a splicing cassette in a promyelocytic leukemia cell line (HL-60). HL-60 cells subjected to methylating and demethylating agents, as well as cells differentiated to neutrophil-like cells, exhibited different levels of spliced/unspliced transcripts. We observed increased levels of spliced transcripts in neutrophil-like (p = 0.0005), activated (p = 0.0034) and methylated cells (p < 0.0001), whereas decreased levels in demethylated cells (p = 0.0126) compared to control untreated HL-60 cells. We also showed that the protein isoform of pyrin lacking the exon 2 has an adverse subcellular localization in neutrophil-like cells. Therefore, it remains in the cytoplasm rather than the nucleus. This may point to an epigenetic involvement in an important inflammatory gene.