A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites.

A Novel Gene Selection Algorithm based on Sparse Representation and Minimum-redundancy Maximum-relevancy of Maximum Compatibility Center

Background:

Tumor classification is important for accurate diagnosis and personalized treatment and has recently received great attention. Analysis of gene expression profile has shown relevant biological significance and thus has become a research hotspot and a new challenge for bio-data mining. In the research methods, some algorithms can identify few genes but with great time complexity, some algorithms can get small time complex methods but with unsatisfactory classification accuracy, this article proposed a new extraction method for gene expression profile.

Methods:

In this paper, we propose a classification method for tumor subtypes based on the Minimum- Redundancy Maximum-Relevancy (MRMR) of maximum compatibility center. First, we performed a fuzzy clustering of gene expression profiles based on the compatibility relation. Next, we used the sparse representation coefficient to assess the importance of the gene for the category, extracted the top-ranked genes, and removed the uncorrelated genes. Finally, the MRMR search strategy was used to select the characteristic gene, reject the redundant gene, and obtain the final subset of characteristic genes.

Results:

Our method and four others were tested on four different datasets to verify its effectiveness. Results show that the classification accuracy and standard deviation of our method are better than those of other methods.

Conclusion:

Our proposed method is robust, adaptable, and superior in classification. This method can help us discover the susceptibility genes associated with complex diseases and understand the interaction between these genes. Our technique provides a new way of thinking and is important to understand the pathogenesis of complex diseases and prevent diseases, diagnosis and treatment.

A Hybrid Deep Learning Model for Predicting Protein Hydroxylation Sites

Protein hydroxylation is one type of post-translational modifications (PTMs) playing critical roles in human diseases. It is known that protein sequence contains many uncharacterized residues of proline and lysine. The question that needs to be answered is: which residue can be hydroxylated, and which one cannot. The answer will not only help understand the mechanism of hydroxylation but can also benefit the development of new drugs. In this paper, we proposed a novel approach for predicting hydroxylation using a hybrid deep learning model integrating the convolutional neural network (CNN) and long short-term memory network (LSTM). We employed a pseudo amino acid composition (PseAAC) method to construct valid benchmark datasets based on a sliding window strategy and used the position-specific scoring matrix (PSSM) to represent samples as inputs to the deep learning model. In addition, we compared our method with popular predictors including CNN, iHyd-PseAAC, and iHyd-PseCp. The results for 5-fold cross-validations all demonstrated that our method significantly outperforms the other methods in prediction accuracy.

Global Similarity Method Based on a Two-tier Random Walk for the Prediction of microRNA-Disease Association

microRNAs (miRNAs) mutation and maladjustment are related to the occurrence and development of human diseases. Studies on disease-associated miRNA have contributed to disease diagnosis and treatment. To address the problems, such as low prediction accuracy and failure to predict the relationship between new miRNAs and diseases and so on, we design a Laplacian score of graphs to calculate the global similarity of networks and propose a Global Similarity method based on a Two-tier Random Walk for the prediction of miRNA-disease association (GSTRW) to reveal the correlation between miRNAs and diseases. This method is a global approach that can simultaneously predict the correlation between all diseases and miRNAs in the absence of negative samples. Experimental results reveal that this method is better than existing approaches in terms of overall prediction accuracy and ability to predict orphan diseases and novel miRNAs. A case study on GSTRW for breast cancer and conlon cancer is also conducted, and the majority of miRNA-disease association can be verified by our experiment. This study indicates that this method is feasible and effective.

Effects of type II collagen epitope carbamylation and citrullination in human leucocyte antigen (HLA)-DR4(+) monozygotic twins discordant for rheumatoid arthritis

The aim of this study is to investigate the effect of the native, citrullinated or carbamylated type II human collagen T cell- and B cell-epitopes on the adaptive immune response in rheumatoid arthritis (RA). Peripheral blood T and B cells obtained from a human leucocyte D4-related (antigen DR4(-) HLA-DR4)(+) woman with early RA, her healthy monozygotic twin and an unrelated HLA-DR3(+) woman with early RA were analysed for activation (CD154/CD69), apoptosis (annexin/7-aminoactinomycin), cytokine production [interferon (IFN)γ/interleukin (IL)-17/IL-4/IL-10/IL-6] and functional phenotype (CD45Ra/CCR7) after stimulation with the collagen native T cell epitope (T261-273), the K264 carbamylated T cell epitope (carT261-273), the native B cell epitope (B359-369) or the R360 citrullinated B cell epitope (citB359-369), and the combinations of these. The T cell memory compartment was activated by T cell epitopes in both discordant DR4(+) twins, but not in the DR3(+) RA. The collagen-specific activation of CD4(+) T cells was induced with both the native and carbamylated T cell epitopes only in the RA twin. Both T cell epitopes also induced IL-17 production in the RA twin, but a greater IL-4 and IL-10 response in the healthy twin. The citrullinated B cell epitope, particularly when combined with the carbamylated T cell epitope, induced B cell activation and an increased IL-6/IL-10 ratio in the RA twin compared to a greater IL-10 production in the healthy twin. Our data suggest that circulating collagen-specific T and B cells are found in HLA-DR4(+) subjects, but only RA activated cells express co-stimulatory molecules and produce proinflammatory cytokines. Carbamylation and citrullination further modulate the activation and cytokine polarization of T and B cells.

A method to distinguish between lysine acetylation and lysine ubiquitination with feature selection and analysis

Lysine acetylation and ubiquitination are two primary post-translational modifications (PTMs) in most eukaryotic proteins. Lysine residues are targets for both types of PTMs, resulting in different cellular roles. With the increasing availability of protein sequences and PTM data, it is challenging to distinguish the two types of PTMs on lysine residues. Experimental approaches are often laborious and time consuming. There is an urgent need for computational tools to distinguish between lysine acetylation and ubiquitination. In this study, we developed a novel method, called DAUFSA (distinguish between lysine acetylation and lysine ubiquitination with feature selection and analysis), to discriminate ubiquitinated and acetylated lysine residues. The method incorporated several types of features: PSSM (position-specific scoring matrix) conservation scores, amino acid factors, secondary structures, solvent accessibilities, and disorder scores. By using the mRMR (maximum relevance minimum redundancy) method and the IFS (incremental feature selection) method, an optimal feature set containing 290 features was selected from all incorporated features. A dagging-based classifier constructed by the optimal features achieved a classification accuracy of 69.53%, with an MCC of .3853. An optimal feature set analysis showed that the PSSM conservation score features and the amino acid factor features were the most important attributes, suggesting differences between acetylation and ubiquitination. Our study results also supported previous findings that different motifs were employed by acetylation and ubiquitination. The feature differences between the two modifications revealed in this study are worthy of experimental validation and further investigation.

Discriminating between lysine sumoylation and lysine acetylation using mRMR feature selection and analysis

Post-translational modifications (PTMs) are crucial steps in protein synthesis and are important factors contributing to protein diversity. PTMs play important roles in the regulation of gene expression, protein stability and metabolism. Lysine residues in protein sequences have been found to be targeted for both types of PTMs: sumoylations and acetylations; however, each PTM has a different cellular role. As experimental approaches are often laborious and time consuming, it is challenging to distinguish the two types of PTMs on lysine residues using computational methods. In this study, we developed a method to discriminate between sumoylated lysine residues and acetylated residues. The method incorporated several features: PSSM conservation scores, amino acid factors, secondary structures, solvent accessibilities and disorder scores. By using the mRMR (Maximum Relevance Minimum Redundancy) method and the IFS (Incremental Feature Selection) method, an optimal feature set was selected from all of the incorporated features, with which the classifier achieved 92.14% accuracy with an MCC value of 0.7322. Analysis of the optimal feature set revealed some differences between acetylation and sumoylation. The results from our study also supported the previous finding that there exist different consensus motifs for the two types of PTMs. The results could suggest possible dominant factors governing the acetylation and sumoylation of lysine residues, shedding some light on the modification dynamics and molecular mechanisms of the two types of PTMs, and provide guidelines for experimental validations.

Identifying functions of protein complexes based on topology similarity with random forest

Elucidating the functions of protein complexes is critical for understanding disease mechanisms, diagnosis and therapy. In this study, based on the concept that protein complexes with similar topology may have similar functions, we firstly model protein complexes as weighted graphs with nodes representing the proteins and edges indicating interaction between proteins. Secondly, we use topology features derived from the graphs to characterize protein complexes based on the graph theory. Finally, we construct a predictor by using random forest and topology features to identify the functions of protein complexes. Effectiveness of the current method is evaluated by identifying the functions of mammalian protein complexes. And then the predictor is also utilized to identify the functions of protein complexes retrieved from human protein-protein interaction networks. We identify some protein complexes with significant roles in the occurrence of tumors, vesicles and retinoblastoma. It is anticipated that the current research has an important impact on pathogenesis and the pharmaceutical industry. The source code of Matlab and the dataset are freely available on request from the authors.