Dataset Information

Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches.

ABSTRACT: In the course of infecting their hosts, pathogenic bacteria secrete numerous effectors, namely, bacterial proteins that pervert host cell biology. Many Gram-negative bacteria, including context-dependent human pathogens, use a type IV secretion system (T4SS) to translocate effectors directly into the cytosol of host cells. Various type IV secreted effectors (T4SEs) have been experimentally validated to play crucial roles in virulence by manipulating host cell gene expression and other processes. Consequently, the identification of novel effector proteins is an important step in increasing our understanding of host-pathogen interactions and bacterial pathogenesis. Here, we train and compare six machine learning models, namely, Naïve Bayes (NB), K-nearest neighbor (KNN), logistic regression (LR), random forest (RF), support vector machines (SVMs) and multilayer perceptron (MLP), for the identification of T4SEs using 10 types of selected features and 5-fold cross-validation. Our study shows that: (1) including different but complementary features generally enhance the predictive performance of T4SEs; (2) ensemble models, obtained by integrating individual single-feature models, exhibit a significantly improved predictive performance and (3) the 'majority voting strategy' led to a more stable and accurate classification performance when applied to predicting an ensemble learning model with distinct single features. We further developed a new method to effectively predict T4SEs, Bastion4 (Bacterial secretion effector predictor for T4SS), and we show our ensemble classifier clearly outperforms two recent prediction tools. In summary, we developed a state-of-the-art T4SE predictor by conducting a comprehensive performance evaluation of different machine learning algorithms along with a detailed analysis of single- and multi-feature selections.

SUBMITTER: Wang J

PROVIDER: S-EPMC6585386 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches.

Wang Jiawei J Yang Bingjiao B An Yi Y Marquez-Lago Tatiana T Leier André A Wilksch Jonathan J Hong Qingyang Q Zhang Yang Y Hayashida Morihiro M Akutsu Tatsuya T Webb Geoffrey I GI Strugnell Richard A RA Song Jiangning J Lithgow Trevor T

Briefings in bioinformatics 20190501 3

In the course of infecting their hosts, pathogenic bacteria secrete numerous effectors, namely, bacterial proteins that pervert host cell biology. Many Gram-negative bacteria, including context-dependent human pathogens, use a type IV secretion system (T4SS) to translocate effectors directly into the cytosol of host cells. Various type IV secreted effectors (T4SEs) have been experimentally validated to play crucial roles in virulence by manipulating host cell gene expression and other processes. ...[more]

PMID: 29186295

Similar Datasets

Project description:Bacterial pathogens have evolved numerous strategies to corrupt, hijack or mimic cellular processes in order to survive and proliferate. Among those strategies, Type IV effectors (T4Es) are proteins secreted by pathogenic bacteria to manipulate host cell processes during infection. They are delivered into eukaryotic cells in an ATP-dependent manner via the type IV secretion system, a specialized multiprotein complex. T4Es contain a wide spectrum of features including eukaryotic-like domains, localization signals or a C-terminal translocation signal. A combination of these features enables prediction of T4Es in a given bacterial genome. In this study, we developed a web-based comprehensive suite of tools with a user-friendly graphical interface. This version 2.0 of S4TE (Searching Algorithm for Type IV Effector Proteins; http://sate.cirad.fr) enables accurate prediction and comparison of T4Es. Search parameters and threshold can be customized by the user to work with any genome sequence, whether publicly available or not. Applications range from characterizing effector features and identifying potential T4Es to analyzing the effectors based on the genome G+C composition and local gene density. S4TE 2.0 allows the comparison of putative T4E repertoires of up to four bacterial strains at the same time. The software identifies T4E orthologs among strains and provides a Venn diagram and lists of genes for each intersection. New interactive features offer the best visualization of the location of candidate T4Es and hyperlinks to NCBI and Pfam databases. S4TE 2.0 is designed to evolve rapidly with the publication of new experimentally validated T4Es, which will reinforce the predictive power of the algorithm. The computational methodology can be used to identify a wide spectrum of candidate bacterial effectors that lack sequence conservation but have similar amino acid characteristics. This approach will provide very valuable information about bacterial host-specificity and virulence factors and help identify host targets for the development of new anti-bacterial molecules.

Project description:Wheat leaf rust caused by Puccinia triticina is one of the most common and serious diseases in wheat production. The constantly changing pathogens overcome the plant resistance to P. triticina. Plant pathogens secrete effector proteins that alter the structure of the host cell, interfere plant defenses, or modify the physiology of plant cells. Therefore, the identification of effector proteins is critical to reveal the pathogenic mechanism. We used SignalP v4.1, TargetP v1.1, TMHMM v2.0, and EffectorP v2.0 to screen the candidate effector proteins in P. triticina isolates - KHTT, JHKT, and THSN. As a result, a total of 635 candidate effector proteins were obtained. Structural analysis showed that effector proteins were small in size (50AA to 422AA) and of diverse sequences, and the conserved sequential elements or clear common elements were not involved, regardless of their secretion from the pathogen to the host. There were 427 candidate effector proteins that contain more than or equal to 4 cysteine residues, and 339 candidate effector proteins contained the known motifs. Sixteen families, 9 domains, and 53 other known functional types were found in 186 candidate effector proteins using the Pfam search. Three novel motifs were found by MEME. Heterogeneous expression system was performed to verify the functions of 30 candidate effectors by inhibiting the programmed cell death (PCD) induced by BAX (the mouse-apoptotic gene elicitor) on Nicotiana benthamiana. Hypersensitive response (HR) can be induced by the six effectors in the wheat leaf rust resistance near isogenic lines, and this would be shown by the method of transient expression through Agrobacterium tumefaciens infiltration. The quantitative reverse transcription PCR (qRT-PCR) analysis of 14 candidate effector proteins secreted after P. triticina inoculation showed that the tested effectors displayed different expression patterns in different stages, suggesting that they may be involved in the wheat-P. triticina interaction. The results showed that the prediction of P. triticina effector proteins based on transcriptomic analysis and multiple bioinformatics software is effective and more accurate, laying the foundation of revealing the pathogenic mechanism of Pt and controlling disease.

Project description:The type III secretion system (TTSS) is a key mechanism for host cell interaction used by a variety of bacterial pathogens and symbionts of plants and animals including humans. The TTSS represents a molecular syringe with which the bacteria deliver effector proteins directly into the host cell cytosol. Despite the importance of the TTSS for bacterial pathogenesis, recognition and targeting of type III secreted proteins has up until now been poorly understood. Several hypotheses are discussed, including an mRNA-based signal, a chaperon-mediated process, or an N-terminal signal peptide. In this study, we systematically analyzed the amino acid composition and secondary structure of N-termini of 100 experimentally verified effector proteins. Based on this, we developed a machine-learning approach for the prediction of TTSS effector proteins, taking into account N-terminal sequence features such as frequencies of amino acids, short peptides, or residues with certain physico-chemical properties. The resulting computational model revealed a strong type III secretion signal in the N-terminus that can be used to detect effectors with sensitivity of approximately 71% and selectivity of approximately 85%. This signal seems to be taxonomically universal and conserved among animal pathogens and plant symbionts, since we could successfully detect effector proteins if the respective group was excluded from training. The application of our prediction approach to 739 complete bacterial and archaeal genome sequences resulted in the identification of between 0% and 12% putative TTSS effector proteins. Comparison of effector proteins with orthologs that are not secreted by the TTSS showed no clear pattern of signal acquisition by fusion, suggesting convergent evolutionary processes shaping the type III secretion signal. The newly developed program EffectiveT3 (http://www.chlamydiaedb.org) is the first universal in silico prediction program for the identification of novel TTSS effectors. Our findings will facilitate further studies on and improve our understanding of type III secretion and its role in pathogen-host interactions.

Dataset Information

Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches.

Publications

Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets