Prediction of T4SS Effector Proteins for Anaplasma phagocytophilum Using OPT4e, A New Software Tool

Abstract

Type IV secretion systems (T4SS) are used by a number of bacterial pathogens to attack the host cell. The complex protein structure of the T4SS is used to directly translocate effector proteins into host cells, often causing fatal diseases in humans and animals. Identification of effector proteins is the first step in understanding how they function to cause virulence and pathogenicity. Accurate prediction of effector proteins via a machine learning approach can assist in the process of their identification. The main goal of this study is to predict a set of candidate effectors for the tick-borne pathogen Anaplasma phagocytophilum , the causative agent of anaplasmosis in humans. To our knowledge, we present the first computational study for effector prediction with a focus on A. phagocytophilum . In a previous study, we systematically selected a set of optimal features from more than 1,000 possible protein characteristics for predicting T4SS effector candidates. This was followed by a study of the features using the proteome of Legionella pneumophila strain Philadelphia deduced from its complete genome. In this manuscript we introduce the OPT4e software package for Optimal-features Predictor for T4SS Effector proteins. An earlier version of OPT4e was verified using cross-validation tests, accuracy tests, and comparison with previous results for L. pneumophila . We use OPT4e to predict candidate effectors from the proteomes of A. phagocytophilum strains HZ and HGE-1 and predict 48 and 46 candidates, respectively, with 16 and 18 deemed most probable as effectors. These latter include the three known validated effectors for A. phagocytophilum .

Assessment of vector-host-pathogen relationships using data mining and machine learning

“… Wang, J., et al 2019 Prediction, Classification, Clustering NB, KNN, LR, RF, SVM, MLP Q1, Q2, Q3 Epigenomics, Genomics, Transcriptomics, Proteomics 5-fold cross-validation complementary features generally enhance the predictive performance of T4SEs; 30,385,576 [19] This study took sequence data from>500 single-stranded RNA viruses and used machine-learning algorithms to extract evolutionary signals imprinted in the virus sequence that offer information about its original hosts and if an arthropod vector, and what type, plays a part in the virus's natural ecology. Babayan, S. A., et al 2018 Prediction, Classification, AR PN, GLM, GBM Q1, Q2, Q3, Q5, Q6, Q7 Genomics, Transcriptomics, Population 83.5, (bagged accuracy = 97.0%) (bagged accuracy = 97.0%) genomic biases can coarsely discriminate viruses, viral codon pair and dinucleotide biases 31,293,540 [33] The main goal of this study is to predict a set of candidate effectors for the tick-borne pathogen Anaplasma phagocytophilum, the causative agent of anaplasmosis in humans. Esna Ashari.…”

“…These modeling approaches are able to reach an accuracy level of 60–95% and similar approaches have been used to predict the diagnosis and clinical prognosis of Dengue in human patients [31] Barman, R.K., et al also proposed a classification approach to identify infectious disease associated host genes by integrating sequence and protein interaction network features [32] . More directly related to vector-borne diseases, Esna Ashari et al used DM and ML to identify Type 4 Secretion System effectors that could be involved in the pathogenicity of the tick-borne bacterium Anaplasma phagocytophilum [33] , as has been done for non-vector-borne pathogens [34] , [35] , [36] .…”

Global Transcription Profiles of Anaplasma phagocytophilum at Key Stages of Infection in Tick and Human Cell Lines and Granulocytes

“…In contrast, Ap bacteria from ISE6 tick cells had a strong transcriptional response to contact with uninfected tick cells (Sample 3, Table S4A), displaying 48 genes that were upregulated in comparison to the control (2 h in medium). These included several genes that encoded structural components of the type 4 secretion system (T4SS) of Ap (two virB2, one virB6), or were predicted to be effectors, i.e., HGE1_01777, an HGE-14 paralog, and six hypothetical genes (21,22). The specific ISE6 host components that these putative effectors interact with are unknown, but it is predictable based on the divergent biology and structure of tick vs. human cells that Ap should be using specific effectors for vector and human host cells.…”

“…Three annotated HGE-14 genes (HGE1_01752, HGE1_01772, and HGE1_01782) and one on the same DNA strand between HGE1_01752 and HGE1_01772 that is not annotated are upregulated at 2 h with HL-60. HGE-14 proteins are putative effectors predicted to enter the host nucleus and alter transcription (21,22). Nucleotide positions in the genome are indicated by numbers above the gray line.…”

PARGT: a software tool for predicting antimicrobial resistance in bacteria

“…PARGT weight the importance of protein features based on their contributions during classification. All the required bioinformatics tools [33][34][35][36][37][38][39] and scripts necessary to generate the protein features required in our machine-learning model are included in PARGT. PARGT uses the best feature subset identified by our GTDWFE algorithm to make predictions.…”