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.

Machine Learning to Predict Contrast-Induced Acute Kidney Injury in Patients With Acute Myocardial Infarction

“…In our previous study (17), we found that Nomogrambased model gave better forecast accuracy results for CI-AKI in AMI patients, as compared to Mehran risk scores. Similar to the previous studies (17)(18)(19), our new data shows that machine learning models are superior to traditional logistic regression for developing predictive models. This finding makes sense because machine learning models are capable of learning complex discriminative features from large volumes of data without assumption of linearity.…”

Computational analysis and prediction of lysine malonylation sites by exploiting informative features in an integrative machine-learning framework

“…The evolutionary data in the form of Position-Specific Scoring Matrix (PSSM) profile are informative and have proved useful in a number of biological classification problems [28,[33][34][35][36][37][38][39][40][41][42][43][44][45]. In this work, the PSSM profile was generated by running PSI-BLAST against the uniref50 database with the parameters j = 3 and h = 0.001.…”

“…As one of the most widely used ML algorithms applied to classification problems [11,13,14,28,35,37,39,42,53], SVM [54] maps the input data into a high-dimensional space through the use of kernel functions and finds a hyperplane that maximizes the distance between the hyperplane and two types of samples. By mapping the unseen samples into the same space, SVM can predict the new samples based on which side of the hyperplane they fall in.…”

T4SE-XGB: Interpretable Sequence-Based Prediction of Type IV Secreted Effectors Using eXtreme Gradient Boosting Algorithm

“…To make a fair comparison, the same independent data set, which consists of 20 T4SEs and 139 non-T4SEs, was used for all models. Among these machine learning-based methods, the results showed that our T4SE-XGB model achieved the overall best performance with an ACC of 97.48%, F-value of 90.48% and MCC of 0.8916, followed by the state-of-the-art machine learning model called Bastion4 (Wang J. et al, 2019), which achieved 96.23% on ACC, 86.96% on F-value and 0.8579 on MCC. Moreover, the T4SE-XGB trained by fewer training samples also gets more stable prediction performance than the deep learningbased method named CNN-T4SE (VOTE 2/3), which takes the majority votes of the three best-performing convolutional neural network-based models (CNN-PSSM, CNNPSSSA, and CNN-Onehot).…”