Pseudouridylation is the most prevalent type of posttranscriptional modification in various stable RNAs of all organisms, which significantly affects many cellular processes that are regulated by RNA. Thus, accurate identification of pseudouridine (Ψ) sites in RNA will be of great benefit for understanding these cellular processes. Due to the low efficiency and high cost of current available experimental methods, it is highly desirable to develop computational methods for accurately and efficiently detecting Ψ sites in RNA sequences. However, the predictive accuracy of existing computational methods is not satisfactory and still needs improvement. In this study, we developed a new model, PseUI, for Ψ sites identification in three species, which are H. sapiens, S. cerevisiae, and M. musculus. Firstly, five different kinds of features including nucleotide composition (NC), dinucleotide composition (DC), pseudo dinucleotide composition (pseDNC), position-specific nucleotide propensity (PSNP), and position-specific dinucleotide propensity (PSDP) were generated based on RNA segments. Then, a sequential forward feature selection strategy was used to gain an effective feature subset with a compact representation but discriminative prediction power. Based on the selected feature subsets, we built our model by using a support vector machine (SVM). Finally, the generalization of our model was validated by both the jackknife test and independent validation tests on the benchmark datasets. The experimental results showed that our model is more accurate and stable than the previously published models. We have also provided a user-friendly web server for our model at http://zhulab.ahu.edu.cn/PseUI , and a brief instruction for the web server is provided in this paper. By using this instruction, the academic users can conveniently get their desired results without complicated calculations. In this study, we proposed a new predictor, PseUI, to detect Ψ sites in RNA sequences. It is shown that our model outperformed the existing state-of-art models. It is expected that our model, PseUI, will become a useful tool for accurate identification of RNA Ψ sites.

Gram-negative bacteria use various secretion systems to deliver their secreted effectors. Among them, type IV secretion system exists widely in a variety of bacterial species, and secretes type IV secreted effectors (T4SEs), which play vital roles in host-pathogen interactions. However, experimental approaches to identify T4SEs are time- and resource-consuming. In the present study, we aim to develop an in silico stacked ensemble method to predict whether a protein is an effector of type IV secretion system or not based on its sequence information. The protein sequences were encoded by the feature of position specific scoring matrix (PSSM)-composition by summing rows that correspond to the same amino acid residues in PSSM profiles. Based on the PSSM-composition features, we develop a stacked ensemble model PredT4SE-Stack to predict T4SEs, which utilized an ensemble of base-classifiers implemented by various machine learning algorithms, such as support vector machine, gradient boosting machine, and extremely randomized trees, to generate outputs for the meta-classifier in the classification system. Our results demonstrated that the framework of PredT4SE-Stack was a feasible and effective way to accurately identify T4SEs based on protein sequence information. The datasets and source code of PredT4SE-Stack are freely available at http://xbioinfo.sjtu.edu.cn/PredT4SE_Stack/index.php.

Hot spots are interface residues that contribute most binding affinity to protein-protein interaction. A compact and relevant feature subset is important for building machine learning methods to predict hot spots on protein-protein interfaces. Although different methods have been used to detect the relevant feature subset from a variety of features related to interface residues, it is still a challenge to detect the optimal feature subset for building the final model. In this study, three different feature selection methods were compared to propose a new hybrid feature selection strategy. This new strategy was proved to effectively reduce the feature space when we were building the prediction models for identifying hotspot residues. It was tested on eighty-two features, both conventional and newly proposed. According to the strategy, combining the feature subsets selected by decision tree and mRMR (maximum Relevance Minimum Redundancy) individually, we were able to build a model with 6 features by using a PSFS (Pseudo Sequential Forward Selection) process. Compared with other state-of-art methods for the independent test set, our model had shown better or comparable predictive performances (with F-measure 0.622 and recall 0.821). Analysis of the 6 features confirmed that our newly proposed feature CNSV_REL1 was important for our model. The analysis also showed that the complementarity between features should be considered as an important aspect when conducting the feature selection. In this study, most important of all, a new strategy for feature selection was proposed and proved to be effective in selecting the optimal feature subset for building prediction models, which can be used to predict hot spot residues on protein-protein interfaces. Moreover, two aspects, the generalization of the single feature and the complementarity between features, were proved to be of great importance and should be considered in feature selection methods. Finally, our newly proposed feature CNSV_REL1 had been proved an alternative and effective feature in predicting hot spots by our study. Our model is available for users through a webserver: http://zhulab.ahu.edu.cn/iPPHOT/ .

As one of the most important post-translational modifications (PTMs), protein lysine crotonylation (Kcr) has attracted wide attention, which involves in important physiological activities, such as cell differentiation and metabolism. However, experimental methods are expensive and time-consuming for Kcr identification. Instead, computational methods can predict Kcr sites in silico with high efficiency and low cost. In this study, we proposed a novel predictor, BERT-Kcr, for protein Kcr sites prediction, which was developed by using a transfer learning method with pre-trained bidirectional encoder representations from transformers (BERT) models. These models were originally used for natural language processing (NLP) tasks, such as sentence classification. Here, we transferred each amino acid into a word as the input information to the pre-trained BERT model. The features encoded by BERT were extracted and then fed to a BiLSTM network to build our final model. Compared with the models built by other machine learning and deep learning classifiers, BERT-Kcr achieved the best performance with AUROC of 0.983 for 10-fold cross validation. Further evaluation on the independent test set indicates that BERT-Kcr outperforms the state-of-the-art model Deep-Kcr with an improvement of about 5% for AUROC. The results of our experiment indicate that the direct use of sequence information and advanced pre-trained models of NLP could be an effective way for identifying PTM sites of proteins. The BERT-Kcr model is publicly available on http://zhulab.org.cn/BERT-Kcr_models/. Supplementary data are available at Bioinformatics online.

5-methylcytosine (m5C) is one of the most common and abundant post-transcriptional modifications (PTCMs) in RNA. Recent studies showed that m5C plays important roles in many biological functions such as RNA metabolism and cell fate decision. Because most experimental methods that determine m5C sites across the transcriptome are time-consuming and expensive, it is urgent to develop accurate computational methods to identify m5C sites effectively. A benchmark dataset is important for developing and evaluating computational methods. In this work, we constructed four different datasets according to the data redundancy and imbalance. Based on these datasets, we generated three different kinds of features, i.e., KNFs (K-nucleotide frequencies), KSNPFs (K-spaced nucleotide pair frequencies), and pseDNC (pseudo-dinucleotide composition), and then used a support vector machine (SVM) to build our models. Based on the imbalanced and nonredundant dataset, Met935, we extensively studied the three kinds of features and determined an optimal combination of the features. Based on the feature combination, we built models on the three different datasets and compared them with state-of-the-art models. According to the predictive results of the stringent jackknife test, the models based on the three features, 4NF, 1SNPF, and pseDNC, are superior or comparable to other methods. To determine the best model between the models based on the imbalanced dataset Met935 and the balanced dataset Met240, we further evaluated the two models on an independent test set Test1157. Our results demonstrate that the model based on the balanced dataset Met240 achieved the highest recall (68.79%) and the highest Matthews correlation coefficient (MCC) (0.154). In addition, the model is also superior to other state-of-the-art methods according to the integrated parameter MCC on the independent test set. Thus, we selected the model based on Met240 as our final model, which was named RNAm5CPred. In addition, a web server for RNAm5CPred (http://zhulab.ahu.edu.cn/RNAm5CPred/) has been provided to facilitate experimental research.

Protein–nucleic acid interactions play essential roles in various biological activities such as gene regulation, transcription, DNA repair and DNA packaging. Understanding the effects of amino acid substitutions on protein–nucleic acid binding affinities can help elucidate the molecular mechanism of protein–nucleic acid recognition. Until now, no comprehensive and updated database of quantitative binding data on alanine mutagenic effects for protein–nucleic acid interactions is publicly accessible. Thus, we developed a new database of Alanine Mutagenic Effects for Protein-Nucleic Acid Interactions (dbAMEPNI). dbAMEPNI is a manually curated, literature-derived database, comprising over 577 alanine mutagenic data with experimentally determined binding affinities for protein–nucleic acid complexes. It contains several important parameters, such as dissociation constant (K_d), Gibbs free energy change (ΔΔG), experimental conditions and structural parameters of mutant residues. In addition, the database provides an extended dataset of 282 single alanine mutations with only qualitative data (or descriptive effects) of thermodynamic information. Database URL: http://zhulab.ahu.edu.cn/dbAMEPNI