Identifying multi-functional bioactive peptide functions using multi-label deep learning.

The bioactive peptide has wide functions, such as lowering blood glucose levels and reducing inflammation. Meanwhile, computational methods such as machine learning are becoming more and more important for peptide functions prediction. Most of the previous studies concentrate on the single-functional bioactive peptides prediction. However, the number of multi-functional peptides is on the increase; therefore, novel computational methods are needed. In this study, we develop a method MLBP (Multi-Label deep learning approach for determining the multi-functionalities of Bioactive Peptides), which can predict multiple functions including anti-cancer, anti-diabetic, anti-hypertensive, anti-inflammatory and anti-microbial simultaneously. MLBP model takes the peptide sequence vector as input to replace the biological and physiochemical features used in other peptides predictors. Using the embedding layer, the dense continuous feature vector is learnt from the sequence vector. Then, we extract convolution features from the feature vector through the convolutional neural network layer and combine with the bidirectional gated recurrent unit layer to improve the prediction performance. The 5-fold cross-validation experiments are conducted on the training dataset, and the results show that Accuracy and Absolute true are 0.695 and 0.685, respectively. On the test dataset, Accuracy and Absolute true of MLBP are 0.709 and 0.697, with 5.0 and 4.7% higher than those of the suboptimum method, respectively. The results indicate MLBP has superior prediction performance on the multi-functional peptides identification. MLBP is available at https://github.com/xialab-ahu/MLBP and http://bioinfo.ahu.edu.cn/MLBP/.

PrMFTP: Multi-functional therapeutic peptides prediction based on multi-head self-attention mechanism and class weight optimization.

Prediction of therapeutic peptide is a significant step for the discovery of promising therapeutic drugs. Most of the existing studies have focused on the mono-functional therapeutic peptide prediction. However, the number of multi-functional therapeutic peptides (MFTP) is growing rapidly, which requires new computational schemes to be proposed to facilitate MFTP discovery. In this study, based on multi-head self-attention mechanism and class weight optimization algorithm, we propose a novel model called PrMFTP for MFTP prediction. PrMFTP exploits multi-scale convolutional neural network, bi-directional long short-term memory, and multi-head self-attention mechanisms to fully extract and learn informative features of peptide sequence to predict MFTP. In addition, we design a class weight optimization scheme to address the problem of label imbalanced data. Comprehensive evaluation demonstrate that PrMFTP is superior to other state-of-the-art computational methods for predicting MFTP. We provide a user-friendly web server of PrMFTP, which is available at http://bioinfo.ahu.edu.cn/PrMFTP.

BBPpred: Sequence-Based Prediction of Blood-Brain Barrier Peptides with Feature Representation Learning and Logistic Regression.

Blood-brain barrier peptides (BBPs) have a large range of biomedical applications since they can cross the blood-brain barrier based on different mechanisms. As experimental methods for the identification of BBPs are laborious and expensive, computational approaches are necessary to be developed for predicting BBPs. In this work, we describe a computational method, BBPpred (blood-brain barrier peptides prediction), that can efficiently identify BBPs using logistic regression. We investigate a wide variety of features from amino acid sequence information, and then a feature learning method is adopted to represent the informative features. To improve the prediction performance, seven informative features are selected for classification by eliminating redundant and irrelevant features. In addition, we specifically create two benchmark data sets (training and independent test), which contain a total of 119 BBPs from public databases and the literature. On the training data set, BBPpred shows promising performances with an AUC score of 0.8764 and an AUPR score of 0.8757 using the 10-fold cross-validation. We also test our new method on the independent test data set and obtain a favorable performance. We envision that BBPpred will be a useful tool for identifying, annotating, and characterizing BBPs. BBPpred is freely available at http://BBPpred.xialab.info.

Prediction of Neuropeptides from Sequence Information Using Ensemble Classifier and Hybrid Features.

As hormones in the endocrine system and neurotransmitters in the immune system, neuropeptides (NPs) provide many opportunities for the discovery of new drugs and targets for nervous system disorders. In spite of their importance in the hormonal regulations and immune responses, the bioinformatics predictor for the identification of NPs is lacking. In this study, we develop a predictor for the identification of NPs, named PredNeuroP, based on a two-layer stacking method. In this ensemble predictor, 45 models are introduced as base-learners by combining nine feature descriptors with five machine learning algorithms. Then, we select eight base-learners referring to the sum of accuracy and Pearson correlation coefficient of base-learner pairs on the first-layer learning. On the second-layer learning, the outputs of these advisable base-learners are imported into logistic regression classifier to train the final model, and the outputs are the final predicting results. The accuracy of PredNeuroP is 0.893 and 0.872 on the training and test data sets, respectively. The consistent performance on these data sets approves the practicability of our predictor. Therefore, we expect that PredNeuroP would provide an important advancement in the discovery of NPs as new drugs for the treatment of nervous system disorders. The data sets and Python code are available at https://github.com/xialab-ahu/PredNeuroP.

PredAPP: Predicting Anti-Parasitic Peptides with Undersampling and Ensemble Approaches.

Anti-parasitic peptides (APPs) have been regarded as promising therapeutic candidate drugs against parasitic diseases. Due to the fact that the experimental techniques for identifying APPs are expensive and time-consuming, there is an urgent need to develop a computational approach to predict APPs on a large scale. In this study, we provided a computational method, termed PredAPP (Prediction of Anti-Parasitic Peptides) that could effectively identify APPs using an ensemble of well-performed machine learning (ML) classifiers. Firstly, to solve the class imbalance problem, a balanced training dataset was generated by the undersampling method. We found that the balanced dataset based on cluster centroid achieved the best performance. Then, nine groups of features and six ML algorithms were combined to generate 54 classifiers and the output of these classifiers formed 54 feature representations, and in each feature group, we selected the feature representation with best performance for classification. Finally, the selected feature representations were integrated using logistic regression algorithm to construct the prediction model PredAPP. On the independent dataset, PredAPP achieved accuracy and AUC of 0.880 and 0.922, respectively, compared to 0.739 and 0.873 of AMPfun, a state-of-the-art method to predict APPs. The web server of PredAPP is freely accessible at http://predapp.xialab.info and https://github.com/xialab-ahu/PredAPP .

Sequence-Based Prediction of Transmembrane Protein Crystallization Propensity.

Transmembrane proteins play a vital role in cell life activities. There are several techniques to determine transmembrane protein structures and X-ray crystallography is the primary methodology. However, due to the special properties of transmembrane proteins, it is still hard to determine their structures by X-ray crystallography technique. To reduce experimental consumption and improve experimental efficiency, it is of great significance to develop computational methods for predicting the crystallization propensity of transmembrane proteins. In this work, we proposed a sequence-based machine learning method, namely Prediction of TransMembrane protein Crystallization propensity (PTMC), to predict the propensity of transmembrane protein crystallization. First, we obtained several general sequence features and the specific encoded features of relative solvent accessibility and hydrophobicity. Second, feature selection was employed to filter out redundant and irrelevant features, and the optimal feature subset is composed of hydrophobicity, amino acid composition and relative solvent accessibility. Finally, we chose extreme gradient boosting by comparing with other several machine learning methods. Comparative results on the independent test set indicate that PTMC outperforms state-of-the-art sequence-based methods in terms of sensitivity, specificity, accuracy, Matthew's Correlation Coefficient (MCC) and Area Under the receiver operating characteristic Curve (AUC). In comparison with two competitors, Bcrystal and TMCrys, PTMC achieves an improvement by 0.132 and 0.179 for sensitivity, 0.014 and 0.127 for specificity, 0.037 and 0.192 for accuracy, 0.128 and 0.362 for MCC, and 0.027 and 0.125 for AUC, respectively.