Antimicrobial peptides (AMPs) are promising candidates in the fight against multidrug-resistant pathogens owing to AMPs’ broad range of activities and low toxicity. Nonetheless, identification of AMPs through wet-lab experiments is still expensive and time consuming. Here, we propose an accurate computational method for AMP prediction by the random forest algorithm. The prediction model is based on the distribution patterns of amino acid properties along the sequence. Using our collection of large and diverse sets of AMP and non-AMP data (3268 and 166791 sequences, respectively), we evaluated 19 random forest classifiers with different positive:negative data ratios by 10-fold cross-validation. Our optimal model, AmPEP with the 1:3 data ratio, showed high accuracy (96%), Matthew’s correlation coefficient (MCC) of 0.9, area under the receiver operating characteristic curve (AUC-ROC) of 0.99, and the Kappa statistic of 0.9. Descriptor analysis of AMP/non-AMP distributions by means of Pearson correlation coefficients revealed that reduced feature sets (from a full-featured set of 105 to a minimal-feature set of 23) can result in comparable performance in all respects except for some reductions in precision. Furthermore, AmPEP outperformed existing methods in terms of accuracy, MCC, and AUC-ROC when tested on benchmark datasets.

Antimicrobial peptides (AMPs) are a valuable source of antimicrobial agents and a potential solution to the multi-drug resistance problem. In particular, short-length AMPs have been shown to have enhanced antimicrobial activities, higher stability, and lower toxicity to human cells. We present a short-length (≤30 aa) AMP prediction method, Deep-AmPEP30, developed based on an optimal feature set of PseKRAAC reduced amino acids composition and convolutional neural network. On a balanced benchmark dataset of 188 samples, Deep-AmPEP30 yields an improved performance of 77% in accuracy, 85% in the area under the receiver operating characteristic curve (AUC-ROC), and 85% in area under the precision-recall curve (AUC-PR) over existing machine learning-based methods. To demonstrate its power, we screened the genome sequence of Candida glabrata-a gut commensal fungus expected to interact with and/or inhibit other microbes in the gut-for potential AMPs and identified a peptide of 20 aa (P3, FWELWKFLKSLWSIFPRRRP) with strong anti-bacteria activity against Bacillus subtilis and Vibrio parahaemolyticus. The potency of the peptide is remarkably comparable to that of ampicillin. Therefore, Deep-AmPEP30 is a promising prediction tool to identify short-length AMPs from genomic sequences for drug discovery. Our method is available at https://cbbio.cis.um.edu.mo/AxPEP for both individual sequence prediction and genome screening for AMPs.

Antimicrobial resistance has become a critical global health problem due to the abuse of conventional antibiotics and the rise of multi-drug-resistant microbes. Antimicrobial peptides (AMPs) are a group of natural peptides that show promise as next-generation antibiotics due to their low toxicity to the host, broad spectrum of biological activity, including antibacterial, antifungal, antiviral, and anti-parasitic activities, and great therapeutic potential, such as anticancer, anti-inflammatory, etc. Most importantly, AMPs kill bacteria by damaging cell membranes using multiple mechanisms of action rather than targeting a single molecule or pathway, making it difficult for bacterial drug resistance to develop. However, experimental approaches used to discover and design new AMPs are very expensive and time-consuming. In recent years, there has been considerable interest in using in silico methods, including traditional machine learning (ML) and deep learning (DL) approaches, to drug discovery. While there are a few papers summarizing computational AMP prediction methods, none of them focused on DL methods. In this review, we aim to survey the latest AMP prediction methods achieved by DL approaches. First, the biology background of AMP is introduced, then various feature encoding methods used to represent the features of peptide sequences are presented. We explain the most popular DL techniques and highlight the recent works based on them to classify AMPs and design novel peptide sequences. Finally, we discuss the limitations and challenges of AMP prediction.

Cancer is one of the leading causes of death worldwide. Conventional cancer treatment relies on radiotherapy and chemotherapy, but both methods bring severe side effects to patients, as these therapies not only attack cancer cells but also damage normal cells. Anticancer peptides (ACPs) are a promising alternative as therapeutic agents that are efficient and selective against tumor cells. Here, we propose a deep learning method based on convolutional neural networks to predict biological activity (EC50, LC50, IC50, and LD50) against six tumor cells, including breast, colon, cervix, lung, skin, and prostate. We show that models derived with multitask learning achieve better performance than conventional single-task models. In repeated 5-fold cross validation using the CancerPPD data set, the best models with the applicability domain defined obtain an average mean squared error of 0.1758, Pearson’s correlation coefficient of 0.8086, and Kendall’s correlation coefficient of 0.6156. As a step toward model interpretability, we infer the contribution of each residue in the sequence to the predicted activity by means of feature importance weights derived from the convolutional layers of the model. The present method, referred to as xDeep-AcPEP, will help to identify effective ACPs in rational peptide design for therapeutic purposes. The data, script files for reproducing the experiments, and the final prediction models can be downloaded from http://github.com/chen709847237/xDeep-AcPEP. The web server to directly access this prediction method is at https://app.cbbio.online/acpep/home.

As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these experiments time consuming and costly, but experiments that involve animal testing are increasingly subject to ethical concerns. While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance. Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL algorithm. Using the Tox21 data, our optimal SSL-GCN models for predicting the twelve toxicological endpoints achieve an average ROC-AUC score of 0.757 in the test set, which is a 6% improvement over GCN models trained by supervised learning and conventional ML methods. Our SSL-GCN models also exhibit superior performance when compared to models constructed using the built-in DeepChem ML methods. This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data. The optimal unannotated to annotated data ratio ranges between 1:1 and 4:1. This study demonstrates the success of SSL in chemical toxicity prediction; the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases. Our optimal model SSL-GCN is hosted on an online server accessible through: https://app.cbbio.online/ssl-gcn/home.

Air pollution in Macau has become a serious problem following the Pearl River Delta’s (PRD) rapid industrialization that began in the 1990s. With this in mind, Macau needs an air quality forecast system that accurately predicts pollutant concentration during the occurrence of pollution episodes to warn the public ahead of time. Five different state-of-the-art machine learning (ML) algorithms were applied to create predictive models to forecast PM_2.5, PM_10, and CO concentrations for the next 24 and 48 h, which included artificial neural networks (ANN), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multiple linear regression (MLR), to determine the best ML algorithms for the respective pollutants and time scale. The diurnal measurements of air quality data in Macau from 2016 to 2021 were obtained for this work. The 2020 and 2021 datasets were used for model testing, while the four-year data before 2020 and 2021 were used to build and train the ML models. Results show that the ANN, RF, XGBoost, SVM, and MLR models were able to provide good performance in building up a 24-h forecast with a higher coefficient of determination (R²) and lower root mean square error (RMSE), mean absolute error (MAE), and biases (BIAS). Meanwhile, all the ML models in the 48-h forecasting performance were satisfactory enough to be accepted as a two-day continuous forecast even if the R² value was lower than the 24-h forecast. The 48-h forecasting model could be further improved by proper feature selection based on the 24-h dataset, using the Shapley Additive Explanations (SHAP) value test and the adjusted R² value of the 48-h forecasting model. In conclusion, the above five ML algorithms were able to successfully forecast the 24 and 48 h of pollutant concentration in Macau, with the RF and SVM models performing the best in the prediction of PM_2.5 and PM₁₀, and CO in both 24 and 48-h forecasts.