Comparative analysis of machine learning-based approaches for identifying therapeutic peptides targeting SARS-CoV-2

Physicochemical properties-based hybrid machine learning technique for the prediction of SARS-CoV-2 T-cell epitopes as vaccine targets

Majority of the existing SARS-CoV-2 vaccines work by presenting the whole pathogen in the attenuated form to immune system to invoke an immune response. On the other hand, the concept of a peptide based vaccine (PBV) is based on the identification and chemical synthesis of only immunodominant peptides known as T-cell epitopes (TCEs) to induce a specific immune response against a particular pathogen. However PBVs have received less attention despite holding huge untapped potential for boosting vaccine safety and immunogenicity. To identify these TCEs for designing PBV, wet-lab experiments are difficult, expensive, and time-consuming. Machine learning (ML) techniques can accurately predict TCEs, saving time and cost for speedy vaccine development. This work proposes novel hybrid ML techniques based on the physicochemical properties of peptides to predict SARS-CoV-2 TCEs. The proposed hybrid ML technique was evaluated using various ML model evaluation metrics and demonstrated promising results. The hybrid technique of decision tree classifier with chi-squared feature weighting technique and forward search optimal feature searching algorithm has been identified as the best model with an accuracy of 98.19%. Furthermore, K-fold cross-validation (KFCV) was performed to ensure that the model is reliable and the results indicate that the hybrid random forest model performs consistently well in terms of accuracy with respect to other hybrid approaches. The predicted TCEs are highly likely to serve as promising vaccine targets, subject to evaluations both in-vivo and in-vitro. This development could potentially save countless lives globally, prevent future epidemic-scale outbreaks, and reduce the risk of mutation escape.

iAVPs-ResBi: Identifying antiviral peptides by using deep residual network and bidirectional gated recurrent unit

Human history is also the history of the fight against viral diseases. From the eradication of viruses to coexistence, advances in biomedicine have led to a more objective understanding of viruses and a corresponding increase in the tools and methods to combat them. More recently, antiviral peptides (AVPs) have been discovered, which due to their superior advantages, have achieved great impact as antiviral drugs. Therefore, it is very necessary to develop a prediction model to accurately identify AVPs. In this paper, we develop the iAVPs-ResBi model using k-spaced amino acid pairs (KSAAP), encoding based on grouped weight (EBGW), enhanced grouped amino acid composition (EGAAC) based on the N5C5 sequence, composition, transition and distribution (CTD) based on physicochemical properties for multi-feature extraction. Then we adopt bidirectional long short-term memory (BiLSTM) to fuse features for obtaining the most differentiated information from multiple original feature sets. Finally, the deep model is built by combining improved residual network and bidirectional gated recurrent unit (BiGRU) to perform classification. The results obtained are better than those of the existing methods, and the accuracies are 95.07, 98.07, 94.29 and 97.50% on the four datasets, which show that iAVPs-ResBi can be used as an effective tool for the identification of antiviral peptides. The datasets and codes are freely available at https://github.com/yunyunliang88/iAVPs-ResBi.

Computational prediction of allergenic proteins based on multi-feature fusion

Allergy is an autoimmune disorder described as an undesirable response of the immune system to typically innocuous substance in the environment. Studies have shown that the ability of proteins to trigger allergic reactions in susceptible individuals can be evaluated by bioinformatics tools. However, developing computational methods to accurately identify new allergenic proteins remains a vital challenge. This work aims to propose a machine learning model based on multi-feature fusion for predicting allergenic proteins efficiently. Firstly, we prepared a benchmark dataset of allergenic and non-allergenic protein sequences and pretested on it with a machine-learning platform. Then, three preferable feature extraction methods, including amino acid composition (AAC), dipeptide composition (DPC) and composition of k-spaced amino acid pairs (CKSAAP) were chosen to extract protein sequence features. Subsequently, these features were fused and optimized by Pearson correlation coefficient (PCC) and principal component analysis (PCA). Finally, the most representative features were picked out to build the optimal predictor based on random forest (RF) algorithm. Performance evaluation results via 5-fold cross-validation showed that the final model, called iAller (https://github.com/laihongyan/iAller), could precisely distinguish allergenic proteins from non-allergenic proteins. The prediction accuracy and AUC value for validation dataset achieved 91.4% and 0.97%, respectively. This model will provide guide for users to identify more allergenic proteins.

ACP-Dnnel: anti-coronavirus peptides' prediction based on deep neural network ensemble learning

The ongoing COVID-19 pandemic has caused dramatic loss of human life. There is an urgent need for safe and efficient anti-coronavirus infection drugs. Anti-coronavirus peptides (ACovPs) can inhibit coronavirus infection. With high-efficiency, low-toxicity, and broad-spectrum inhibitory effects on coronaviruses, they are promising candidates to be developed into a new type of anti-coronavirus drug. Experiment is the traditional way of ACovPs' identification, which is less efficient and more expensive. With the accumulation of experimental data on ACovPs, computational prediction provides a cheaper and faster way to find anti-coronavirus peptides' candidates. In this study, we ensemble several state-of-the-art machine learning methodologies to build nine classification models for the prediction of ACovPs. These models were pre-trained using deep neural networks, and the performance of our ensemble model, ACP-Dnnel, was evaluated across three datasets and independent dataset. We followed Chou's 5-step rules. (1) we constructed the benchmark datasets data1, data2, and data3 for training and testing, and introduced the independent validation dataset ACVP-M; (2) we analyzed the peptides sequence composition feature of the benchmark dataset; (3) we constructed the ACP-Dnnel model with deep convolutional neural network (DCNN) merged the bi-directional long short-term memory (BiLSTM) as the base model for pre-training to extract the features embedded in the benchmark dataset, and then, nine classification algorithms were introduced to ensemble together for classification prediction and voting together; (4) tenfold cross-validation was introduced during the training process, and the final model performance was evaluated; (5) finally, we constructed a user-friendly web server accessible to the public at http://150.158.148.228:5000/ . The highest accuracy (ACC) of ACP-Dnnel reaches 97%, and the Matthew's correlation coefficient (MCC) value exceeds 0.9. On three different datasets, its average accuracy is 96.0%. After the latest independent dataset validation, ACP-Dnnel improved at MCC, SP, and ACC values 6.2%, 7.5% and 6.3% greater, respectively. It is suggested that ACP-Dnnel can be helpful for the laboratory identification of ACovPs, speeding up the anti-coronavirus peptide drug discovery and development. We constructed the web server of anti-coronavirus peptides' prediction and it is available at http://150.158.148.228:5000/ .

PRR-HyPred: A two-layer hybrid framework to predict pattern recognition receptors and their families by employing sequence encoded optimal features

Pattern recognition receptors (PRRs) recognize distinct features on the surface of pathogens or damaged cells and play key roles in the innate immune system. PRRs are divided into various families, including Toll-like receptors, retinoic acid-inducible gene-I-like receptors, nucleotide oligomerization domain-like receptors, and C-type lectin receptors. As these are implicated in host health and several diseases, their accurate identification is indispensable for their functional characterization and targeted therapeutic approaches. Here, we construct PRR-HyPred, a novel two-layer hybrid framework in which the first layer predicts whether a given sequence is PRR or non-PRR using a support vector machine, and in the second, the predicted PRR sequence is assigned to a specific family using a random forest-based classifier. Based on a 10-fold cross-validation test, PRR-HyPred achieved 83.4 % accuracy in the first layer and 95 % in the second, with Matthew's correlation coefficient values of 0.639 and 0.816, respectively. This is the first study that can simultaneously predict and classify PRRs into specific families. PRR-HyPred is available as a web portal at https://procarb.org/PRRHyPred/. We hope that it could be a valuable tool for the large-scale prediction and classification of PRRs and subsequently facilitate future studies.

EdeepSADPr: an extensive deep-learning architecture for prediction of the in situ crosstalks of serine phosphorylation and ADP-ribosylation

The in situ post-translational modification (PTM) crosstalk refers to the interactions between different types of PTMs that occur on the same residue site of a protein. The crosstalk sites generally have different characteristics from those with the single PTM type. Studies targeting the latter's features have been widely conducted, while studies on the former's characteristics are rare. For example, the characteristics of serine phosphorylation (pS) and serine ADP-ribosylation (SADPr) have been investigated, whereas those of their in situ crosstalks (pSADPr) are unknown. In this study, we collected 3,250 human pSADPr, 7,520 SADPr, 151,227 pS and 80,096 unmodified serine sites and explored the features of the pSADPr sites. We found that the characteristics of pSADPr sites are more similar to those of SADPr compared to pS or unmodified serine sites. Moreover, the crosstalk sites are likely to be phosphorylated by some kinase families (e.g., AGC, CAMK, STE and TKL) rather than others (e.g., CK1 and CMGC). Additionally, we constructed three classifiers to predict pSADPr sites from the pS dataset, the SADPr dataset and the protein sequences separately. We built and evaluated five deep-learning classifiers in ten-fold cross-validation and independent test datasets. We also used the classifiers as base classifiers to develop a few stacking-based ensemble classifiers to improve performance. The best classifiers had the AUC values of 0.700, 0.914 and 0.954 for recognizing pSADPr sites from the SADPr, pS and unmodified serine sites, respectively. The lowest prediction accuracy was achieved by separating pSADPr and SADPr sites, which is consistent with the observation that pSADPr's characteristics are more similar to those of SADPr than the rest. Finally, we developed an online tool for extensively predicting human pSADPr sites based on the CNN_OH classifier, dubbed EdeepSADPr. It is freely available through http://edeepsadpr.bioinfogo.org/. We expect our investigation will promote a comprehensive understanding of crosstalks.

COVID-DSNet: A novel deep convolutional neural network for detection of coronavirus (SARS-CoV-2) cases from CT and Chest X-Ray images

COVID-19 (SARS-CoV-2), which causes acute respiratory syndrome, is a contagious and deadly disease that has devastating effects on society and human life. COVID-19 can cause serious complications, especially in patients with pre-existing chronic health problems such as diabetes, hypertension, lung cancer, weakened immune systems, and the elderly. The most critical step in the fight against COVID-19 is the rapid diagnosis of infected patients. Computed Tomography (CT), chest X-ray (CXR), and RT-PCR diagnostic kits are frequently used to diagnose the disease. However, due to difficulties such as the inadequacy of RT-PCR test kits and false negative (FN) results in the early stages of the disease, the time-consuming examination of medical images obtained from CT and CXR imaging techniques by specialists/doctors, and the increasing workload on specialists, it is challenging to detect COVID-19. Therefore, researchers have suggested searching for new methods in COVID- 19 detection. In analysis studies with CT and CXR radiography images, it was determined that COVID-19-infected patients experienced abnormalities related to COVID-19. The anomalies observed here are the primary motivation for artificial intelligence researchers to develop COVID-19 detection applications with deep convolutional neural networks. Here, convolutional neural network-based deep learning algorithms from artificial intelligence technologies with high discrimination capabilities can be considered as an alternative approach in the disease detection process. This study proposes a deep convolutional neural network, COVID-DSNet, to diagnose typical pneumonia (bacterial, viral) and COVID-19 diseases from CT, CXR, hybrid CT + CXR images. In the multi-classification study with the CT dataset, 97.60 % accuracy and 97.60 % sensitivity values were obtained from the COVID-DSNet model, and 100 %, 96.30 %, and 96.58 % sensitivity values were obtained in the detection of typical, common pneumonia and COVID-19, respectively. The proposed model is an economical, practical deep learning network that data scientists can benefit from and develop. Although it is not a definitive solution in disease diagnosis, it may help experts as it produces successful results in detecting pneumonia and COVID-19.

Prediction of anti-inflammatory peptides by a sequence-based stacking ensemble model named AIPStack

Accurate and efficient identification of anti-inflammatory peptides (AIPs) is crucial for the treatment of inflammation. Here, we proposed a two-layer stacking ensemble model, AIPStack, to effectively predict AIPs. At first, we constructed a new dataset for model building and validation. Then, peptide sequences were represented by hybrid features, which were fused by two amino acid composition descriptors. Next, the stacking ensemble model was constructed by random forest and extremely randomized tree as the base-classifiers and logistic regression as the meta-classifier to receive the outputs from the base-classifiers. AIPStack achieved an AUC of 0.819, accuracy of 0.755, and MCC of 0.510 on the independent set 3, which were higher than other AIP predictors. Furthermore, the essential sequence features were highlighted by the Shapley Additive exPlanation (SHAP) method. It is anticipated that AIPStack could be used for AIP prediction in a high-throughput manner and facilitate the hypothesis-driven experimental design.

•

AIPStack model was developed for the prediction of anti-inflammatory peptides

•

The hybrid features were used to describe the peptide sequences

•

The proposed model AIPStack outperformed existing ones

•

SHAP was used to highlight the essential features required for AIP prediction

iACVP: markedly enhanced identification of anti-coronavirus peptides using a dataset-specific word2vec model

The COVID-19 pandemic caused several million deaths worldwide. Development of anti-coronavirus drugs is thus urgent. Unlike conventional non-peptide drugs, antiviral peptide drugs are highly specific, easy to synthesize and modify, and not highly susceptible to drug resistance. To reduce the time and expense involved in screening thousands of peptides and assaying their antiviral activity, computational predictors for identifying anti-coronavirus peptides (ACVPs) are needed. However, few experimentally verified ACVP samples are available, even though a relatively large number of antiviral peptides (AVPs) have been discovered. In this study, we attempted to predict ACVPs using an AVP dataset and a small collection of ACVPs. Using conventional features, a binary profile and a word-embedding word2vec (W2V), we systematically explored five different machine learning methods: Transformer, Convolutional Neural Network, bidirectional Long Short-Term Memory, Random Forest (RF) and Support Vector Machine. Via exhaustive searches, we found that the RF classifier with W2V consistently achieved better performance on different datasets. The two main controlling factors were: (i) the dataset-specific W2V dictionary was generated from the training and independent test datasets instead of the widely used general UniProt proteome and (ii) a systematic search was conducted and determined the optimal k-mer value in W2V, which provides greater discrimination between positive and negative samples. Therefore, our proposed method, named iACVP, consistently provides better prediction performance compared with existing state-of-the-art methods. To assist experimentalists in identifying putative ACVPs, we implemented our model as a web server accessible via the following link: http://kurata35.bio.kyutech.ac.jp/iACVP.

SAPPHIRE: A stacking-based ensemble learning framework for accurate prediction of thermophilic proteins

Thermophilic proteins (TPPs) are important in the field of protein biochemistry and development of new enzymes. Thus, computational methods must be urgently developed to accurately and rapidly identify TPPs. To date, several computational methods have been developed for TPP identification; however, few limitations in terms of performance and utility remain. In this study, we present a novel computational method, SAPPHIRE, to achieve more accurate identification of TPPs using only sequence information without any need for structural information. We combined twelve different feature encodings representing different perspectives and six popular machine learning algorithms to train 72 baseline models and extract the key information of TPPs. Subsequently, the informative predicted probabilities from the baseline models were mined and selected using a genetic algorithm in conjunction with a self-assessment-report approach. Finally, the final meta-predictor, SAPPHIRE, was built and optimized by applying an optimal feature set. The performance of SAPPHIRE in the 10-fold cross-validation test showed that a superior predictive performance compared with several baseline models could be achieved. Moreover, SAPPHIRE yielded an accuracy of 0.942 and Matthew's coefficient correlation of 0.884, which were 7.68 and 5.12% higher than those of the current existing methods, respectively, as indicated by the independent test. The proposed computational approach is anticipated to facilitate large-scale identification of TPPs and accelerate their applications in the food industry. The codes and datasets are available at https://github.com/plenoi/SAPPHIRE.

A Machine Learning Classification Model for Gold-Binding Peptides

There has been growing interest in using peptides for the controlled synthesis of nanomaterials. Peptides play a crucial role not only in regulating the nanostructure formation process but also in influencing the resulting properties of the nanomaterials. Leveraging machine learning (ML) in the biomimetic workflow is anticipated to accelerate peptide discovery, make the process more resource-efficient, and unravel associations among attributes that may be useful in peptide design. In this study, a binary ML classifier is formulated that was trained and tested on 1720 peptide examples. The support vector machine classifier uses Kidera factors to categorize peptides into one of two groups based on their binding ability. The classifier exhibits satisfactory performance, as demonstrated by various performance metrics. In addition, key variables that bear a huge impact on the model were identified, such as peptide hydrophobicity. As these trends were derived from a large and diverse dataset, the insights drawn from the data are expected to be generalizable and robust. Thus, the presented ML model is an important step toward the rational and predictive peptide design.