Guided diffusion for molecular generation with interaction prompt.

Molecular generative models have exhibited promising capabilities in designing molecules from scratch with high binding affinities in a predetermined protein pocket, offering potential synergies with traditional structural-based drug design strategy. However, the generative processes of such models are random and the atomic interaction information between ligand and protein are ignored. On the other hand, the ligand has high propensity to bind with residues called hotspots. Hotspot residues contribute to the majority of the binding free energies and have been recognized as appealing targets for designed molecules. In this work, we develop an interaction prompt guided diffusion model, InterDiff to deal with the challenges. Four kinds of atomic interactions are involved in our model and represented as learnable vector embeddings. These embeddings serve as conditions for individual residue to guide the molecular generative process. Comprehensive in silico experiments evince that our model could generate molecules with desired ligand-protein interactions in a guidable way. Furthermore, we validate InterDiff on two realistic protein-based therapeutic agents. Results show that InterDiff could generate molecules with better or similar binding mode compared to known targeted drugs.

A two-stage computational framework for identifying antiviral peptides and their functional types based on contrastive learning and multi-feature fusion strategy.

Antiviral peptides (AVPs) have shown potential in inhibiting viral attachment, preventing viral fusion with host cells and disrupting viral replication due to their unique action mechanisms. They have now become a broad-spectrum, promising antiviral therapy. However, identifying effective AVPs is traditionally slow and costly. This study proposed a new two-stage computational framework for AVP identification. The first stage identifies AVPs from a wide range of peptides, and the second stage recognizes AVPs targeting specific families or viruses. This method integrates contrastive learning and multi-feature fusion strategy, focusing on sequence information and peptide characteristics, significantly enhancing predictive ability and interpretability. The evaluation results of the model show excellent performance, with accuracy of 0.9240 and Matthews correlation coefficient (MCC) score of 0.8482 on the non-AVP independent dataset, and accuracy of 0.9934 and MCC score of 0.9869 on the non-AMP independent dataset. Furthermore, our model can predict antiviral activities of AVPs against six key viral families (Coronaviridae, Retroviridae, Herpesviridae, Paramyxoviridae, Orthomyxoviridae, Flaviviridae) and eight viruses (FIV, HCV, HIV, HPIV3, HSV1, INFVA, RSV, SARS-CoV). Finally, to facilitate user accessibility, we built a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼dbAMP/AVP/.

PlantPAN 4.0: updated database for identifying conserved non-coding sequences and exploring dynamic transcriptional regulation in plant promoters.

PlantPAN 4.0 (http://PlantPAN.itps.ncku.edu.tw/) is an integrative resource for constructing transcriptional regulatory networks for diverse plant species. In this release, the gene annotation and promoter sequences were expanded to cover 115 species. PlantPAN 4.0 can help users characterize the evolutionary differences and similarities among cis-regulatory elements; furthermore, this system can now help in identification of conserved non-coding sequences among homologous genes. The updated transcription factor binding site repository contains 3428 nonredundant matrices for 18305 transcription factors; this expansion helps in exploration of combinational and nucleotide variants of cis-regulatory elements in conserved non-coding sequences. Additionally, the genomic landscapes of regulatory factors were manually updated, and ChIP-seq data sets derived from a single-cell green alga (Chlamydomonas reinhardtii) were added. Furthermore, the statistical review and graphical analysis components were improved to offer intelligible information through ChIP-seq data analysis. These improvements included easy-to-read experimental condition clusters, searchable gene-centered interfaces for the identification of promoter regions' binding preferences by considering experimental condition clusters and peak visualization for all regulatory factors, and the 20 most significantly enriched gene ontology functions for regulatory factors. Thus, PlantPAN 4.0 can effectively reconstruct gene regulatory networks and help compare genomic cis-regulatory elements across plant species and experiments.

BRCC3 Regulation of ALK2 in Vascular Smooth Muscle Cells: Implication in Pulmonary Hypertension.

BACKGROUND: An imbalance of antiproliferative BMP (bone morphogenetic protein) signaling and proliferative TGF-ß (transforming growth factor-ß) signaling is implicated in the development of pulmonary arterial hypertension (PAH). The posttranslational modification (eg, phosphorylation and ubiquitination) of TGF-ß family receptors, including BMPR2 (bone morphogenetic protein type 2 receptor)/ALK2 (activin receptor-like kinase-2) and TGF-ßR2/R1, and receptor-regulated (R) Smads significantly affects their activity and thus regulates the target cell fate. BRCC3 modifies the activity and stability of its substrate proteins through K63-dependent deubiquitination. By modulating the posttranslational modifications of the BMP/TGF-ß-PPARγ pathway, BRCC3 may play a role in pulmonary vascular remodeling, hence the pathogenesis of PAH. METHODS: Bioinformatic analyses were used to explore the mechanism of BRCC3 deubiquitinates ALK2. Cultured pulmonary artery smooth muscle cells (PASMCs), mouse models, and specimens from patients with idiopathic PAH were used to investigate the rebalance between BMP and TGF-ß signaling in regulating ALK2 phosphorylation and ubiquitination in the context of pulmonary hypertension. RESULTS: BRCC3 was significantly downregulated in PASMCs from patients with PAH and animals with experimental pulmonary hypertension. BRCC3, by de-ubiquitinating ALK2 at Lys-472 and Lys-475, activated receptor-regulated Smad1/5/9 (Smad1/5/9), which resulted in transcriptional activation of BMP-regulated PPARγ, p53, and Id1. Overexpression of BRCC3 also attenuated TGF-ß signaling by downregulating TGF-ß expression and inhibiting phosphorylation of Smad3. Experiments in vitro indicated that overexpression of BRCC3 or the de-ubiquitin-mimetic ALK2-K472/475R attenuated PASMC proliferation and migration and enhanced PASMC apoptosis. In SM22α-BRCC3-Tg mice, pulmonary hypertension was ameliorated because of activation of the ALK2-Smad1/5-PPARγ axis in PASMCs. In contrast, Brcc3-/- mice showed increased susceptibility of experimental pulmonary hypertension because of inhibition of the ALK2-Smad1/5 signaling. CONCLUSIONS: These results suggest a pivotal role of BRCC3 in sustaining pulmonary vascular homeostasis by maintaining the integrity of the BMP signaling (ie, the ALK2-Smad1/5-PPARγ axis) while suppressing TGF-ß signaling in PASMCs. Such rebalance of BMP/TGF-ß pathways is translationally important for PAH alleviation.

Holistic similarity-based prediction of phosphorylation sites for understudied kinases.

Phosphorylation is an essential mechanism for regulating protein activities. Determining kinase-specific phosphorylation sites by experiments involves time-consuming and expensive analyzes. Although several studies proposed computational methods to model kinase-specific phosphorylation sites, they typically required abundant experimentally verified phosphorylation sites to yield reliable predictions. Nevertheless, the number of experimentally verified phosphorylation sites for most kinases is relatively small, and the targeting phosphorylation sites are still unidentified for some kinases. In fact, there is little research related to these understudied kinases in the literature. Thus, this study aims to create predictive models for these understudied kinases. A kinase-kinase similarity network was generated by merging the sequence-, functional-, protein-domain- and 'STRING'-related similarities. Thus, besides sequence data, protein-protein interactions and functional pathways were also considered to aid predictive modelling. This similarity network was then integrated with a classification of kinase groups to yield highly similar kinases to a specific understudied type of kinase. Their experimentally verified phosphorylation sites were leveraged as positive sites to train predictive models. The experimentally verified phosphorylation sites of the understudied kinase were used for validation. Results demonstrate that 82 out of 116 understudied kinases were predicted with adequate performance via the proposed modelling strategy, achieving a balanced accuracy of 0.81, 0.78, 0.84, 0.84, 0.85, 0.82, 0.90, 0.82 and 0.85, for the 'TK', 'Other', 'STE', 'CAMK', 'TKL', 'CMGC', 'AGC', 'CK1' and 'Atypical' groups, respectively. Therefore, this study demonstrates that web-like predictive networks can reliably capture the underlying patterns in such understudied kinases by harnessing relevant sources of similarities to predict their specific phosphorylation sites.

Identification of species-specific RNA N6-methyladinosine modification sites from RNA sequences.

N6-methyladinosine (m6A) modification is the most abundant co-transcriptional modification in eukaryotic RNA and plays important roles in cellular regulation. Traditional high-throughput sequencing experiments used to explore functional mechanisms are time-consuming and labor-intensive, and most of the proposed methods focused on limited species types. To further understand the relevant biological mechanisms among different species with the same RNA modification, it is necessary to develop a computational scheme that can be applied to different species. To achieve this, we proposed an attention-based deep learning method, adaptive-m6A, which consists of convolutional neural network, bi-directional long short-term memory and an attention mechanism, to identify m6A sites in multiple species. In addition, three conventional machine learning (ML) methods, including support vector machine, random forest and logistic regression classifiers, were considered in this work. In addition to the performance of ML methods for multi-species prediction, the optimal performance of adaptive-m6A yielded an accuracy of 0.9832 and the area under the receiver operating characteristic curve of 0.98. Moreover, the motif analysis and cross-validation among different species were conducted to test the robustness of one model towards multiple species, which helped improve our understanding about the sequence characteristics and biological functions of RNA modifications in different species.

Extraction of microRNA-target interaction sentences from biomedical literature by deep learning approach.

MicroRNA (miRNA)-target interaction (MTI) plays a substantial role in various cell activities, molecular regulations and physiological processes. Published biomedical literature is the carrier of high-confidence MTI knowledge. However, digging out this knowledge in an efficient manner from large-scale published articles remains challenging. To address this issue, we were motivated to construct a deep learning-based model. We applied the pre-trained language models to biomedical text to obtain the representation, and subsequently fed them into a deep neural network with gate mechanism layers and a fully connected layer for the extraction of MTI information sentences. Performances of the proposed models were evaluated using two datasets constructed on the basis of text data obtained from miRTarBase. The validation and test results revealed that incorporating both PubMedBERT and SciBERT for sentence level encoding with the long short-term memory (LSTM)-based deep neural network can yield an outstanding performance, with both F1 and accuracy being higher than 80% on validation data and test data. Additionally, the proposed deep learning method outperformed the following machine learning methods: random forest, support vector machine, logistic regression and bidirectional LSTM. This work would greatly facilitate studies on MTI analysis and regulations. It is anticipated that this work can assist in large-scale screening of miRNAs, thereby revealing their functional roles in various diseases, which is important for the development of highly specific drugs with fewer side effects. Source code and corpus are publicly available at https://github.com/qi29.

A risk assessment framework for multidrug-resistant Staphylococcus aureus using machine learning and mass spectrometry technology.

The emergence of multidrug-resistant bacteria is a critical global crisis that poses a serious threat to public health, particularly with the rise of multidrug-resistant Staphylococcus aureus. Accurate assessment of drug resistance is essential for appropriate treatment and prevention of transmission of these deadly pathogens. Early detection of drug resistance in patients is critical for providing timely treatment and reducing the spread of multidrug-resistant bacteria. This study aims to develop a novel risk assessment framework for S. aureus that can accurately determine the resistance to multiple antibiotics. The comprehensive 7-year study involved ˃20 000 isolates with susceptibility testing profiles of six antibiotics. By incorporating mass spectrometry and machine learning, the study was able to predict the susceptibility to four different antibiotics with high accuracy. To validate the accuracy of our models, we externally tested on an independent cohort and achieved impressive results with an area under the receiver operating characteristic curve of 0. 94, 0.90, 0.86 and 0.91, and an area under the precision-recall curve of 0.93, 0.87, 0.87 and 0.81, respectively, for oxacillin, clindamycin, erythromycin and trimethoprim-sulfamethoxazole. In addition, the framework evaluated the level of multidrug resistance of the isolates by using the predicted drug resistance probabilities, interpreting them in the context of a multidrug resistance risk score and analyzing the performance contribution of different sample groups. The results of this study provide an efficient method for early antibiotic decision-making and a better understanding of the multidrug resistance risk of S. aureus.

Identifying Antitubercular Peptides via Deep Forest Architecture with Effective Feature Representation.

Tuberculosis (TB) is a severe disease caused by Mycobacterium tuberculosis that poses a significant threat to human health. The emergence of drug-resistant strains has made the global fight against TB even more challenging. Antituberculosis peptides (ATPs) have shown promising results as a potential treatment for TB. However, conventional wet lab-based approaches to ATP discovery are time-consuming and costly and often fail to discover peptides with desired properties. To address these challenges, we propose a novel machine learning-based framework called ATPfinder that can significantly accelerate the discovery of ATP. Our approach integrates various efficient peptide descriptors and utilizes the deep forest algorithm to construct the model. This neural network-like cascading structure can effectively process and mine features without complex hyperparameter tuning. Our experimental results show that ATPfinder outperforms existing ATP prediction tools, achieving state-of-the-art performance with an accuracy of 89.3% and an MCC of 0.70. Moreover, our framework exhibits better robustness than baseline algorithms commonly used for other sequence analysis tasks. Additionally, the excellent interpretability of our model can assist researchers in understanding the critical features of ATP. Finally, we developed a downloadable desktop application to simplify the use of our framework for researchers. Therefore, ATPfinder can facilitate the discovery of peptide drugs and provide potential solutions for TB treatment. Our framework is freely available at https://github.com/lantianyao/ATPfinder/ (data sets and code) and https://awi.cuhk.edu.cn/dbAMP/ATPfinder.html (software).

CapsEnhancer: An Effective Computational Framework for Identifying Enhancers Based on Chaos Game Representation and Capsule Network.

Enhancers are a class of noncoding DNA, serving as crucial regulatory elements in governing gene expression by binding to transcription factors. The identification of enhancers holds paramount importance in the field of biology. However, traditional experimental methods for enhancer identification demand substantial human and material resources. Consequently, there is a growing interest in employing computational methods for enhancer prediction. In this study, we propose a two-stage framework based on deep learning, termed CapsEnhancer, for the identification of enhancers and their strengths. CapsEnhancer utilizes chaos game representation to encode DNA sequences into unique images and employs a capsule network to extract local and global features from sequence "images". Experimental results demonstrate that CapsEnhancer achieves state-of-the-art performance in both stages. In the first and second stages, the accuracy surpasses the previous best methods by 8 and 3.5%, reaching accuracies of 94.5 and 95%, respectively. Notably, this study represents the pioneering application of computer vision methods to enhancer identification tasks. Our work not only contributes novel insights to enhancer identification but also provides a fresh perspective for other biological sequence analysis tasks.

CircNet 2.0: an updated database for exploring circular RNA regulatory networks in cancers.

Circular RNAs (circRNAs), which are single-stranded RNA molecules that have individually formed into a covalently closed continuous loop, act as sponges of microRNAs to regulate transcription and translation. CircRNAs are important molecules in the field of cancer diagnosis, as growing evidence suggests that they are closely related to pathological cancer features. Therefore, they have high potential for clinical use as novel cancer biomarkers. In this article, we present our updates to CircNet (version 2.0), into which circRNAs from circAtlas and MiOncoCirc, and novel circRNAs from The Cancer Genome Atlas database have been integrated. In total, 2732 samples from 37 types of cancers were integrated into CircNet 2.0 and analyzed using several of the most reliable circRNA detection algorithms. Furthermore, target miRNAs were predicted from the full-length circRNA sequence using three reliable tools (PITA, miRanda and TargetScan). Additionally, 384 897 experimentally verified miRNA-target interactions from miRTarBase were integrated into our database to facilitate the construction of high-quality circRNA-miRNA-gene regulatory networks. These improvements, along with the user-friendly interactive web interface for data presentation, search, and visualization, showcase the updated CircNet database as a powerful, experimentally validated resource, for providing strong data support in the biomedical fields. CircNet 2.0 is currently accessible at https://awi.cuhk.edu.cn/∼CircNet.

dbAMP 2.0: updated resource for antimicrobial peptides with an enhanced scanning method for genomic and proteomic data.

The last 18 months, or more, have seen a profound shift in our global experience, with many of us navigating a once-in-100-year pandemic. To date, COVID-19 remains a life-threatening pandemic with little to no targeted therapeutic recourse. The discovery of novel antiviral agents, such as vaccines and drugs, can provide therapeutic solutions to save human beings from severe infections; however, there is no specifically effective antiviral treatment confirmed for now. Thus, great attention has been paid to the use of natural or artificial antimicrobial peptides (AMPs) as these compounds are widely regarded as promising solutions for the treatment of harmful microorganisms. Given the biological significance of AMPs, it was obvious that there was a significant need for a single platform for identifying and engaging with AMP data. This led to the creation of the dbAMP platform that provides comprehensive information about AMPs and facilitates their investigation and analysis. To date, the dbAMP has accumulated 26 447 AMPs and 2262 antimicrobial proteins from 3044 organisms using both database integration and manual curation of >4579 articles. In addition, dbAMP facilitates the evaluation of AMP structures using I-TASSER for automated protein structure prediction and structure-based functional annotation, providing predictive structure information for clinical drug development. Next-generation sequencing (NGS) and third-generation sequencing have been applied to generate large-scale sequencing reads from various environments, enabling greatly improved analysis of genome structure. In this update, we launch an efficient online tool that can effectively identify AMPs from genome/metagenome and proteome data of all species in a short period. In conclusion, these improvements promote the dbAMP as one of the most abundant and comprehensively annotated resources for AMPs. The updated dbAMP is now freely accessible at http://awi.cuhk.edu.cn/dbAMP.

dbPTM in 2022: an updated database for exploring regulatory networks and functional associations of protein post-translational modifications.

Protein post-translational modifications (PTMs) play an important role in different cellular processes. In view of the importance of PTMs in cellular functions and the massive data accumulated by the rapid development of mass spectrometry (MS)-based proteomics, this paper presents an update of dbPTM with over 2 777 000 PTM substrate sites obtained from existing databases and manual curation of literature, of which more than 2 235 000 entries are experimentally verified. This update has manually curated over 42 new modification types that were not included in the previous version. Due to the increasing number of studies on the mechanism of PTMs in the past few years, a great deal of upstream regulatory proteins of PTM substrate sites have been revealed. The updated dbPTM thus collates regulatory information from databases and literature, and merges them into a protein-protein interaction network. To enhance the understanding of the association between PTMs and molecular functions/cellular processes, the functional annotations of PTMs are curated and integrated into the database. In addition, the existing PTM-related resources, including annotation databases and prediction tools are also renewed. Overall, in this update, we would like to provide users with the most abundant data and comprehensive annotations on PTMs of proteins. The updated dbPTM is now freely accessible at https://awi.cuhk.edu.cn/dbPTM/.

miRTarBase update 2022: an informative resource for experimentally validated miRNA-target interactions.

MicroRNAs (miRNAs) are noncoding RNAs with 18-26 nucleotides; they pair with target mRNAs to regulate gene expression and produce significant changes in various physiological and pathological processes. In recent years, the interaction between miRNAs and their target genes has become one of the mainstream directions for drug development. As a large-scale biological database that mainly provides miRNA-target interactions (MTIs) verified by biological experiments, miRTarBase has undergone five revisions and enhancements. The database has accumulated >2 200 449 verified MTIs from 13 389 manually curated articles and CLIP-seq data. An optimized scoring system is adopted to enhance this update's critical recognition of MTI-related articles and corresponding disease information. In addition, single-nucleotide polymorphisms and disease-related variants related to the binding efficiency of miRNA and target were characterized in miRNAs and gene 3' untranslated regions. miRNA expression profiles across extracellular vesicles, blood and different tissues, including exosomal miRNAs and tissue-specific miRNAs, were integrated to explore miRNA functions and biomarkers. For the user interface, we have classified attributes, including RNA expression, specific interaction, protein expression and biological function, for various validation experiments related to the role of miRNA. We also used seed sequence information to evaluate the binding sites of miRNA. In summary, these enhancements render miRTarBase as one of the most research-amicable MTI databases that contain comprehensive and experimentally verified annotations. The newly updated version of miRTarBase is now available at https://miRTarBase.cuhk.edu.cn/.

Roles of KLF4 and AMPK in the inhibition of glycolysis by pulsatile shear stress in endothelial cells.

Vascular endothelial cells (ECs) sense and respond to hemodynamic forces such as pulsatile shear stress (PS) and oscillatory shear stress (OS). Among the metabolic pathways, glycolysis is differentially regulated by atheroprone OS and atheroprotective PS. Studying the molecular mechanisms by which PS suppresses glycolytic flux at the epigenetic, transcriptomic, and kinomic levels, we have demonstrated that glucokinase regulatory protein (GCKR) was markedly induced by PS in vitro and in vivo, although PS down-regulates other glycolysis enzymes such as hexokinase (HK1). Using next-generation sequencing data, we identified the binding of PS-induced Krüppel-like factor 4 (KLF4), which functions as a pioneer transcription factor, binding to the GCKR promoter to change the chromatin structure for transactivation of GCKR. At the posttranslational level, PS-activated AMP-activated protein kinase (AMPK) phosphorylates GCKR at Ser-481, thereby enhancing the interaction between GCKR and HK1 in ECs. In vivo, the level of phosphorylated GCKR Ser-481 and the interaction between GCKR and HK1 were increased in the thoracic aorta of wild-type AMPKα2+/+ mice in comparison with littermates with EC ablation of AMPKα2 (AMPKα2-/-). In addition, the level of GCKR was elevated in the aortas of mice with a high level of voluntary wheel running. The underlying mechanisms for the PS induction of GCKR involve regulation at the epigenetic level by KLF4 and at the posttranslational level by AMPK.

Interpretable Multi-Scale Deep Learning for RNA Methylation Analysis across Multiple Species.

RNA modification plays a crucial role in cellular regulation. However, traditional high-throughput sequencing methods for elucidating their functional mechanisms are time-consuming and labor-intensive, despite extensive research. Moreover, existing methods often limit their focus to specific species, neglecting the simultaneous exploration of RNA modifications across diverse species. Therefore, a versatile computational approach is necessary for interpretable analysis of RNA modifications across species. A multi-scale biological language-based deep learning model is proposed for interpretable, sequential-level prediction of diverse RNA modifications. Benchmark comparisons across species demonstrate the model's superiority in predicting various RNA methylation types over current state-of-the-art methods. The cross-species validation and attention weight visualization also highlight the model's capability to capture sequential and functional semantics from genomic backgrounds. Our analysis of RNA modifications helps us find the potential existence of "biological grammars" in each modification type, which could be effective for mapping methylation-related sequential patterns and understanding the underlying biological mechanisms of RNA modifications.

Machine Learning-Based Characterization and Identification of Tertiary Lymphoid Structures Using Spatial Transcriptomics Data.

Tertiary lymphoid structures (TLSs) are organized aggregates of immune cells in non-lymphoid tissues and are associated with a favorable prognosis in tumors. However, TLS markers remain inconsistent, and the utilization of machine learning techniques for this purpose is limited. To tackle this challenge, we began by identifying TLS markers through bioinformatics analysis and machine learning techniques. Subsequently, we leveraged spatial transcriptomic data from Gene Expression Omnibus (GEO) and built two support vector classifier models for TLS prediction: one without feature selection and the other using the marker genes. The comparable performances of these two models confirm the efficacy of the selected markers. The majority of the markers are immunoglobulin genes, demonstrating their importance in the identification of TLSs. Our research has identified the markers of TLSs using machine learning methods and constructed a model to predict TLS location, contributing to the detection of TLS and holding the promising potential to impact cancer treatment strategies.

The impact of Lacticaseibacillus paracasei GMNL-143 toothpaste on gingivitis and oral microbiota in adults: a randomized, double-blind, crossover, placebo-controlled trial.

BACKGROUND: This study examines the oral health benefits of heat-killed Lacticaseibacillus paracasei GMNL-143, particularly its potential in oral microbiota alterations and gingivitis improvement. METHODS: We assessed GMNL-143's in vitro interactions with oral pathogens and its ability to prevent pathogen adherence to gingival cells. A randomized, double-blind, crossover clinical trial was performed on gingivitis patients using GMNL-143 toothpaste or placebo for four weeks, followed by a crossover after a washout. RESULTS: GMNL-143 showed coaggregation with oral pathogens in vitro, linked to its surface layer protein. In patients, GMNL-143 toothpaste lowered the gingival index and reduced Streptococcus mutans in crevicular fluid. A positive relationship was found between Aggregatibacter actinomycetemcomitans and gingival index changes, and a negative one between Campylobacter and gingival index changes in plaque. CONCLUSION: GMNL-143 toothpaste may shift oral bacterial composition towards a healthier state, suggesting its potential in managing mild to moderate gingivitis. TRIAL REGISTRATION: ID NCT04190485 ( https://clinicaltrials.gov/ ); 09/12/2019, retrospective registration.

Identifying anti-coronavirus peptides by incorporating different negative datasets and imbalanced learning strategies.

As the current worldwide outbreaks of the SARS-CoV-2, it is urgently needed to develop effective therapeutic agents for inhibiting the pathogens or treating the related diseases. Antimicrobial peptides (AMP) with functional activity against coronavirus could be a considerable solution, yet there is no research for identifying anti-coronavirus (anti-CoV) peptides with the computational approach. In this study, we first investigated the physiochemical and compositional properties of the collected anti-CoV peptides by comparing against three other negative sets: antivirus peptides without anti-CoV function (antivirus), regular AMP without antivirus functions (non-AVP) and peptides without antimicrobial functions (non-AMP). Then, we established classifiers for identifying anti-CoV peptides between different negative sets based on random forest. Imbalanced learning strategies were adopted due to the severe class-imbalance within the datasets. The geometric mean of the sensitivity and specificity (GMean) under the identification from antivirus, non-AVP and non-AMP reaches 83.07%, 85.51% and 98.82%, respectively. Then, to pursue identifying anti-CoV peptides from broad-spectrum peptides, we designed a double-stages classifier based on the collected datasets. In the first stage, the classifier characterizes AMPs from regular peptides. It achieves an area under the receiver operating curve (AUCROC) value of 97.31%. The second stage is to identify the anti-CoV peptides between the combined negatives of other AMPs. Here, the GMean of evaluation on the independent test set is 79.42%. The proposed approach is considered as an applicable scheme for assisting the development of novel anti-CoV peptides. The datasets and source codes used in this study are available at https://github.com/poncey/PreAntiCoV.

AVPIden: a new scheme for identification and functional prediction of antiviral peptides based on machine learning approaches.

Antiviral peptide (AVP) is a kind of antimicrobial peptide (AMP) that has the potential ability to fight against virus infection. Machine learning-based prediction with a computational biology approach can facilitate the development of the novel therapeutic agents. In this study, we proposed a double-stage classification scheme, named AVPIden, for predicting the AVPs and their functional activities against different viruses. The first stage is to distinguish the AVP from a broad-spectrum peptide collection, including not only the regular peptides (non-AMP) but also the AMPs without antiviral functions (non-AVP). The second stage is responsible for characterizing one or more virus families or species that the AVP targets. Imbalanced learning is utilized to improve the performance of prediction. The AVPIden uses multiple descriptors to precisely demonstrate the peptide properties and adopts explainable machine learning strategies based on Shapley value to exploit how the descriptors impact the antiviral activities. Finally, the evaluation performance of the proposed model suggests its ability to predict the antivirus activities and their potential functions against six virus families (Coronaviridae, Retroviridae, Herpesviridae, Paramyxoviridae, Orthomyxoviridae, Flaviviridae) and eight kinds of virus (FIV, HCV, HIV, HPIV3, HSV1, INFVA, RSV, SARS-CoV). The AVPIden gives an option for reinforcing the development of AVPs with the computer-aided method and has been deployed at http://awi.cuhk.edu.cn/AVPIden/.