An ensemble deep learning model for predicting minimum inhibitory concentrations of antimicrobial peptides against pathogenic bacteria.

The rise of antibiotic resistance necessitates effective alternative therapies. Antimicrobial peptides (AMPs) are promising due to their broad inhibitory effects. This study focuses on predicting the minimum inhibitory concentration (MIC) of AMPs against whom-priority pathogens: Staphylococcus aureus ATCC 25923, Escherichia coli ATCC 25922, and Pseudomonas aeruginosa ATCC 27853. We developed a comprehensive regression model integrating AMP sequence-based and genomic features. Using eight AI-based architectures, including deep learning with protein language model embeddings, we created an ensemble model combining bi-directional long short-term memory (BiLSTM), convolutional neural network (CNN), and multi-branch model (MBM). The ensemble model showed superior performance with Pearson correlation coefficients of 0.756, 0.781, and 0.802 for the bacterial strains, demonstrating its accuracy in predicting MIC values. This work sets a foundation for future studies to enhance model performance and advance AMP applications in combating antibiotic resistance.

ACP-CapsPred: an explainable computational framework for identification and functional prediction of anticancer peptides based on capsule network.

Cancer is a severe illness that significantly threatens human life and health. Anticancer peptides (ACPs) represent a promising therapeutic strategy for combating cancer. In silico methods enable rapid and accurate identification of ACPs without extensive human and material resources. This study proposes a two-stage computational framework called ACP-CapsPred, which can accurately identify ACPs and characterize their functional activities across different cancer types. ACP-CapsPred integrates a protein language model with evolutionary information and physicochemical properties of peptides, constructing a comprehensive profile of peptides. ACP-CapsPred employs a next-generation neural network, specifically capsule networks, to construct predictive models. Experimental results demonstrate that ACP-CapsPred exhibits satisfactory predictive capabilities in both stages, reaching state-of-the-art performance. In the first stage, ACP-CapsPred achieves accuracies of 80.25% and 95.71%, as well as F1-scores of 79.86% and 95.90%, on benchmark datasets Set 1 and Set 2, respectively. In the second stage, tasked with characterizing the functional activities of ACPs across five selected cancer types, ACP-CapsPred attains an average accuracy of 90.75% and an F1-score of 91.38%. Furthermore, ACP-CapsPred demonstrates excellent interpretability, revealing regions and residues associated with anticancer activity. Consequently, ACP-CapsPred presents a promising solution to expedite the development of ACPs and offers a novel perspective for other biological sequence analyses.

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.

Multi-Omics Characterization of E3 Regulatory Patterns in Different Cancer Types.

Ubiquitination, a post-translational modification, refers to the covalent attachment of ubiquitin molecules to substrates. This modification plays a critical role in diverse cellular processes such as protein degradation. The specificity of ubiquitination for substrates is regulated by E3 ubiquitin ligases. Dysregulation of ubiquitination has been associated with numerous diseases, including cancers. In our study, we first investigated the protein expression patterns of E3 ligases across 12 cancer types. Our findings indicated that E3 ligases tend to be up-regulated and exhibit reduced tissue specificity in tumors. Moreover, the correlation of protein expression between E3 ligases and substrates demonstrated significant changes in cancers, suggesting that E3-substrate specificity alters in tumors compared to normal tissues. By integrating transcriptome, proteome, and ubiquitylome data, we further characterized the E3-substrate regulatory patterns in lung squamous cell carcinoma. Our analysis revealed that the upregulation of the SKP2 E3 ligase leads to excessive degradation of BRCA2, potentially promoting tumor cell proliferation and metastasis. Furthermore, the upregulation of E3 ubiquitin-protein ligase TRIM33 was identified as a biomarker associated with a favorable prognosis by inhibiting the cell cycle. This work exemplifies how leveraging multi-omics data to analyze E3 ligases across various cancers can unveil prognosis biomarkers and facilitate the identification of potential drug targets for cancer therapy.

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/.

Recent insights into breast milk microRNA: their role as functional regulators.

Breast milk (BM) is a primary biofluid that plays a crucial role in infant development and the regulation of the immune system. As a class of rich biomolecules in BM, microRNAs (miRNAs) are regarded as active factors contributing to infant growth and development. Surprisingly, these molecules exhibit resilience in harsh conditions, providing an opportunity for infants to absorb them. In addition, many studies have shown that miRNAs in breast milk, when absorbed into the gastrointestinal system, can act as a class of functional regulators to effectively regulate gene expression. Understanding the absorption pattern of BM miRNA may facilitate the creation of formula with a more optimal miRNA balance and pave the way for novel drug delivery techniques. In this review, we initially present evidence of BM miRNA absorption. Subsequently, we compile studies that integrate both in vivo and in vitro findings to illustrate the bioavailability and biodistribution of BM miRNAs post-absorption. In addition, we evaluate the strengths and weaknesses of previous studies and discuss potential variables contributing to discrepancies in their outcomes. This literature review indicates that miRNAs can be absorbed and act as regulatory agents.

AMPActiPred: A three-stage framework for predicting antibacterial peptides and activity levels with deep forest.

The emergence and spread of antibiotic-resistant bacteria pose a significant public health threat, necessitating the exploration of alternative antibacterial strategies. Antibacterial peptide (ABP) is a kind of antimicrobial peptide (AMP) that has the potential ability to fight against bacteria infection, offering a promising avenue for developing novel therapeutic interventions. This study introduces AMPActiPred, a three-stage computational framework designed to identify ABPs, characterize their activity against diverse bacterial species, and predict their activity levels. AMPActiPred employed multiple effective peptide descriptors to effectively capture the compositional features and physicochemical properties of peptides. AMPActiPred utilized deep forest architecture, a cascading architecture similar to deep neural networks, capable of effectively processing and exploring original features to enhance predictive performance. In the first stage, AMPActiPred focuses on ABP identification, achieving an Accuracy of 87.6% and an MCC of 0.742 on an elaborate dataset, demonstrating state-of-the-art performance. In the second stage, AMPActiPred achieved an average GMean at 82.8% in identifying ABPs targeting 10 bacterial species, indicating AMPActiPred can achieve balanced predictions regarding the functional activity of ABP across this set of species. In the third stage, AMPActiPred demonstrates robust predictive capabilities for ABP activity levels with an average PCC of 0.722. Furthermore, AMPActiPred exhibits excellent interpretability, elucidating crucial features associated with antibacterial activity. AMPActiPred is the first computational framework capable of predicting targets and activity levels of ABPs. Finally, to facilitate the utilization of AMPActiPred, we have established a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼AMPActiPred/.

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.

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.

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 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 by which 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, 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.

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.

KinPred-RNA-kinase activity inference and cancer type classification using machine learning on RNA-seq data.

Kinases as important enzymes can transfer phosphate groups from high-energy and phosphate-donating molecules to specific substrates and play essential roles in various cellular processes. Existing algorithms for kinase activity from phosphorylated proteomics data are often costly, requiring valuable samples. Moreover, methods to extract kinase activities from bulk RNA sequencing data remain undeveloped. In this study, we propose a computational framework KinPred-RNA to derive kinase activities from bulk RNA-sequencing data in cancer samples. KinPred-RNA framework, using the extreme gradient boosting (XGBoost) regression model, outperforms random forest regression, multiple linear regression, and support vector machine regression models in predicting kinase activities from cancer-related RNA sequencing data. Efficient gene signatures from the LINCS-L1000 dataset were used as inputs for KinPred-RNA. The results highlight its potential to be related to biological function. In conclusion, KinPred RNA constitutes a significant advance in cancer research by potentially facilitating the identification of cancer.

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).

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.

Predicting Anti-inflammatory Peptides by Ensemble Machine Learning and Deep Learning.

Inflammation is a biological response to harmful stimuli, aiding in the maintenance of tissue homeostasis. However, excessive or persistent inflammation can precipitate a myriad of pathological conditions. Although current treatments such as NSAIDs, corticosteroids, and immunosuppressants are effective, they can have side effects and resistance issues. In this backdrop, anti-inflammatory peptides (AIPs) have emerged as a promising therapeutic approach against inflammation. Leveraging machine learning methods, we have the opportunity to accelerate the discovery and investigation of these AIPs more effectively. In this study, we proposed an advanced framework by ensemble machine learning and deep learning for AIP prediction. Initially, we constructed three individual models with extremely randomized trees (ET), gated recurrent unit (GRU), and convolutional neural networks (CNNs) with attention mechanism and then used stacking architecture to build the final predictor. By utilizing various sequence encodings and combining the strengths of different algorithms, our predictor demonstrated exemplary performance. On our independent test set, our model achieved an accuracy, MCC, and F1-score of 0.757, 0.500, and 0.707, respectively, clearly outperforming other contemporary AIP prediction methods. Additionally, our model offers profound insights into the feature interpretation of AIPs, establishing a valuable knowledge foundation for the design and development of future anti-inflammatory strategies.

Assessing Non-Specific Neck Pain through Pose Estimation from Images Based on Ensemble Learning.

BACKGROUND: Mobile phones, laptops, and computers have become an indispensable part of our lives in recent years. Workers may have an incorrect posture when using a computer for a prolonged period of time. Using these products with an incorrect posture can lead to neck pain. However, there are limited data on postures in real-life situations. METHODS: In this study, we used a common camera to record images of subjects carrying out three different tasks (a typing task, a gaming task, and a video-watching task) on a computer. Different artificial intelligence (AI)-based pose estimation approaches were applied to analyze the head's yaw, pitch, and roll and coordinate information of the eyes, nose, neck, and shoulders in the images. We used machine learning models such as random forest, XGBoost, logistic regression, and ensemble learning to build a model to predict whether a subject had neck pain by analyzing their posture when using the computer. RESULTS: After feature selection and adjustment of the predictive models, nested cross-validation was applied to evaluate the models and fine-tune the hyperparameters. Finally, the ensemble learning approach was utilized to construct a model via bagging, which achieved a performance with 87% accuracy, 92% precision, 80.3% recall, 95.5% specificity, and an AUROC of 0.878. CONCLUSIONS: We developed a predictive model for the identification of non-specific neck pain using 2D video images without the need for costly devices, advanced environment settings, or extra sensors. This method could provide an effective way for clinically evaluating poor posture during real-world computer usage scenarios.

Multi-label classification and features investigation of antimicrobial peptides with various functional classes.

The challenge of drug-resistant bacteria to global public health has led to increased attention on antimicrobial peptides (AMPs) as a targeted therapeutic alternative with a lower risk of resistance. However, high production costs and limitations in functional class prediction have hindered progress in this field. In this study, we used multi-label classifiers with binary relevance and algorithm adaptation techniques to predict different functions of AMPs across a wide range of pathogen categories, including bacteria, mammalian cells, fungi, viruses, and cancer cells. Our classifiers attained promising AUC scores varying from 0.8492 to 0.9126 on independent testing data. Forward feature selection identified sequence order and charge as critical, with specific amino acids (C and E) as discriminative. These findings provide valuable insights for the design of antimicrobial peptides (AMPs) with multiple functionalities, thus contributing to the broader effort to combat drug-resistant pathogens.

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.

A Robust Drug-Target Interaction Prediction Framework with Capsule Network and Transfer Learning.

Drug-target interactions (DTIs) are considered a crucial component of drug design and drug discovery. To date, many computational methods were developed for drug-target interactions, but they are insufficiently informative for accurately predicting DTIs due to the lack of experimentally verified negative datasets, inaccurate molecular feature representation, and ineffective DTI classifiers. Therefore, we address the limitations of randomly selecting negative DTI data from unknown drug-target pairs by establishing two experimentally validated datasets and propose a capsule network-based framework called CapBM-DTI to capture hierarchical relationships of drugs and targets, which adopts pre-trained bidirectional encoder representations from transformers (BERT) for contextual sequence feature extraction from target proteins through transfer learning and the message-passing neural network (MPNN) for the 2-D graph feature extraction of compounds to accurately and robustly identify drug-target interactions. We compared the performance of CapBM-DTI with state-of-the-art methods using four experimentally validated DTI datasets of different sizes, including human (Homo sapiens) and worm (Caenorhabditis elegans) species datasets, as well as three subsets (new compounds, new proteins, and new pairs). Our results demonstrate that the proposed model achieved robust performance and powerful generalization ability in all experiments. The case study on treating COVID-19 demonstrates the applicability of the model in virtual screening.