An aged immune system drives senescence and ageing of solid organs.

Ageing of the immune system, or immunosenescence, contributes to the morbidity and mortality of the elderly1,2. To define the contribution of immune system ageing to organism ageing, here we selectively deleted Ercc1, which encodes a crucial DNA repair protein3,4, in mouse haematopoietic cells to increase the burden of endogenous DNA damage and thereby senescence5-7 in the immune system only. We show that Vav-iCre+/-;Ercc1-/fl mice were healthy into adulthood, then displayed premature onset of immunosenescence characterized by attrition and senescence of specific immune cell populations and impaired immune function, similar to changes that occur during ageing in wild-type mice8-10. Notably, non-lymphoid organs also showed increased senescence and damage, which suggests that senescent, aged immune cells can promote systemic ageing. The transplantation of splenocytes from Vav-iCre+/-;Ercc1-/fl or aged wild-type mice into young mice induced senescence in trans, whereas the transplantation of young immune cells attenuated senescence. The treatment of Vav-iCre+/-;Ercc1-/fl mice with rapamycin reduced markers of senescence in immune cells and improved immune function11,12. These data demonstrate that an aged, senescent immune system has a causal role in driving systemic ageing and therefore represents a key therapeutic target to extend healthy ageing.

A positively tuned voltage indicator for extended electrical recordings in the brain.

Genetically encoded voltage indicators (GEVIs) enable optical recording of electrical signals in the brain, providing subthreshold sensitivity and temporal resolution not possible with calcium indicators. However, one- and two-photon voltage imaging over prolonged periods with the same GEVI has not yet been demonstrated. Here, we report engineering of ASAP family GEVIs to enhance photostability by inversion of the fluorescence-voltage relationship. Two of the resulting GEVIs, ASAP4b and ASAP4e, respond to 100-mV depolarizations with ≥180% fluorescence increases, compared with the 50% fluorescence decrease of the parental ASAP3. With standard microscopy equipment, ASAP4e enables single-trial detection of spikes in mice over the course of minutes. Unlike GEVIs previously used for one-photon voltage recordings, ASAP4b and ASAP4e also perform well under two-photon illumination. By imaging voltage and calcium simultaneously, we show that ASAP4b and ASAP4e can identify place cells and detect voltage spikes with better temporal resolution than commonly used calcium indicators. Thus, ASAP4b and ASAP4e extend the capabilities of voltage imaging to standard one- and two-photon microscopes while improving the duration of voltage recordings.

CELA-MFP: a contrast-enhanced and label-adaptive framework for multi-functional therapeutic peptides prediction.

Functional peptides play crucial roles in various biological processes and hold significant potential in many fields such as drug discovery and biotechnology. Accurately predicting the functions of peptides is essential for understanding their diverse effects and designing peptide-based therapeutics. Here, we propose CELA-MFP, a deep learning framework that incorporates feature Contrastive Enhancement and Label Adaptation for predicting Multi-Functional therapeutic Peptides. CELA-MFP utilizes a protein language model (pLM) to extract features from peptide sequences, which are then fed into a Transformer decoder for function prediction, effectively modeling correlations between different functions. To enhance the representation of each peptide sequence, contrastive learning is employed during training. Experimental results demonstrate that CELA-MFP outperforms state-of-the-art methods on most evaluation metrics for two widely used datasets, MFBP and MFTP. The interpretability of CELA-MFP is demonstrated by visualizing attention patterns in pLM and Transformer decoder. Finally, a user-friendly online server for predicting multi-functional peptides is established as the implementation of the proposed CELA-MFP and can be freely accessed at http://dreamai.cmii.online/CELA-MFP.

ReHoGCNES-MDA: prediction of miRNA-disease associations using homogenous graph convolutional networks based on regular graph with random edge sampler.

Numerous investigations increasingly indicate the significance of microRNA (miRNA) in human diseases. Hence, unearthing associations between miRNA and diseases can contribute to precise diagnosis and efficacious remediation of medical conditions. The detection of miRNA-disease linkages via computational techniques utilizing biological information has emerged as a cost-effective and highly efficient approach. Here, we introduced a computational framework named ReHoGCNES, designed for prospective miRNA-disease association prediction (ReHoGCNES-MDA). This method constructs homogenous graph convolutional network with regular graph structure (ReHoGCN) encompassing disease similarity network, miRNA similarity network and known MDA network and then was tested on four experimental tasks. A random edge sampler strategy was utilized to expedite processes and diminish training complexity. Experimental results demonstrate that the proposed ReHoGCNES-MDA method outperforms both homogenous graph convolutional network and heterogeneous graph convolutional network with non-regular graph structure in all four tasks, which implicitly reveals steadily degree distribution of a graph does play an important role in enhancement of model performance. Besides, ReHoGCNES-MDA is superior to several machine learning algorithms and state-of-the-art methods on the MDA prediction. Furthermore, three case studies were conducted to further demonstrate the predictive ability of ReHoGCNES. Consequently, 93.3% (breast neoplasms), 90% (prostate neoplasms) and 93.3% (prostate neoplasms) of the top 30 forecasted miRNAs were validated by public databases. Hence, ReHoGCNES-MDA might serve as a dependable and beneficial model for predicting possible MDAs.

Mutant ß1-adrenergic receptor improves REM sleep and ameliorates tau accumulation in a mouse model of tauopathy.

Sleep is essential for our well-being, and chronic sleep deprivation has unfavorable health consequences. We recently demonstrated that two familial natural short sleep (FNSS) mutations, DEC2-P384R and Npsr1-Y206H, are strong genetic modifiers of tauopathy in PS19 mice, a model of tauopathy. To gain more insight into how FNSS variants modify the tau phenotype, we tested the effect of another FNSS gene variant, Adrb1-A187V, by crossing mice with this mutation onto the PS19 background. We found that the Adrb1-A187V mutation helped restore rapid eye movement (REM) sleep and alleviated tau aggregation in a sleep-wake center, the locus coeruleus (LC), in PS19 mice. We found that ADRB1+ neurons in the central amygdala (CeA) sent projections to the LC, and stimulating CeAADRB1+ neuron activity increased REM sleep. Furthermore, the mutant Adrb1 attenuated tau spreading from the CeA to the LC. Our findings suggest that the Adrb1-A187V mutation protects against tauopathy by both mitigating tau accumulation and attenuating tau spreading.

AFP-MFL: accurate identification of antifungal peptides using multi-view feature learning.

Recently, peptide-based drugs have gained unprecedented interest in discovering and developing antifungal drugs due to their high efficacy, broad-spectrum activity, low toxicity and few side effects. However, it is time-consuming and expensive to identify antifungal peptides (AFPs) experimentally. Therefore, computational methods for accurately predicting AFPs are highly required. In this work, we develop AFP-MFL, a novel deep learning model that predicts AFPs only relying on peptide sequences without using any structural information. AFP-MFL first constructs comprehensive feature profiles of AFPs, including contextual semantic information derived from a pre-trained protein language model, evolutionary information, and physicochemical properties. Subsequently, the co-attention mechanism is utilized to integrate contextual semantic information with evolutionary information and physicochemical properties separately. Extensive experiments show that AFP-MFL outperforms state-of-the-art models on four independent test datasets. Furthermore, the SHAP method is employed to explore each feature contribution to the AFPs prediction. Finally, a user-friendly web server of the proposed AFP-MFL is developed and freely accessible at http://inner.wei-group.net/AFPMFL/, which can be considered as a powerful tool for the rapid screening and identification of novel AFPs.

Subtype-DCC: decoupled contrastive clustering method for cancer subtype identification based on multi-omics data.

Due to the high heterogeneity and complexity of cancers, patients with different cancer subtypes often have distinct groups of genomic and clinical characteristics. Therefore, the discovery and identification of cancer subtypes are crucial to cancer diagnosis, prognosis and treatment. Recent technological advances have accelerated the increasing availability of multi-omics data for cancer subtyping. To take advantage of the complementary information from multi-omics data, it is necessary to develop computational models that can represent and integrate different layers of data into a single framework. Here, we propose a decoupled contrastive clustering method (Subtype-DCC) based on multi-omics data integration for clustering to identify cancer subtypes. The idea of contrastive learning is introduced into deep clustering based on deep neural networks to learn clustering-friendly representations. Experimental results demonstrate the superior performance of the proposed Subtype-DCC model in identifying cancer subtypes over the currently available state-of-the-art clustering methods. The strength of Subtype-DCC is also supported by the survival and clinical analysis.

Maize RNA 3'-terminal phosphate cyclase-like protein promotes 18S pre-rRNA cleavage and is important for kernel development.

Plant ribosomes contain four specialized ribonucleic acids, the 5S, 5.8S, 18S, and 25S ribosomal RNAs (rRNAs). Maturation of the latter three rRNAs requires cooperative processing of a single transcript by several endonucleases and exonucleases at specific sites. In maize (Zea mays), the exact nucleases and components required for rRNA processing remain poorly understood. Here, we characterized a conserved RNA 3'-terminal phosphate cyclase (RCL)-like protein, RCL1, that functions in 18S rRNA maturation. RCL1 is highly expressed in the embryo and endosperm during early seed development. Loss of RCL1 function resulted in lethality due to aborted embryo cell differentiation. We also observed pleiotropic defects in the rcl1 endosperm, including abnormal basal transfer cell layer growth and aleurone cell identity, and reduced storage reserve accumulation. The rcl1 seeds had lower levels of mature 18S rRNA and the related precursors were altered in abundance compared with wild type. Analysis of transcript levels and protein accumulation in rcl1 revealed that the observed lower levels of zein and starch synthesis enzymes mainly resulted from effects at the transcriptional and translational levels, respectively. These results demonstrate that RCL1-mediated 18S pre-rRNA processing is essential for ribosome function and messenger RNA translation during maize seed development.

STGIC: A graph and image convolution-based method for spatial transcriptomic clustering.

Spatial transcriptomic (ST) clustering employs spatial and transcription information to group spots spatially coherent and transcriptionally similar together into the same spatial domain. Graph convolution network (GCN) and graph attention network (GAT), fed with spatial coordinates derived adjacency and transcription profile derived feature matrix are often used to solve the problem. Our proposed method STGIC (spatial transcriptomic clustering with graph and image convolution) is designed for techniques with regular lattices on chips. It utilizes an adaptive graph convolution (AGC) to get high quality pseudo-labels and then resorts to dilated convolution framework (DCF) for virtual image converted from gene expression information and spatial coordinates of spots. The dilation rates and kernel sizes are set appropriately and updating of weight values in the kernels is made to be subject to the spatial distance from the position of corresponding elements to kernel centers so that feature extraction of each spot is better guided by spatial distance to neighbor spots. Self-supervision realized by Kullback-Leibler (KL) divergence, spatial continuity loss and cross entropy calculated among spots with high confidence pseudo-labels make up the training objective of DCF. STGIC attains state-of-the-art (SOTA) clustering performance on the benchmark dataset of 10x Visium human dorsolateral prefrontal cortex (DLPFC). Besides, it's capable of depicting fine structures of other tissues from other species as well as guiding the identification of marker genes. Also, STGIC is expandable to Stereo-seq data with high spatial resolution.

Tuning the Flat Band in Bi2O2Se by Pressure to Induce Superconductivity.

The discovery of superconductivity in twisted bilayer graphene has reignited enthusiasm in the field of flat-band superconductivity. However, important challenges remain, such as constructing a flat-band structure and inducing a superconducting state in materials. Here, we successfully achieved superconductivity in Bi2O2Se by pressure-tuning the flat-band electronic structure. Experimental measurements combined with theoretical calculations reveal that the occurrence of pressure-induced superconductivity at 30 GPa is associated with a flat-band electronic structure near the Fermi level. Moreover, in Bi2O2Se, a van Hove singularity is observed at the Fermi level alongside pronounced Fermi surface nesting. These remarkable features play a crucial role in promoting strong electron-phonon interactions, thus potentially enhancing the superconducting properties of the material. These findings demonstrate that pressure offers a potential experimental strategy for precisely tuning the flat band and achieving superconductivity.

SVPath: an accurate pipeline for predicting the pathogenicity of human exon structural variants.

Although there are a large number of structural variations in the chromosomes of each individual, there is a lack of more accurate methods for identifying clinical pathogenic variants. Here, we proposed SVPath, a machine learning-based method to predict the pathogenicity of deletions, insertions and duplications structural variations that occur in exons. We constructed three types of annotation features for each structural variation event in the ClinVar database. First, we treated complex structural variations as multiple consecutive single nucleotide polymorphisms events, and annotated them with correlation scores based on single nucleic acid substitutions, such as the impact on protein function. Second, we determined which genes the variation occurred in, and constructed gene-based annotation features for each structural variation. Third, we also calculated related features based on the transcriptome, such as histone signal, the overlap ratio of variation and genomic element definitions, etc. Finally, we employed a gradient boosting decision tree machine learning method, and used the deletions, insertions and duplications in the ClinVar database to train a structural variation pathogenicity prediction model SVPath. These structural variations are clearly indicated as pathogenic or benign. Experimental results show that our SVPath has achieved excellent predictive performance and outperforms existing state-of-the-art tools. SVPath is very promising in evaluating the clinical pathogenicity of structural variants. SVPath can be used in clinical research to predict the clinical significance of unknown pathogenicity and new structural variation, so as to explore the relationship between diseases and structural variations in a computational way.

Identifying the kind behind SMILES-anatomical therapeutic chemical classification using structure-only representations.

Anatomical Therapeutic Chemical (ATC) classification for compounds/drugs plays an important role in drug development and basic research. However, previous methods depend on interactions extracted from STITCH dataset which may make it depend on lab experiments. We present a pilot study to explore the possibility of conducting the ATC prediction solely based on the molecular structures. The motivation is to eliminate the reliance on the costly lab experiments so that the characteristics of a drug can be pre-assessed for better decision-making and effort-saving before the actual development. To this end, we construct a new benchmark consisting of 4545 compounds which is with larger scale than the one used in previous study. A light-weight prediction model is proposed. The model is with better explainability in the sense that it is consists of a straightforward tokenization that extracts and embeds statistically and physicochemically meaningful tokens, and a deep network backed by a set of pyramid kernels to capture multi-resolution chemical structural characteristics. Its efficacy has been validated in the experiments where it outperforms the state-of-the-art methods by 15.53% in accuracy and by 69.66% in terms of efficiency. We make the benchmark dataset, source code and web server open to ease the reproduction of this study.

MDF-SA-DDI: predicting drug-drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism.

One of the main problems with the joint use of multiple drugs is that it may cause adverse drug interactions and side effects that damage the body. Therefore, it is important to predict potential drug interactions. However, most of the available prediction methods can only predict whether two drugs interact or not, whereas few methods can predict interaction events between two drugs. Accurately predicting interaction events of two drugs is more useful for researchers to study the mechanism of the interaction of two drugs. In the present study, we propose a novel method, MDF-SA-DDI, which predicts drug-drug interaction (DDI) events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism. MDF-SA-DDI is mainly composed of two parts: multi-source drug fusion and multi-source feature fusion. First, we combine two drugs in four different ways and input the combined drug feature representation into four different drug fusion networks (Siamese network, convolutional neural network and two auto-encoders) to obtain the latent feature vectors of the drug pairs, in which the two auto-encoders have the same structure, and their main difference is the number of neurons in the input layer of the two auto-encoders. Then, we use transformer blocks that include self-attention mechanism to perform latent feature fusion. We conducted experiments on three different tasks with two datasets. On the small dataset, the area under the precision-recall-curve (AUPR) and F1 scores of our method on task 1 reached 0.9737 and 0.8878, respectively, which were better than the state-of-the-art method. On the large dataset, the AUPR and F1 scores of our method on task 1 reached 0.9773 and 0.9117, respectively. In task 2 and task 3 of two datasets, our method also achieved the same or better performance as the state-of-the-art method. More importantly, the case studies on five DDI events are conducted and achieved satisfactory performance. The source codes and data are available at https://github.com/ShenggengLin/MDF-SA-DDI.

DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model.

MOTIVATION: Identifying the functional sites of a protein, such as the binding sites of proteins, peptides, or other biological components, is crucial for understanding related biological processes and drug design. However, existing sequence-based methods have limited predictive accuracy, as they only consider sequence-adjacent contextual features and lack structural information. RESULTS: In this study, DeepProSite is presented as a new framework for identifying protein binding site that utilizes protein structure and sequence information. DeepProSite first generates protein structures from ESMFold and sequence representations from pretrained language models. It then uses Graph Transformer and formulates binding site predictions as graph node classifications. In predicting protein-protein/peptide binding sites, DeepProSite outperforms state-of-the-art sequence- and structure-based methods on most metrics. Moreover, DeepProSite maintains its performance when predicting unbound structures, in contrast to competing structure-based prediction methods. DeepProSite is also extended to the prediction of binding sites for nucleic acids and other ligands, verifying its generalization capability. Finally, an online server for predicting multiple types of residue is established as the implementation of the proposed DeepProSite. AVAILABILITY AND IMPLEMENTATION: The datasets and source codes can be accessed at https://github.com/WeiLab-Biology/DeepProSite. The proposed DeepProSite can be accessed at https://inner.wei-group.net/DeepProSite/.

Epinecidin-1 and lactic acid synergistically inhibit Aeromonas hydrophila through membrane disruption.

Epinecidin-1 (Epi-1) is an antimicrobial peptide originated from fish with various pharmacological activities but carries the risk of acquiring resistance with long-term use. In the present study, we use L-lactic acid to enhance the antibacterial activity of synthesized Epi-1 against the aquaculture and food pathogen Aeromonas hydrophila. The results showed that 5.5 mmol/L lactic acid increased the inhibitory and bactericidal activity of 25 µmol/L Epi-1 against two strains of A. hydrophila. The laser confocal images proved that lactic acid pre-treatment improved the attachment efficiency of Epi-1 in A.hydrophila cells. In addition, lactic acid enhanced the damaging effect of Epi-1 on the cell membrane of A. hydrophila, evidenced by releasing more nucleic acids, proteins, and transmembrane pH ingredients decrease and electromotive force dissipation. SEM images showed that compared with the single Epi-1 treatment, the co-treatment of Epi-1 and lactic acid caused more outer membrane vesicles (OMVs) and more severe cell deformation. These findings proved that lactic acid could enhance the efficiency of Epi-1 against A. hydrophila and shed light on new aspects to avoid resistance of pathogens against Epi-1.

Structural vaccinology, molecular simulation and immune simulation approaches to design multi-epitopes vaccine against John Cunningham virus.

The JCV (John Cunningham Virus) is known to cause progressive multifocal leukoencephalopathy, a condition that results in the formation of tumors. Symptoms of this condition such as sensory defects, cognitive dysfunction, muscle weakness, homonosapobia, difficulties with coordination, and aphasia. To date, there is no specific and effective treatment to completely cure or prevent John Cunningham polyomavirus infections. Since the best way to control the disease is vaccination. In this study, the immunoinformatic tools were used to predict the high immunogenic and non-allergenic B cells, helper T cells (HTL), and cytotoxic T cells (CTL) epitopes from capsid, major capsid, and T antigen proteins of JC virus to design the highly efficient subunit vaccines. The specific immunogenic linkers were used to link together the predicted epitopes and subjected to 3D modeling by using the Robetta server. MD simulation was used to confirm that the newly constructed vaccines are stable and properly fold. Additionally, the molecular docking approach revealed that the vaccines have a strong binding affinity with human TLR-7. The codon adaptation index (CAI) and GC content values verified that the constructed vaccines would be highly expressed in E. coli pET28a (+) plasmid. The immune simulation analysis indicated that the human immune system would have a strong response to the vaccines, with a high titer of IgM and IgG antibodies being produced. In conclusion, this study will provide a pre-clinical concept to construct an effective, highly antigenic, non-allergenic, and thermostable vaccine to combat the infection of the John Cunningham virus.

Development and validation of a preoperative CT­based radiomics nomogram to differentiate tuberculosis granulomas from lung adenocarcinomas: an external validation study.

BACKGROUND: An accurate and non-invasive approach is urgently needed to distinguish tuberculosis granulomas from lung adenocarcinomas. This study aimed to develop and validate a nomogram based on contrast enhanced-compute tomography (CE-CT) to preoperatively differentiate tuberculosis granuloma from lung adenocarcinoma appearing as solitary pulmonary solid nodules (SPSN). METHODS: This retrospective study analyzed 143 patients with lung adenocarcinoma (mean age: 62.4 ± 6.5 years; 54.5% female) and 137 patients with tuberculosis granulomas (mean age: 54.7 ± 8.2 years; 29.2% female) from two centers between March 2015 and June 2020. The training and internal validation cohorts included 161 and 69 patients (7:3 ratio) from center No.1, respectively. The external testing cohort included 50 patients from center No.2. Clinical factors and conventional radiological characteristics were analyzed to build independent predictors. Radiomics features were extracted from each CT-volume of interest (VOI). Feature selection was performed using univariate and multivariate logistic regression analysis, as well as the least absolute shrinkage and selection operator (LASSO) method. A clinical model was constructed with clinical factors and radiological findings. Individualized radiomics nomograms incorporating clinical data and radiomics signature were established to validate the clinical usefulness. The diagnostic performance was assessed using the receiver operating characteristic (ROC) curve analysis with the area under the receiver operating characteristic curve (AUC). RESULTS: One clinical factor (CA125), one radiological characteristic (enhanced-CT value) and nine radiomics features were found to be independent predictors, which were used to establish the radiomics nomogram. The nomogram demonstrated better diagnostic efficacy than any single model, with respective AUC, accuracy, sensitivity, and specificity of 0.903, 0.857, 0.901, and 0.807 in the training cohort; 0.933, 0.884, 0.893, and 0.892 in the internal validation cohort; 0.914, 0.800, 0.937, and 0.735 in the external test cohort. The calibration curve showed a good agreement between prediction probability and actual clinical findings. CONCLUSION: The nomogram incorporating clinical factors, radiological characteristics and radiomics signature provides additional value in distinguishing tuberculosis granuloma from lung adenocarcinoma in patients with a SPSN, potentially serving as a robust diagnostic strategy in clinical practice.

Synthesis of 2,3-Dialkyl-5-hydroxybenzofurans via a One-pot, Three-step Reaction Sequence of 2-Monosubstituted 1,3-Diketones and 1,4-Benzoquinones.

An economical one-pot, three-step reaction sequence of readily available 2-monosubstituted 1,3-diketones and 1,4-benzoquinones has been explored for the facile access of 2,3-dialkyl-5-hydroxybenzofurans. By using cheap K2CO3 and conc. HCl as the reaction promoters, the reaction occurs smoothly via sequential Michael addition, aromatization, retro-Claisen, deacylation, hemiketalization, and dehydration processes under mild conditions in a practical manner. Additionally, an interesting phenomenon was observed during the derivatization studies, where the dihydroquinoline was converted into tetrahydroquinoline and quinoline products, respectively, via a disproportionation process.

DDSBC: A Stacking Ensemble Classifier-Based Approach for Breast Cancer Drug-Pair Cell Synergy Prediction.

Breast cancer (BC) ranks as a leading cause of mortality among women worldwide, with incidence rates continuing to rise. The quest for effective treatments has led to the adoption of drug combination therapy, aiming to enhance drug efficacy. However, identifying synergistic drug combinations remains a daunting challenge due to the myriad of potential drug pairs. Current research leverages machine learning (ML) and deep learning (DL) models for drug-pair synergy prediction and classification. Nevertheless, these models often underperform on specific cancer types, including BC, as they are trained on data spanning various cancers without any specialization. Here, we introduce a stacking ensemble classifier, the drug-drug synergy for breast cancer (DDSBC), tailored explicitly for BC drug-pair cell synergy classification. Unlike existing models that generalize across cancer types, DDSBC is exclusively developed for BC, offering a more focused approach. Our comparative analysis against classical ML methods as well as DL models developed for drug synergy prediction highlights DDSBC's superior performance across test and independent datasets on BC data. Despite certain metrics where other methods narrowly surpass DDSBC by 1-2%, DDSBC consistently emerges as the top-ranked model, showcasing significant differences in scoring metrics and robust performance in ablation studies. DDSBC's performance and practicality position it as a preferred choice or an adjunctive validation tool for identifying synergistic or antagonistic drug pairs in BC, providing valuable insights for treatment strategies.

MATT-DDI: Predicting multi-type drug-drug interactions via heterogeneous attention mechanisms.

The joint use of multiple drugs can result in adverse drug-drug interactions (DDIs) and side effects that harm the body. Accurate identification of DDIs is crucial for avoiding accidental drug side effects and understanding potential mechanisms underlying DDIs. Several computational methods have been proposed for multi-type DDI prediction, but most rely on the similarity profiles of drugs as the drug feature vectors, which may result in information leakage and overoptimistic performance when predicting interactions between new drugs. To address this issue, we propose a novel method, MATT-DDI, for predicting multi-type DDIs based on the original feature vectors of drugs and multiple attention mechanisms. MATT-DDI consists of three main modules: the top k most similar drug pair selection module, heterogeneous attention mechanism module and multi­type DDI prediction module. Firstly, based on the feature vector of the input drug pair (IDP), k drug pairs that are most similar to the input drug pair from the training dataset are selected according to cosine similarity between drug pairs. Then, the vectors of k selected drug pairs are averaged to obtain a new drug pair (NDP). Next, IDP and NDP are fed into heterogeneous attention modules, including scaled dot product attention and bilinear attention, to extract latent feature vectors. Finally, these latent feature vectors are taken as input of the classification module to predict DDI types. We evaluated MATT-DDI on three different tasks. The experimental results show that MATT-DDI provides better or comparable performance compared to several state-of-the-art methods, and its feasibility is supported by case studies. MATT-DDI is a robust model for predicting multi-type DDIs with excellent performance and no information leakage.