Accurate prediction of protein-protein interaction sites is crucial to understanding biological processes, elucidating disease mechanisms, and accelerating drug discovery. Although graph neural network methods have shown potential in this field, but existing methods are limited by the static integrate multi-group features and insufficient perception of hierarchical 3D spatial geometric information, leading to insufficient predictive ability of orphan sites. To address these issues, this paper proposes a Dperception mechanism within a Hierarchical E(n)-equivariant Graph architecture (DHEG). DHEG introduces a dynamic feature importance perception mechanism that adaptively perceives the contextual inter-dependencies of features and assigns weights to feature groups based on their relevance to the interaction relationship. And a hierarchical gated architecture based on E(n)-equivariant graph neural networks that effectively captures protein 3D spatial structures while mitigating over-smoothing problems. The results show that DHEG achieves improvements in 11 of 13 key metrics, with an enhancement 8% in Matthews correlation coefficient, indicating that DHEG not only predicts more interaction sites but also does so with greater reliability. Furthermore, case studies and visualization analyzes show that DHEG aligns better with the biological mechanism and has excellent predictive capabilities for both orphan sites and continuous regions, demonstrating interpretability, and application potential.

Protein-protein interactions (PPIs) are fundamental to many biological processes, including cell signaling, gene expression regulation, immune responses, and protein complex formation. Small molecule inhibitors targeting specific PPIs are expected to treat diseases such as cancer and viral infections by modulating pathophysiological processes. Despite their clinical importance, the development of PPI inhibitors is challenging due to limited experimental validation data, which complicates the accurate prediction of novel inhibitors. Therefore, there is an urgent need for advanced computational methods that can effectively integrate multiple data types and improve prediction accuracy. In this study, we proposed a new framework, PTPPI, to efficiently predict protein-protein interaction inhibitors (PPIIs). PTPPI integrates multiple molecular features, including extended connectivity fingerprints (ECFPs) for structural representation and deep semantic embeddings of SMILES sequences generated by the ChemBERTa pre-trained model. These features are processed by independent encoders and fused using an interactive attention mechanism, which enhances the molecular representation. In addition, PTPPI adopts a multi-task learning approach, enabling the model to both reconstruct input features and accurately predict inhibition scores. Experimental results on eight PPI target families, focusing on inhibitor identification and potency prediction, demonstrate that PTPPI outperforms existing methods. It not only integrates multiple molecular features effectively but also achieves superior prediction performance. This makes PTPPI a valuable and reliable tool for discovering new PPI inhibitors, thus opening up new possibilities for drug discovery and disease treatment.

Accurate prediction of molecular properties is a fundamental component of Artificial Intelligence-driven Drug Design (AIDD). In molecular property prediction, even slight structural variations, such as atomic arrangement or bond length, could impact molecular properties. Existing methods primarily focus on coarse-grained molecular modeling on SMILES, 2D, or 3D graphs. However, this paradigm struggles to adequately capture complex internal molecular interactions and overlooks finer-grained structural details, such as atom-bond-spatial positions. In this paper, we propose a molecular property prediction model, TriPercept, based on unified fine-grained representation learning. Specifically, TriPercept integrates atomic, topological, and geometric features, fully exploiting their intrinsic complementarity. We introduce three dedicated encoders to separately learn features at the atomic, bond, and spatial distance levels, thus addressing the neglect of complex structural details. Additionally, we design a structure-aware graph neural network to integrate these features and enhance structural consistency modeling with a contrastive and self-supervised based pretraining strategy. To evaluate the performance of TriPercept, we conduct systematic experiments on six classification datasets and six regression datasets. The results demonstrate that TriPercept performs excellently on most datasets. Visualization experiments further verify that TriPercept not only confirms the effectiveness of multi-level structural integration but also clearly reveals its interpretability in focusing on chemically relevant features and capturing complex structural relationships. The data and code are available at https://github.com/TiAW-Go/TriPercept.

Drug-target interaction (DTI) prediction plays a crucial role in drug discovery and repositioning. However, existing computational methods often overlook the internal chemical structure of drugs, the structural context of proteins, and their dynamic conformational adaptability during binding. To address these limitations, we propose MoFA-DTI, a deep learning-based multimodal fusion model for accurate DTI prediction. Our approach employs a graph convolutional network (GCN) to extract molecular graph features and a bidirectional gated recurrent unit (BiGRU) to capture protein sequence dependencies. A modalityaware feature aggregation module integrates self-attention and cross-attention mechanisms to learn both intra-modal and intermodal representations. Positional encoding and convolutional layers further enhance protein feature refinement. Experimental results on multiple public datasets show that MoFA-DTI consistently outperforms existing methods.

Graph neural networks have demonstrated impressive performance in molecular representation learning. However, when dealing with out-of-distribution data, the generalization ability of existing models often drops significantly. To address this challenge, we have proposed an adversarial domain generalization framework aimed at achieving robust molecular characterization in heterogeneous environments. Specifically, we designed a multi-stage task that first discovers latent domain distributions through latent category-independent features, and then applies adversarial optimization to enhance class invariance and domain invariance respectively. In addition, we have introduced two types of adversarial balance strategies to reduce class domain correlation and stabilize adversarial training. Extensive experiments have shown that our model performs significantly better than the state-of-the-art baseline models. T-SNE visualization and paired H -divergence measurements further confirm that the learned feature space exhibits clear domain separability and domain distribution differences.

Seeking effective numerical approximations for partial differential equations (PDEs) is a major challenge in modern science and technology. Recently, AI-inspired data-driven solvers, such as neural operators, have achieved great success in quickly PDE solving. However, in the design of neural operators, the processing of frequency domain information is crucial, while the importance of low-frequency information is excessively overlooked. In order to reduce low-frequency error in PDE solving, we propose the multi scale spectral mixture neural operator (MSSMNO) architecture and design a residual learning structure that transfers residuals in multi-scale cycle by combining the frequency domain learning patterns of the FNO method. Meanwhile, we designed interpolation operator and restriction operator to effectively transmit and reconstruct high-frequency information in MSSMNO. Experimentally, MSSMNO achieves state-of-the-art and yields a relative error reduction of 21.9% averaged on four classical benchmarks.

Protein-protein interactions (PPIs) play a critical role in cellular functions, which are essential for maintaining the proper physiological state of organisms. Therefore, identifying PPI sites with high accuracy is crucial. Recently, graph neural networks (GNNs) have achieved significant progress in predicting PPI sites, but there is still potential for further enhancement. In this study, we introduce GTE-PPIS, an innovative PPI site predictor that utilizes two components: a graph transformer and an equivariant GNN, to collaboratively extract features. These extracted features are subsequently processed through a multilayer perceptron to generate the final predictions. Our experimental results show that GTE-PPIS consistently outperforms existing methods on multiple evaluation metrics across benchmark datasets, strongly supporting the effectiveness of our approach.

MOTIVATION: Predicting protein-protein interaction (PPI) sites is essential for advancing our understanding of protein interactions, as accurate predictions can significantly reduce experimental costs and time. While considerable progress has been made in identifying binding sites at the level of individual amino acid residues, the prediction accuracy for residue subsequences at transitional boundaries-such as those represented by patterns like singular structures (mutation characteristics of contiguous interacting-residue segments) or edge structures (boundary transitions between interacting/non-interacting residue segments) still requires improvement. RESULTS: we propose a novel PPI site prediction method named MVSO-PPIS. This method integrates two complementary feature extraction modules, a subgraph-based module and an enhanced graph attention module. The extracted features are fused using an attention-based fusion mechanism, producing a composite representation that captures both local protein substructures and global contextual dependencies. MVSO-PPIS is trained to jointly optimize three objectives: overall PPI site prediction accuracy, edge structural consistency, and recognition of unique structural patterns in PPI site sequences. Experimental results on benchmark datasets demonstrate that MVSO-PPIS outperforms existing baseline models in both accuracy and structural interpretability. AVAILABILITY AND IMPLEMENTATION: The datasets, source codes, and models of MVSO-PPIS are all available at https://github.com/Edwardblue282/MVSO-PPIS.

Accurate prediction of molecular properties is a key component of Artificial Intelligence-driven Drug Design (AIDD). Despite significant progress in improving these predictive models, balancing accuracy with computational complexity remains a challenge. Molecular topological and geometric features provide rich spatial information, crucial for improving prediction accuracy, but their extraction typically increases model complexity. To address this, we propose TGF-M (Topology-augmented Geometric Features for Molecular Property Prediction), a novel predictive model that optimizes feature extraction to enhance information capture and improve model accuracy, and reduces model complexity to lower computational cost. This approach enhances the model's ability to leverage both topological and geometric features without unnecessary complexity. On the re-segmented PCQM4Mv2 dataset, TGF-M performs remarkably, achieving a low mean absolute error (MAE) of 0.0647 in the HOMO-LUMO gap prediction task with only 6.4M parameters. Compared to two recent state-of-the-art models evaluated within a unified validation framework, TGF-M demonstrates comparable performance with less than one-tenth of the parameters. We conducted an in-depth analysis of TGF-M's chemical interpretability. The results further validate the method's effectiveness in leveraging complex molecular topology and geometry during model learning, underscoring its potential and advantages. The trained models and source code of TGF-M are publicly available at https://github.com/TiAW-Go/TGF-M.

Disease is one of the primary factors affecting life activities, with complex etiologies often influenced by gene expression and mutation. Currently, wet lab experiments have analyzed the mechanisms of mutations, but these are usually limited by the costs of wet experiments and constraints in sample types and scales. Therefore, this paper constructs a real-world mutation-induced disease dataset and proposes Capsule and Graph topology networks with Multi-head attention (CGM) to predict the mutation-disease associations. CGM can accurately predict protein mutation-disease associations, and to further elucidate the pathogenicity of protein mutations, we also verified that protein mutations lead to protein structural alterations by the model, which suggests that mutation-induced conformational changes may be an important pathogenic factor. Limited by the size of the mutated protein dataset, we also performed experiments on benchmark and imbalanced datasets, where CGM mined 22 unknown protein interaction pairs from the benchmark dataset, better illustrating the potential of CGM in predicting mutation-disease associations. In summary, this paper curates a real dataset. It proposes that CGM predicts protein mutations and disease associations, providing a novel tool for further understanding of biomolecular pathways and disease mechanisms.

Generating drug-like molecules that specifically bind to target proteins remains a resource-intensive challenge. Many studies focus on designing effective networks to accurately extract relevant features from target proteins, which can be challenging. Additionally, most target-specific molecule generation methods based on diffusion models process the 3D information of molecules and proteins, necessitating the maintenance of equivariance at each step. This paper proposes TarMGDif, a novel target-specific molecular graph generation model based on a discrete denoising diffusion framework which could handle graph structure. TarMGDif incorporates a global features embedding network that captures ring features to generate chemically valid rings, while the time step of the diffusion model is also learned through this network. Besides, a novel node-to-edge attention module is proposed to capture dependencies between nodes and edges. Extensive experiments conducted on three datasets demonstrate the advanced performance of TarMGDif. Furthermore, through transfer learning, the model generates molecules specifically targeting the DRD2 protein, with the newly designed molecules exhibiting pharmacological properties similar to known inhibitors. These findings underscore the potential of TarMGDif in facilitating the efficient design of target-specific drug-like molecules.

The traditional super-resolution dataset construction using artificial down-sampling techniques can result in information loss, insufficient diversity, and non-uniqueness. Furthermore, existing methods for image super-resolution are limited to single-modal images and cannot accommodate the complexities of multimodal images. This is problematic because diverse modal data requires individualized model design and training, which can hinder the exploitation of complementary relationships among multimodal data. In this article, we have addressed these issues by undertaking a two-step solution approach. In the first step, we constructed a super-resolution dataset that utilized remote-sensing images of tropical cyclones in “real cases.” This dataset comprises HR–LR image pairs originating from multiple sensors of varying satellite sources, resulting in multimodal data. However, the HR–LR image pairs suffer from an additional misalignment issue. Thus, in the second step, we designed a super-resolution network based on MAT to address the misalignment problem in multimodal environment. After numerous ablation experiments and comparison experiments, we have shown that our model is effective, with an improvement of 50% over the original baseline model, and an increase varying between 20% and 50% compared to other common super-resolution models. We have made our source code and data publicly available online at https://github.com/kleenY/MMTCSR .

Biomedical knowledge graph reasoning is capable of discovering hidden new knowledge based on existing biomedical data, providing ideas and references for new drug discovery, disease research, and so on. The entire graph topology structure formed by triplets and the attribute descriptions for each entity are crucial information for discovering new knowledge. Some add a variety of additional information to aid reasoning, namely multimodal reasoning. However, current multimodal reasoning techniques often rely solely on vector space distance inferences based on triplets themselves, making it difficult to capture more complex relationships and dependencies between facts. This work integrated triplet entity relations, graph topology structures, and attribute descriptions for each entity to incorporate richer information, and utilized logical rules as external knowledge for relational reasoning in biomedical knowledge graphs. We have evaluated our approach on PharmKG.

Retrosynthesis constructs rational synthetic pathways by predicting reactants from the target product. Previous research utilizing Graph Neural Networks often relies on two-dimensional molecular representations. The two-dimensional representations of functional groups of the same type are identical, and ignoring differences in their three-dimensional(3D) structures can cause confusion in identifying reaction centers. Additionally, they disconnect the reaction centers, hindering the accurate identification of chemical transformation rules. To address these issues, we propose the Retro3D model based on a semi-template-based method, integrating 3D structural information to enhance molecular representation. Due to the discrepancies in bond lengths and bond angles of the same type of functional groups in different 3D spatial structures, our method improves the accuracy of identifying reaction centers in the target product. Furthermore, our method determines whether reaction centers are disconnected, differentiating between types of reaction centers to obtain two types of chemical transformation rules. Given the known reaction class, experiments demonstrate that our model achieves superior accuracy in predicting reaction centers and final reactants compared to previous benchmark models. In summary, our methodology aligns with established chemical principles, enhancing its interpretability and broad applicability across diverse synthetic challenges.

The calculation of the drug-target affinity (DTA) is of paramount importance in drug discovery. Recently, there exist various deep learning methodologies geared towards extracting features from drug-target interactions to ascertain their mutual existence. The majority of these methods utilize sequences of targets and drugs as descriptors, potentially resulting in suboptimal performance in feature extraction by the networks. Recently, particularly with the Mamba, the Selective Structured State Space Model has demonstrated significant potential in modeling long-range dependencies with linear complexity. Inspired by the aforementioned, and to mitigate the high computational complexity faced by long biological sequences in deep learning, we propose a novel DTA prediction method named MambaDTA. Specifically, we design a novel drug sequence feature extraction module based on Mamba, which achieves knowledge extraction through the effective selection of feature information, enabling the model to extract more representative features from the data. Furthermore, we combine convolutional layers and Convolutional Block Attention Module (CBAM) to extract more important features from target sequences. We evaluate MambaDTA on three benchmarks and compare with state-of-the-art methods to ensure its performance and consistency. The results show that the proposed method demonstrate excellent performance, showcasing significant performance advantages over other state-of-the-art methods when handling DT sequence data. Last, we performed interpretability studies by incorporating a weighted attention mechanism into the network. By visualizing the interactions through attention weights, the results demonstrate that our model can provide valuable guidance for drug discovery.

Gene expression is a pivotal biological process within organisms, and in recent years, the prediction of gene expression levels has garnered increasing attention due to its vast potential in clinical applications. Predicting gene expression levels is a complex problem as gene expression is influenced by multiple factors, including but not limited to gene sequences, epigenetic modifications, transcription factor binding, and micro-environmental conditions. This paper proposes a model named Multimodal Expression, based on the Transformer architecture, which integrates various data types. The model can extract effective features from gene promoter sequences and combine pre-transcriptional and post-transcriptional regulatory information to predict gene expression levels. Experimental results demonstrate that our model can extract more effective information from promoter sequences, and the attention mechanism in the Transformer can integrate multiple data types to jointly predict gene expression levels. Compared to previous methods, our model’s R2values improved by 7.05%, 8.9%, and 1.91% when using gene sequence data alone, gene sequence data combined with mRNA half-life data, and gene sequence data combined with mRNA half-life data and transcription factor data, respectively.

Efficient and accurate identification of drug-target affinity (DTA) is crucial in the virtual screening stage of drug discovery and the reuse of existing drugs. Deep neural networks are becoming popular tools for providing fast and accurate binding affinity prediction. MGraphDTA is one of the best performing models for DTA prediction, utilizing a super-deep graph neural network to extract features, demonstrating good generalization and interpretation capabilities. However, the complex deep neural networks come with a higher computational cost of model inference. Meanwhile, due to the expansion of drug databases, rapid completion of large-scale virtual screening still presents challenges. In this work, we propose an efficient binding affinity prediction method called DCUI-MGraphDTA through a series of optimizations on MGraphDTA to achieve large-scale virtual screening for millions of molecules on the Deep Computing Unit (DCU) cluster. The optimized DCUI-MGraphDTA model achieves a speedup of approximately 5.83 times on a single DCU compared to the original MGraphDTA. As the number of DCUs expands from 1 to 32, the total time for the model to process 1.28 million data significantly decreases, achieving a speedup of approximately 11.9 times.

Depression is a prevalent global mental health issue that significantly impacts both individuals and societies. Current methods often overlook the heterogeneity of depressive symptoms and fail to fully leverage available data, underscoring the need for more advanced computational methods DTI prediction. This paper introduces KGM4DTI, a multi-semantic, multi-view, and multi-level meta-path Transformer framework that integrates Transformer and GNN. KGM4DTI effectively captures both global semantic and local structural information between interaction pairs within a depression knowledge graph (DepKG), which comprises 2,258 drugs, 3,360 proteins, 6 subtypes of depression, 196 phenotypes, and 238 pathways. Comparative experiments have demonstrated that KGM4DTI significantly outperforms existing state-of-the-art methods, achieving an AUROC of 99.72 and an AUPR of 99.76. The robustness of framework is further confirmed through extensive ablation studies, which highlight the crucial role of integrating both global and local information. These results underscore the potential of KGM4DTI in accurately predicting DTI. This approach has promising implications for drug discovery, particularly in developing effective treatments for depression, and could extend its applicability to broader mental health disorders. The data and code are available at https://github.com/Tianxyuu/KGM4DTI/.

Fourier Neural Operator (FNO) has been proven to be a universal and effective deep learning framework capable of achieving remarkable accuracy on Partial Differential Equation (PDE) solution problem. However, certain key components of emerging FNO-based models cannot leverage hardware potential, which makes it difficult to apply in high resolution and high realtime demand scenario. This paper presents a high optimized model called Speed Galerkin Transformer, including multilevel parallel SliceK-SplitK-ReduceK strategy for batched skinny matrix multiplication, memory layout optimization for QKV matrices and positional encodings and multi-head layer normalization fusion, as well as batched transposition optimization with strided scattering and gathering in 2D FNO, and these strategies can achieve $10.29 \mathrm{x}, 4.41 \mathrm{x}$ and 2.38 x speedup respectively under specific configuration. When solving the Darcy Flow equation at 512x512 resolution, the Speed Galerkin Transformer model can achieve about 1.72 x speedup, and achieve more than $\mathbf{9 0 \%}$ parallel efficiency on 8 GPUs.

MOTIVATION: Protein-protein interaction sites (PPIS) are crucial for deciphering protein action mechanisms and related medical research, which is the key issue in protein action research. Recent studies have shown that graph neural networks have achieved outstanding performance in predicting PPIS. However, these studies often neglect the modeling of information at different scales in the graph and the symmetry of protein molecules within three-dimensional space. RESULTS: In response to this gap, this article proposes the MEG-PPIS approach, a PPIS prediction method based on multi-scale graph information and E(n) equivariant graph neural network (EGNN). There are two channels in MEG-PPIS: the original graph and the subgraph obtained by graph pooling. The model can iteratively update the features of the original graph and subgraph through the weight-sharing EGNN. Subsequently, the max-pooling operation aggregates the updated features of the original graph and subgraph. Ultimately, the model feeds node features into the prediction layer to obtain prediction results. Comparative assessments against other methods on benchmark datasets reveal that MEG-PPIS achieves optimal performance across all evaluation metrics and gets the fastest runtime. Furthermore, specific case studies demonstrate that our method can predict more true positive and true negative sites than the current best method, proving that our model achieves better performance in the PPIS prediction task. AVAILABILITY AND IMPLEMENTATION: The data and code are available at https://github.com/dhz234/MEG-PPIS.git.

BACKGROUND: The prediction of protein-protein interaction sites plays a crucial role in biochemical processes. Investigating the interaction between viruses and receptor proteins through biological techniques aids in understanding disease mechanisms and guides the development of corresponding drugs. While various methods have been proposed in the past, they often suffer from drawbacks such as long processing times, high costs, and low accuracy. RESULTS: Addressing these challenges, we propose a novel protein-protein interaction site prediction network based on multi-information fusion. In our approach, the initial amino acid features are depicted by the position-specific scoring matrix, hidden Markov model, dictionary of protein secondary structure, and one-hot encoding. Simultaneously, we adopt a multi-channel approach to extract deep-level amino acids features from different perspectives. The graph convolutional network channel effectively extracts spatial structural information. The bidirectional long short-term memory channel treats the amino acid sequence as natural language, capturing the protein's primary structure information. The ProtT5 protein large language model channel outputs a more comprehensive amino acid embedding representation, providing a robust complement to the two aforementioned channels. Finally, the obtained amino acid features are fed into the prediction layer for the final prediction. CONCLUSION: , Matthews correlation coefficient, and area under the precision recall curve, which demonstrates the superiority of our model.

Enhancer-promoter interactions are one of the essential mechanisms in the regulation of gene expression, and Accurate identification of enhancer-promoter interactions (EPIs) is challenging. In recent years, many deep learning methods have been used for EPI prediction. In this study, we propose DeepDualEPI, a dual-channel deep learning model based on genomic signals and DNA sequences, for predicting enhancer-promoter interactions (EPI). We used network architectures such as Dilated CNN, BiLSTM, and Transformer to process genomic signals, and network architectures such as multiscale CNN to extract DNA sequence features, and finally obtained hybrid features and output EPI prediction probabilities. To obtain the best combination of parameters for the model, we conducted several ablation experiments to optimize the model parameters. And to validate the performance of DeepDualEPI, we conducted experiments on four independent test sets to verify the generalization ability of the model. Compared with other state-of-the-art EPI prediction models, the DeepDualEPI model shows significant improvement in both AUC and AUPR evaluation metrics and experimentally demonstrates that better results are achieved on every chromosome, which proves that our model can stably perform EPI prediction across cell lines. And this paper demonstrates through ablation experiments that the inclusion of DNA sequence information can improve the performance of the model. Therefore, the two-channel hybrid feature deep learning approach via genomic signals and DNA sequences proposed in this paper helps to improve the overall accuracy of EPI prediction.

Protein-protein interactions (PPIs) are a major component of the cellular biochemical reaction network. Rich sequence information and machine learning techniques reduce the dependence of exploring PPIs on wet experiments, which are costly and time-consuming. This paper proposes a PPI prediction model, multi-scale architecture residual network for PPIs (MARPPI), based on dual-channel and multi-feature. Multi-feature leverages Res2vec to obtain the association information between residues, and utilizes pseudo amino acid composition, autocorrelation descriptors and multivariate mutual information to achieve the amino acid composition and order information, physicochemical properties and information entropy, respectively. Dual channel utilizes multi-scale architecture improved ResNet network which extracts protein sequence features to reduce protein feature loss. Compared with other advanced methods, MARPPI achieves 96.03%, 99.01% and 91.80% accuracy in the intraspecific datasets of Saccharomyces cerevisiae, Human and Helicobacter pylori, respectively. The accuracy on the two interspecific datasets of Human-Bacillus anthracis and Human-Yersinia pestis is 97.29%, and 95.30%, respectively. In addition, results on specific datasets of disease (neurodegenerative and metabolic disorders) demonstrate the ability to detect hidden interactions. To better illustrate the performance of MARPPI, evaluations on independent datasets and PPIs network suggest that MARPPI can be used to predict cross-species interactions. The above shows that MARPPI can be regarded as a concise, efficient and accurate tool for PPI datasets.

Dysregulation of microRNAs (miRNAs) is closely associated with refractory human diseases, and the identification of potential associations between small molecule (SM) drugs and miRNAs can provide valuable insights for clinical treatment. Existing computational techniques for inferring potential associations suffer from limitations in terms of accuracy and efficiency. To address these challenges, we devise a novel predictive model called RPCA$\Gamma $NR, in which we propose a new Robust principal component analysis (PCA) framework based on $\gamma $-norm and $l_{2,1}$-norm regularization and design an Augmented Lagrange Multiplier method to optimize it, thereby deriving the association scores. The Gaussian Interaction Profile Kernel Similarity is calculated to capture the similarity information of SMs and miRNAs in known associations. Through extensive evaluation, including Cross Validation Experiments, Independent Validation Experiment, Efficiency Analysis, Ablation Experiment, Matrix Sparsity Analysis, and Case Studies, RPCA$\Gamma $NR outperforms state-of-the-art models concerning accuracy, efficiency and robustness. In conclusion, RPCA$\Gamma $NR can significantly streamline the process of determining SM-miRNA associations, thus contributing to advancements in drug development and disease treatment.

Tropical cyclones (TC) are one of the extreme disasters that have the most significant impact on human beings. Unfortunately, intensity forecasting of TC has been a difficult and bottleneck in weather forecasting. Recently, deep learning‐based intensity forecasting of TC has shown the potential to surpass traditional methods. However, due to the Earth system’s complexity, nonlinearity, and chaotic effects, there is inherent uncertainty in weather forecasting. Besides, previous studies have not quantified the uncertainty, which is necessary for decision‐making and risk assessment. This study proposes an intelligent system based on deep learning, PTCIF, to quantify this uncertainty based on multimodal meteorological data, which, to our knowledge, is the first study to assess the uncertainty of TC based on a deep learning approach. In this study, probabilistic forecasts are made for the intensity of 6–24 hours. Experimental results show that our proposed method is comparable to the forecast performance of weather forecast centers in terms of deterministic forecasts. Moreover, reliable prediction intervals and probabilistic forecasts can be obtained, which is vital for disaster warning and is expected to be a complement to operational models.

Tropical cyclones (TC) bring enormous harm to human beings, and it is crucial to accurately forecast the intensity of TCs, but the progress of intensity forecasting has been slow in recent years, and tropical cyclones are an extreme weather phenomenon with short duration, and the sample size of TC intensity series is small and short in length. In this paper, we devolop a tensor ARIMA model based on feature reconstruction to solve the problem, which represents multiple time series as low-rank Block Hankel Tensor(BHT), and combine the tensor decomposition technique with ARIMA for time series prediction. The method predicts the sustained maximum wind speed and central minimum pressure of TC 6-24 hours in advance, and the results show that the method exceeds the global numerical model GSM operated by the Japan Meteorological Agency (JMA) in the short term. We further checked the prediction results for a TC, and the results show the validity of the method.

Drug repositioning, which recommends approved drugs to potential targets by predicting drug-target interactions (DTIs), can save the cost and shorten the period of drug development. In this work, we propose a novel knowledge graph based deep learning method, named KG-DTI, for DTIs predictions. Specifically, a knowledge graph of 29,607 positive drug-target pairs is constructed by DistMult embedding strategy. A Conv-Conv module is proposed to extract features of drug-target pairs (DTPs), which is followed by a fully connected neural network for DTIs calculation. Data experiments are conducted on randomly chosen 11,840 positive and negative samples. It is obtained that KG-DTI achieves average ACC by 88.0%, F1-Score by 87.7%, AUROC by 94.3% and AUPR by 95% in five-fold cross-validation. In practice, KG-DTI is applied to reposition drugs to Alzheimer’s disease (AD) by Apolipoprotein E target. As results, it is found that seven of the top ten recommended drugs have been used in clinic practice or with literature supported useful to AD. Ligand-target docking results show that the top one recommended drug can dock with Apolipoprotein E significantly, which gives vital hints in repositioning potential drug to AD treatment.

The properties of the drug may be altered by the combination, which may cause unexpected drug-drug interactions (DDIs). Prediction of DDIs provides combination strategies of drugs for systematic and effective treatment. In most of deep learning-based methods for predicting DDI, encoded information about the drugs is insufficient in some extent, which limits the performances of DDIs prediction. In this work, we propose a novel attention-mechanism-based multidimensional feature encoder for DDIs prediction, namely attention-based multidimensional feature encoder (AMDE). Specifically, in AMDE, we encode drug features from multiple dimensions, including information from both Simplified Molecular-Input Line-Entry System sequence and atomic graph of the drug. Data experiments are conducted on DDI data set selected from Drugbank, involving a total of 34 282 DDI relationships with 17 141 positive DDI samples and 17 141 negative samples. Experimental results show that our AMDE performs better than some state-of-the-art baseline methods, including Random Forest, One-Dimension Convolutional Neural Networks, DeepDrug, Long Short-Term Memory, Seq2seq, Deepconv, DeepDDI, Graph Attention Networks and Knowledge Graph Neural Networks. In practice, we select a set of 150 drugs with 3723 DDIs, which are never appeared in training, validation and test sets. AMDE performs well in DDIs prediction task, with AUROC and AUPRC 0.981 and 0.975. As well, we use Torasemide (DB00214) as an example and predict the most likely drug to interact with it. The top 15 scores all have been reported with clear interactions in literatures.

We construct a protein-protein interaction (PPI) targeted drug-likeness dataset and propose a deep molecular generative framework to generate novel drug-likeness molecules from the features of the seed compounds. This framework gains inspiration from published molecular generative models, uses the key features associated with PPI inhibitors as input and develops deep molecular generative models for de novo molecular design of PPI inhibitors. For the first time, quantitative estimation index for compounds targeting PPI was applied to the evaluation of the molecular generation model for de novo design of PPI-targeted compounds. Our results estimated that the generated molecules had better PPI-targeted drug-likeness and drug-likeness. Additionally, our model also exhibits comparable performance to other several state-of-the-art molecule generation models. The generated molecules share chemical space with iPPI-DB inhibitors as demonstrated by chemical space analysis. The peptide characterization-oriented design of PPI inhibitors and the ligand-based design of PPI inhibitors are explored. Finally, we recommend that this framework will be an important step forward for the de novo design of PPI-targeted therapeutics.

Deep learning shortens the cycle of the drug discovery for its success in extracting features of molecules and proteins. Generating new molecules with deep learning methods could enlarge the molecule space and obtain molecules with specific properties. However, it is also a challenging task considering that the connections between atoms are constrained by chemical rules. Aiming at generating and optimizing new valid molecules, this article proposed Molecular Substructure Tree Generative Model, in which the molecule is generated by adding substructure gradually. The proposed model is based on the Variational Auto-Encoder architecture, which uses the encoder to map molecules to the latent vector space, and then builds an autoregressive generative model as a decoder to generate new molecules from Gaussian distribution. At the same time, for the molecular optimization task, a molecular optimization model based on CycleGAN was constructed. Experiments showed that the model could generate valid and novel molecules, and the optimized model effectively improves the molecular properties.

Tropical cyclones (TCs) generally carry large amounts of water vapor and can cause large-scale extreme rainfall. Passive microwave (PMW) rainfall (PMR) estimation of TC with high spatial and temporal resolution is crucial for disaster warning of TC, but remains a challenging problem due to low temporal resolution of microwave sensors. This study attempts to solve this problem by directly predicting PMW rainfall images (PMRIs) from satellite infrared (IR) images of TC. We develop a generative adversarial network (GAN) to simulate PMRI using IR images and establish the mapping relationship between TC cloud-top brightness temperature and PMR, and the algorithm is named tropical cyclone rainfall (TCR)-GAN. Meanwhile, a new dataset that is available as a benchmark, Dataset of TC IR-to-Rainfall Prediction (TCIRRP), was established, which is expected to advance the development of artificial intelligence in this direction. The experimental results show that the algorithm can effectively extract key features from IR. The end-to-end deep learning approach shows potential as a technique that can be applied globally and provides a new perspective TC precipitation prediction via satellite, which is expected to provide important insights for real-time visualization of TC rainfall globally in operations.

A large number of clinical studies have proved that body shape is closely related to health. Considering the actual situation, the traditional health examination has some limitations, such as low efficiency, complex process and unable to achieve real-time monitoring. In order to make health prevention more targeted and reduce the risk and deterioration of some diseases, we propose a prediction model of obesity diseases. In this model, a method based on three-dimensional human body model is used to obtain the size of human body. The shape features of human body are extracted from two human body images (front image and side image), and the dense ellipse model proposed by us is used to measure the size of human body on the three-dimensional human body model. We also summarize the traditional and nontraditional anthropometric parameters for predicting obesity diseases, and give the possible disease types and risks according to the measured body size. Users only need to take two photos through smart phones, and about 15 seconds can get health reports including anthropometric dimensions and possible types of diseases. In summary, our method can measure 38 body dimensions with an accuracy rate of 97.4%, calculate 15 anthropometric parameters related to obesity, and analyze 10 possible types of diseases.

Tropical cyclone (TC) is one of the major meteorological disasters in the world, which seriously threatens the safety of human life and property. In this study, we adopt the tropical cyclone best track archive and the global tropical cyclone exposure data sets, using the ensemble machine learning approach for exposed to the TCs of the population and asset to estimate. To the best of our knowledge, this research is the first hazards assessment study using machine learning methods to estimate the exposure of tropical cyclones to population and property end-to-end. In particular, we validated our model using data from the country most affected by tropical cyclones. The results depicted a 10% improvement over traditional methods. The correlation coefficient r between the predicted value and the exposure data is 0.813, demonstrating a strong correlation between the predicted results and the great potential of machine learning to solve the problem of hazards assessment. However, there is still uncertainty in assessing the impact of tropical cyclones, especially the impact caused by high wind speeds.

Cyclone, especially tropical cyclones, are one of the most significant meteorological disasters in the world, which seriously threaten the safety of life and property. The ability to accurately identify the type and intensity of cyclones is crucial for disaster prevention. This article proposes the use of dual branches Convolutional Neural Network (CNN) model, based on Global Forecast System Analysis (GFS) to identify cyclones, including tropical cyclones, extratropical cyclones and subtropical cyclones, a total of 11 types of cyclone-related phenomena. The model can learn spatial information and extract crucial features, and merge at the end to achieve end-to-end prediction output. The results indicate that the model's identify accuracy of tropical cyclones and extratropical cyclones exceeds 90%, and the identify accuracy of cyclones disturbances and subtropical cyclones is also more than 75%, the model does not require expert knowledge, and the speed of operation fast.

The accurate estimation of tropical cyclone (TC) size is one of the key steps in TC forecasting and disaster warninglmanagement. In this study, we proposed the use of deep convolutional neural networks (CNN) to estimate the size of tropical cyclone. To the best of our knowledge, this is the first study to estimate the size of tropical cyclones using deep learning methods; we use about 1,000 tropical cyclones which contain about 30,000 infrared remote sensing images as the data set. Compared with the best track archives, the mean error of our proposed model is 24nmi, the error is even smaller than the Multiplatform Tropical Cyclone Surface Winds Analysis (MTCSWA) operated by National Oceanic and Atmospheric Administration(NOAA), which shows the great potential of deep learning in estimating the size of tropical cyclones.

The prediction of tropical cyclones (TCs) is a valuable and challenging task. As a research hotspot of deep learning, generative adversarial network (GAN) has obtained promising results in TC prediction recently. However, different kinds of GAN applied in meteorology usually focus on how to generate high-quality images, but ignore how GAN learns the physical characteristics in the training process. This paper visualizes the intermediate results of GAN in the training process, and shows the process of learning the physical characteristics of data distribution similar to TC images for GAN. The core method in this paper is deep convolutional generative adversarial networks (DCGAN). In order to obtain prediction results with interpretable physical characteristics, we propose two training strategies for DCGAN, namely the long short-term training method and training parameters selection according to physical characteristics. Experimental results show that the DCGAN model and two strategies proposed in this paper have good performance in the visual prediction of TCs.

Ovarian cancer is a malignant tumor that poses a serious threat to women’s lives. Computer-aided diagnosis (CAD) systems can classify the type of ovarian tumors, but few of them can provide exactly the location information of ovarian cancer cells. Recently, deep learning technology becomes hot for automatic detection of cancer cells, particularly for detecting their locations. In this work, we propose a novel end-to-end network YOLO-OC (Ovarian cancer) model, which can extract the characteristics of ovarian cancer more efficiently. In our method, deformable convolution is used to enhance the model’s ability to learn geometric deformation in space. Squeeze-and-Excitation (SE) module is proposed to automatically learn the importance of different channel features. Data experiments are conducted on datasets collected from The Affiliated Hospital of Qingdao University Medical College, China. Experimental results show that our YOLO-OC model achieves 91.83%, 85.66% and 73.82% on mean average precision [email protected], [email protected] and mAP@[.5,.95], respectively, which performs better than Faster R-CNN, SSD and RetinaNet on both accuracy and efficiency.

Traditional Chinese medicine has been used to treat and prevent infectious diseases for thousands of years, and has accumulated a large number of effective prescriptions. Deep learning methods provide powerful applications in calculating interactions between drugs and targets. In this study, we try to use the method of deep learning to reposition molecules of Chinese medicines (CMs) and the targets of syndrome coronavirus 2 (SARS-CoV-2). A deep convolution neural network with residual module (DCNN-Res) is constructed and trained on KIBA dataset. The accuracy of predicting the binding affinity of drugtarget pairs is 85.33%. By ranking binding affinity scores of 433 molecules in 35 CMs to 6 targets of SARS-Cov-2, DCNN-Res recommends 30 possible repositioning molecules. The consistency between our result and the latest research is 0.827. The molecules in Gancao and Huangqin have a strong binding affinity to targets of SARS-CoV-2, which is also consistent with the latest research.

In computational drug discovery, accurately predicting drug-target interaction (DTI) is vital for drug repositioning and developing new drugs. With DTI data rapidly accumulated in recent years, it is recently hot to use deep learning technology to predict DTIs, but still a challenge to design light learning frameworks by using less protein descriptors. In this work, to address the challenge, a novel light deep convolutional neural network (namely LDCNN) is proposed to predict DTIs, in which a small number of protein descriptors are produced by convolving amino acid sequences of different lengths. As results, it is obtained that LDCNN can reduce the number of neurons in convolution layers and filters by 50%, with lose of AUC 1.3% and AUPR 4% comparing with DeepConv method. Our LDCNN models can give hints in designing light deep learning models for DTI prediction.

Abstract Object tracking is a very important step in building an intelligent video monitoring system that can protect people’s lives and property. In recent years, although visual tracking has made great progress in terms of speed and accuracy, there are still few real-time high-precision tracking algorithms. Although discriminative correlation filters have excellent performance in tracking speed, there are deficiencies in handling fast motion. This leads to the inability to achieve long-term stable tracking results. The long-time tracking with discriminative correlation filter (LT-DCF) was proposed to solve these deficiencies. We use larger size detection image blocks and smaller size filters to increase the proportion of real samples to solve the boundary effects of fast motion. And we combine the histogram of oriented gradient (HOG) feature detection and scale-invariant feature transform (SIFT) key point detection to solve the obstacles caused by scale variations. The detector with deep feature flow is then incorporated into the tracker to detect key frames to improve tracking accuracy. This method has achieved more than 75% of the distance accuracy and 70% of the overlapping success rate on the VOT2015 and VOT2016 datasets, and the stable tracking video length can reach 6895 frames.

Tissue P systems are a class of bio-inspired computing models motivated by biochemical interactions between cells in a tissue-like arrangement. Tissue P systems with cell division offer a theoretical device to generate an exponentially growing structure in order to solve computationally hard problems efficiently with the assumption that there exists a global clock to mark the time for the system, the execution of each rule is completed in exactly one time unit. Actually, the execution time of different biochemical reactions in cells depends on many uncertain factors. In this work, with this biological inspiration, we remove the restriction on the execution time of each rule, and the computational efficiency of tissue P systems with cell division is investigated. Specifically, we solve subset sum problem by tissue P systems with cell division in a time-free manner in the sense that the correctness of the solution to the problem does not depend on the execution time of the involved rules.

Roll-to-roll (R2R) printing provides a continuous printing process to print the multicolor patterns onto the flexible strip materials. The process of aligning successive print patterns on the material to form a multicolor pattern is called print registration and the registration error is the position misalignment between the two adjacent overlapped patterns. In previous studies, many works focused mainly on the dynamic model analysis and the accuracy of print registration, but few of them took the volatility of control signal into consideration, which may cause the great impact to drive motors. In this work, an optimized feedforward decoupling PD register control method is derived to generate optimized control signal without the loss of accuracy of print registration, where a novel membrane algorithm inspired by the biological functioning of cells communicating by means of delivering biochemical objects is developed to search the optimal compensation control signal instead of the exact compensation control signal. Results obtained from the simulations and industrial practice on a 7-axis rotogravure printing press show that our method can significantly decrease the 1-norm and 2-norm of control signal without losing the accuracy of print registration. The proposed method may provide a feasible way to smooth the control signal and decrease the impact to drive motors in R2R web systems.

Spiking neural P systems (SN P systems for short) are a class of neural-like computing models in the framework of membrane computing. Inspired by the neurophysiological structure of the brain, SN P systems have been extended in various ways. P–Lingua

Inspired by mitosis process and membrane fission processes, cell-like P systems with symport/antiport rules and membrane division rules or membrane separation rules have been introduced, respectively. These computation systems have two key features: the ability to have infinite copies of some objects (within an active environment) and to generate an exponential workspace in polynomial time. In this work, we extend the P-Lingua framework for simulating that kind of P systems taking into account these two features. Consequently, a new simulator has been developed and included in pLinguaCore library. The functioning of the simulator has been checked by simulating efficient solutions to SAT problem using a family of cell-like P systems with symport/antiport rules and membrane division rules or membrane separation rules. The corresponding MeCoSim based application is also provided.

Spiking neural P systems with weights are a new class of distributed and parallel computing models inspired by spiking neurons. In such models, a neuron fires when its potential equals a given value (called a threshold). In this work, spiking neural P systems with thresholds (SNPT systems) are introduced, where a neuron fires not only when its potential equals the threshold but also when its potential is higher than the threshold. Two types of SNPT systems are investigated. In the first one, we consider that the firing of a neuron consumes part of the potential (the amount of potential consumed depends on the rule to be applied). In the second one, once a neuron fires, its potential vanishes (i.e., it is reset to zero). The computation power of the two types of SNPT systems is investigated. We prove that the systems of the former type can compute all Turing computable sets of numbers and the systems of the latter type characterize the family of semilinear sets of numbers. The results show that the firing mechanism of neurons has a crucial influence on the computation power of the SNPT systems, which also answers an open problem formulated in Wang, Hoogeboom, Pan, Păun, and Pérez-Jiménez ( 2010 ).