MOTIVATION: Spatial transcriptome data have both gene expression information and cell spatial location information, offering exceptional prospects for analyzing cell-cell interaction (CCI) network. Most existing statistical and optimal transport-based methods rely only on known ligand-receptor pairs to infer CCI network. Furthermore, most current deep learning frameworks rely on symmetric decoders or undirected graph architectures. RESULTS: Taking advantage of spatial transcriptomic data and graph autoencoders, we present a directed heterogeneous graph autoencoder-based approach DualCellChat to reconstruct a complete and accurate CCI network from incomplete single cell spatial transcriptomics. Benchmarked on five single-cell spatial datasets from four different technologies, we demonstrate that DualCellChat outperforms existing deep learning-based methods and can inherently model the direction of cellular interactions. Furthermore, we introduce downstream analysis to infer signature genes involved in cellular interactions from the reconstructed CCI network and infer significant ligand-receptor pairs for specific cell types. AVAILABILITY AND IMPLEMENTATION: The dataset and code are available in GitHub (https://github.com/JinxianHu/DualCellChat) and Zenodo (DOI: 10.5281/zenodo.18512678).

MOTIVATION: In recent years, protein language models (pLMs) and graph neural networks (GNNs) have demonstrated powerful expressive and reasoning capabilities in modeling protein-RNA/DNA interactions. However, existing methods, which use simple graphs to describe the relationships between residues, struggle to effectively capture the high-order, multi-body residue interactions present in protein-nucleic acid complex structures. In fact, spatially continuous but sequence-wise discontinuous residues often cooperatively determine nucleic acid binding capacity. RESULTS: In this study, we present IKANbind, a computational approach that combines hypergraph representation learning and interpretable Kolmogorov-Arnold Networks (KANs), for identifying nucleic acid binding residues (NBRs) in proteins. By combining the advantages of pLM, hypergraph neural networks and symbolic KAN, IKANbind outperforms existing methods on multiple NBR benchmark datasets. We also demonstrated that the pLM used in IKANbind can implicitly learn the physicochemical properties of binding residues, such as charge and hydrophobicity. In addition, the symbolic KAN, which uses a unique weighted mechanism of decomposable basis functions, can accurately identify the features with the greatest contribution to NBR recognition. We found that polarity and charge make greater contributions to NBR prediction than other physicochemical properties or evolutionary information. Finally, IKANbind achieves promising performance when extended to other ligand-binding residue prediction tasks. AVAILABILITY AND IMPLEMENTATION: IKANbind is freely available at https://github.com/yangfengzhuguet/IKANBind.

Comprehending biological reproduction and cellular metabolism is facilitated by the Enzyme Commission, which matches protein sequences to the biochemical reactions they catalyse through EC numbers. In recent years, several methods have been proposed for predicting enzyme function. However, these methods still encounter challenges. Firstly, traditional methods for manually designing enzyme features are complex and cumbersome, lacking an effective generalized method for embedding enzyme sequences. Secondly, the distribution gap between different enzymes is significant, which resulting in existing methods struggling to predict multilevel enzyme functions. Thirdly, traditional enzyme function prediction models only extract single view feature of enzyme, so there is still room for further improving the ability of these models to extract enzyme data. To address these challenges, a new multilevel enzyme function prediction model (SMENET) based on multi-view semantics is proposed. This method uses protein large language model to extract semantic information. Subsequently, this semantic information is fed into multiple information extraction network modules, followed by using Biologic Sematic Attention to integrate these views' information. Finally, a multi-view adaptive fusion network is designed to extract the best common representation between multiple semantic views. Extensive experiments were conducted on multiple datasets to validate the effectiveness of SMENET.

The rapid development of RNA vaccines and therapeutics puts forward intensive requirements on the sequence design of RNAs. RNA sequence design, or RNA inverse folding, aims to generate RNA sequences that can fold into specific target structures. To date, efficient and high-accuracy prediction models for secondary structures of RNAs have been developed. They provide a basis for computational RNA sequence design methods. Especially, reinforcement learning (RL) has emerged as a promising approach for RNA design due to its ability to learn from trial and error in generation tasks and work without ground truth data. However, existing RL methods are limited in considering complex hierarchical structures in RNA design environments. To address the above limitation, we propose DRAG, an RL method that builds design environments for target secondary structures with hierarchical division based on graph neural networks. Through extensive experiments on benchmark datasets, DRAG exhibits remarkable performance compared with current machine-learning approaches for RNA sequence design. This advantage is particularly evident in long and intricate tasks involving structures with significant depth.

Studying the changes in cellular transcriptional profiles induced by small molecules can significantly advance our understanding of cellular state alterations and response mechanisms under chemical perturbations, which plays a crucial role in drug discovery and screening processes. Considering that experimental measurements need substantial time and cost, we developed a deep learning-based method called Molecule-induced Transcriptional Change Predictor (MiTCP) to predict changes in transcriptional profiles (CTPs) of 978 landmark genes induced by molecules. MiTCP utilizes graph neural network-based approaches to simultaneously model molecular structure representation and gene co-expression relationships, and integrates them for CTP prediction. After training on the L1000 dataset, MiTCP achieves an average Pearson correlation coefficient (PCC) of 0.482 on the test set and an average PCC of 0.801 for predicting the top 50 differentially expressed genes, which outperforms other existing methods. Furthermore, we used MiTCP to predict CTPs of three cancer drugs, palbociclib, irinotecan and goserelin, and performed gene enrichment analysis on the top differentially expressed genes and found that the enriched pathways and Gene Ontology terms are highly relevant to the corresponding diseases, which reveals the potential of MiTCP in drug development.

MOTIVATION: The pathogenesis of diseases is closely associated with genes, and the discovery of disease genes holds significant importance for understanding disease mechanisms and designing targeted therapeutics. However, biological validation of all genes for diseases is expensive and challenging. RESULTS: In this study, we propose DGP-AMIO, a computational method based on graph attention networks, to rank all unknown genes and identify potential novel disease genes by integrating multi-omics and gene interaction networks from multiple data sources. DGP-AMIO outperforms other methods significantly on 20 disease datasets, with an average AUROC and AUPR exceeding 0.9. The superior performance of DGP-AMIO is attributed to the integration of multiomics and gene interaction networks from multiple databases, as well as triGAT, a proposed GAT-based method that enables precise identification of disease genes in directed gene networks. Enrichment analysis conducted on the top 100 genes predicted by DGP-AMIO and literature research revealed that a majority of enriched GO terms, KEGG pathways and top genes were associated with diseases supported by relevant studies. We believe that our method can serve as an effective tool for identifying disease genes and guiding subsequent experimental validation efforts. AVAILABILITY AND IMPLEMENTATION: DGP-AMIO is publicly available at https://github.com/yangkaiyuan1027/DGP-AMIO.

MOTIVATION: Spatial clustering is a key analytical technique for exploring spatial transcriptomics data. Recent graph neural network-based methods have shown promise in spatial clustering but face notable challenges. One significant issue is that analyzing the functions and complex mechanisms of organisms from a single scale is difficult and most methods focus exclusively on the single-scale representation of transcriptomic data, potentially limiting the discriminative power of extracted features for spatial domain clustering. Furthermore, classical clustering algorithms are often applied directly to latent representation, making it a worthwhile endeavor to explore a tailored clustering method to further improve the accuracy of spatial domain annotation. RESULTS: To address these limitations, we propose m2ST, a novel dual multi-scale graph clustering method. m2ST first uses a multi-scale masked graph autoencoder to extract representations across different scales from spatial transcriptomic data. To effectively compress and distill meaningful knowledge embedded in the data, m2ST introduces a random masking mechanism for node features and uses a scaled cosine error as the loss function. Additionally, we introduce a tailored multi-scale clustering framework that integrates scale-common and scale-specific information exploration into the clustering process, achieving more robust annotation performance. Shannon entropy is finally utilized to dynamically adjust the importance of different scales. Extensive experiments on multiple spatial transcriptomic datasets demonstrate the superior performance of m2ST compared to existing methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/BBKing49/m2ST.

The development of intelligent methods capable of predicting protein-ligand binding sites has become a popular research field. Recently, deep learning based methods have been proposed as a promising solution for this task. However, some limitations still exist. For example, the network structure is not optimized for predicting protein binding pockets, which limits the model's capabilities. To address the aforementioned challenges, a novel method called CATransUnetLPB is proposed, in which a new network structure named CATransUnet is designed. The proposed CATransUnet combines CNN and Transformer models to accurately segment binding pocket regions from protein 3D structures. It outperforms existing representative methods on three test sets, demonstrating the effectiveness of optimizing the deep network model for detecting protein ligand binding pockets. Furthermore, we conduct thorough analysis on applying data augmentation to protein data structure and confirm that such technique can enhance the model's generalization ability, thereby ensuring good performance on new protein structures. Moreover, experiments show that the predicted binding pockets from our model can complement the results obtained from other methods. This suggests that integrating our method with existing approaches could further improve the prediction of protein-ligand binding pockets.

Intelligent prediction of protein function is more efficient and less resource-consuming and has achieved significant progress in recent years. However, most of the current methods are performed solely based on the sequence information of proteins. These methods overlook information of other modalities that the proteins themselves possess, which makes it difficult to achieve the desired predicted results. Furthermore, a few existing methods based on multiple modal information fuse them in a simple splicing manner and fail to fully exploit the complementary relation between different modalities. To address the above-mentioned challenges, we propose Multi-modal Multi-attention fusion Features (DMMAFS), a method based on deep learning, to predict protein function. On the one hand, DMMAFS gains the semantic information embedded in the sequence itself through the self-attention learning of the sequence. On the other hand, DMMAFS employs the 3D structural information of proteins to compensate for the sequence information. Particularly, a S-C cross-modal cross-attention fusion network module is proposed that not only optimizes the weights of the semantic information but also efficiently fuses the sequence features with the structural information, thus avoiding the simple splicing of different modal features. Our experimental results demonstrate that the proposed DMMAFS outperforms the state-of-the-art methods in protein function prediction.

RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full-length RNA transcripts is crucial for understanding these mechanisms and their roles in diseases. While machine learning methods can predict RBP binding to RNA fragments, extending this to full-length transcripts presents challenges due to sequence length and data imbalance. In this paper, we introduce RBP-Former, a binding site joint prediction model designed specifically for full-length RNA transcripts that can be used for multiple RBPs. This model processes information at both coarse and fine-grained levels to fully exploit sequence data and its interactions with multiple RBPs. We develop multi-level imbalance learning strategies, achieving favorable results on imbalanced data. Our method outperforms existing methods in predicting binding sites on full-length RNA transcripts for multiple RBPs, demonstrating its effectiveness in handling imbalanced label and sample distributions.

Designing de novo molecules with specific biological activity is an essential task since it holds the potential to bypass the exploration of target genes, which is an initial step in the modern drug discovery paradigm. However, traditional methods mainly screen molecules by comparing the desired molecular effects within the documented experimental results. The data set limits this process, and it is hard to conduct direct cross-modal comparisons. Therefore, we propose a solution based on cross-modal generation called GexMolGen (Gene Expression-based Molecule Generator), which generates hit-like molecules using gene expression signatures alone. These signatures are calculated by inputting control and desired gene expression states. Our model GexMolGen adopts a "first-align-then-generate" strategy, aligning the gene expression signatures and molecules within a mapping space, ensuring a smooth cross-modal transition. The transformed molecular embeddings are then decoded into molecular graphs. In addition, we employ an advanced single-cell large language model for input flexibility and pre-train a scaffold-based molecular model to ensure that all generated molecules are 100% valid. Empirical results show that our model can produce molecules highly similar to known references, whether feeding in- or out-of-domain transcriptome data. Furthermore, it can also serve as a reliable tool for cross-modal screening.

MOTIVATION: Drug-target interaction (DTI) prediction refers to the prediction of whether a given drug molecule will bind to a specific target and thus exert a targeted therapeutic effect. Although intelligent computational approaches for drug target prediction have received much attention and made many advances, they are still a challenging task that requires further research. The main challenges are manifested as follows: (i) most graph neural network-based methods only consider the information of the first-order neighboring nodes (drug and target) in the graph, without learning deeper and richer structural features from the higher-order neighboring nodes. (ii) Existing methods do not consider both the sequence and structural features of drugs and targets, and each method is independent of each other, and cannot combine the advantages of sequence and structural features to improve the interactive learning effect. RESULTS: To address the above challenges, a Multi-view Integrated learning Network that integrates Deep learning and Graph Learning (MINDG) is proposed in this study, which consists of the following parts: (i) a mixed deep network is used to extract sequence features of drugs and targets, (ii) a higher-order graph attention convolutional network is proposed to better extract and capture structural features, and (iii) a multi-view adaptive integrated decision module is used to improve and complement the initial prediction results of the above two networks to enhance the prediction performance. We evaluate MINDG on two dataset and show it improved DTI prediction performance compared to state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: https://github.com/jnuaipr/MINDG.

Protein-ligand binding affinity prediction is an important task in structural bioinformatics for drug discovery and design. Although various scoring functions (SFs) have been proposed, it remains challenging to accurately evaluate the binding affinity of a protein-ligand complex with the known bound structure because of the potential preference of scoring system. In recent years, deep learning (DL) techniques have been applied to SFs without sophisticated feature engineering. Nevertheless, existing methods cannot model the differential contribution of atoms in various regions of proteins, and the relationship between atom properties and intermolecular distance is also not fully explored. We propose a novel empirical graph neural network for accurate protein-ligand binding affinity prediction (EGNA). Graphs of protein, ligand and their interactions are constructed based on different regions of each bound complex. Proteins and ligands are effectively represented by graph convolutional layers, enabling the EGNA to capture interaction patterns precisely by simulating empirical SFs. The contributions of different factors on binding affinity can thus be transparently investigated. EGNA is compared with the state-of-the-art machine learning-based SFs on two widely used benchmark data sets. The results demonstrate the superiority of EGNA and its good generalization capability.

MOTIVATION: Generating molecules of high quality and drug-likeness in the vast chemical space is a big challenge in the drug discovery. Most existing molecule generative methods focus on diversity and novelty of molecules, but ignoring drug potentials of the generated molecules during the generation process. RESULTS: In this study, we present a novel de novo multiobjective quality assessment-based drug design approach (QADD), which integrates an iterative refinement framework with a novel graph-based molecular quality assessment model on drug potentials. QADD designs a multiobjective deep reinforcement learning pipeline to generate molecules with multiple desired properties iteratively, where a graph neural network-based model for accurate molecular quality assessment on drug potentials is introduced to guide molecule generation. Experimental results show that QADD can jointly optimize multiple molecular properties with a promising performance and the quality assessment module is capable of guiding the generated molecules with high drug potentials. Furthermore, applying QADD to generate novel molecules binding to a biological target protein DRD2 also demonstrates the algorithm's efficacy. AVAILABILITY AND IMPLEMENTATION: QADD is freely available online for academic use at https://github.com/yifang000/QADD or http://www.csbio.sjtu.edu.cn/bioinf/QADD.

MOTIVATION: CircRNAs play a critical regulatory role in physiological processes, and the abnormal expression of circRNAs can mediate the processes of diseases. Therefore, exploring circRNAs-disease associations is gradually becoming an important area of research. Due to the high cost of validating circRNA-disease associations using traditional wet-lab experiments, novel computational methods based on machine learning are gaining more and more attention in this field. However, current computational methods suffer to insufficient consideration of latent features in circRNA-disease interactions. RESULTS: In this study, a multilayer attention neural graph-based collaborative filtering (MLNGCF) is proposed. MLNGCF first enhances multiple biological information with autoencoder as the initial features of circRNAs and diseases. Then, by constructing a central network of different diseases and circRNAs, a multilayer cooperative attention-based message propagation is performed on the central network to obtain the high-order features of circRNAs and diseases. A neural network-based collaborative filtering is constructed to predict the unknown circRNA-disease associations and update the model parameters. Experiments on the benchmark datasets demonstrate that MLNGCF outperforms state-of-the-art methods, and the prediction results are supported by the literature in the case studies. AVAILABILITY AND IMPLEMENTATION: The source codes and benchmark datasets of MLNGCF are available at https://github.com/ABard0/MLNGCF.

BACKGROUND: Antibody-mediated immune responses play a crucial role in the immune defense of human body. The evolution of bioengineering has led the progress of antibody-derived drugs, showing promising efficacy in cancer and autoimmune disease therapy. A critical step of this development process is obtaining the affinity between antibodies and their binding antigens. RESULTS: In this study, we introduce a novel sequence-based antigen-antibody affinity prediction method, named DG-Affinity. DG-Affinity uses deep neural networks to efficiently and accurately predict the affinity between antibodies and antigens from sequences, without the need for structural information. The sequences of both the antigen and the antibody are first transformed into embedding vectors by two pre-trained language models, then these embeddings are concatenated into an ConvNeXt framework with a regression task. The results demonstrate the superiority of DG-Affinity over the existing structure-based prediction methods and the sequence-based tools, achieving a Pearson's correlation of over 0.65 on an independent test dataset. CONCLUSIONS: Compared to the baseline methods, DG-Affinity achieves the best performance and can advance the development of antibody design. It is freely available as an easy-to-use web server at https://www.digitalgeneai.tech/solution/affinity .

N6-methyladenosine (m6A) is a universal post-transcriptional modification of RNAs, and it is widely involved in various biological processes. Identifying m6A modification sites accurately is indispensable to further investigate m6A-mediated biological functions. How to better represent RNA sequences is crucial for building effective computational methods for detecting m6A modification sites. However, traditional encoding methods require complex biological prior knowledge and are time-consuming. Furthermore, most of the existing m6A sites prediction methods are limited to single species, and few methods are able to predict m6A sites across different species and tissues. Thus, it is necessary to design a more efficient computational method to predict m6A sites across multiple species and tissues. In this paper, we proposed ELMo4m6A, a contextual language embedding-based method for predicting m6A sites from RNA sequences without any prior knowledge. ELMo4m6A first learns embeddings of RNA sequences using a language model ELMo, then uses a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) to identify m6A sites. The results of 5-fold cross-validation and independent testing demonstrate that ELMo4m6A is superior to state-of-the-art methods. Moreover, we applied integrated gradients to find potential sequence patterns contributing to m6A sites.

Long noncoding RNAs (lncRNAs) play important roles in various biological regulatory processes, and are closely related to the occurrence and development of diseases. Identifying lncRNA-disease associations is valuable for revealing the molecular mechanism of diseases and exploring treatment strategies. Thus, it is necessary to computationally predict lncRNA-disease associations as a complementary method for biological experiments. In this study, we proposed a novel prediction method GCRFLDA based on the graph convolutional matrix completion. GCRFLDA first constructed a graph using the available lncRNA-disease association information. Then, it constructed an encoder consisting of conditional random field and attention mechanism to learn efficient embeddings of nodes, and a decoder layer to score lncRNA-disease associations. In GCRFLDA, the Gaussian interaction profile kernels similarity and cosine similarity were fused as side information of lncRNA and disease nodes. Experimental results on four benchmark datasets show that GCRFLDA is superior to other existing methods. Moreover, we conducted case studies on four diseases and observed that 70 of 80 predicted associated lncRNAs were confirmed by the literature.

Circular RNAs (circRNAs) generally bind to RNA-binding proteins (RBPs) to play an important role in the regulation of autoimmune diseases. Thus, it is crucial to study the binding sites of RBPs on circRNAs. Although many methods, including traditional machine learning and deep learning, have been developed to predict the interactions between RNAs and RBPs, and most of them are focused on linear RNAs. At present, few studies have been done on the binding relationships between circRNAs and RBPs. Thus, in-depth research is urgently needed. In the existing circRNA-RBP binding site prediction methods, circRNA sequences are the main research subjects, but the relevant characteristics of circRNAs have not been fully exploited, such as the structure and composition information of circRNA sequences. Some methods have extracted different views to construct recognition models, but how to efficiently use the multi-view data to construct recognition models is still not well studied. Considering the above problems, this paper proposes a multi-view classification method called DMSK based on multi-view deep learning, subspace learning and multi-view classifier for the identification of circRNA-RBP interaction sites. In the DMSK method, first, we converted circRNA sequences into pseudo-amino acid sequences and pseudo-dipeptide components for extracting high-dimensional sequence features and component features of circRNAs, respectively. Then, the structure prediction method RNAfold was used to predict the secondary structure of the RNA sequences, and the sequence embedding model was used to extract the context-dependent features. Next, we fed the above four views' raw features to a hybrid network, which is composed of a convolutional neural network and a long short-term memory network, to obtain the deep features of circRNAs. Furthermore, we used view-weighted generalized canonical correlation analysis to extract four views' common features by subspace learning. Finally, the learned subspace common features and multi-view deep features were fed to train the downstream multi-view TSK fuzzy system to construct a fuzzy rule and fuzzy inference-based multi-view classifier. The trained classifier was used to predict the specific positions of the RBP binding sites on the circRNAs. The experiments show that the prediction performance of the proposed method DMSK has been improved compared with the existing methods. The code and dataset of this study are available at https://github.com/Rebecca3150/DMSK.

Circular RNA (circRNA) is closely involved in physiological and pathological processes of many diseases. Discovering the associations between circRNAs and diseases is of great significance. Due to the high-cost to verify the circRNA-disease associations by wet-lab experiments, computational approaches for predicting the associations become a promising research direction. In this paper, we propose a method, MDGF-MCEC, based on multi-view dual attention graph convolution network (GCN) with cooperative ensemble learning to predict circRNA-disease associations. First, MDGF-MCEC constructs two disease relation graphs and two circRNA relation graphs based on different similarities. Then, the relation graphs are fed into a multi-view GCN for representation learning. In order to learn high discriminative features, a dual-attention mechanism is introduced to adjust the contribution weights, at both channel level and spatial level, of different features. Based on the learned embedding features of diseases and circRNAs, nine different feature combinations between diseases and circRNAs are treated as new multi-view data. Finally, we construct a multi-view cooperative ensemble classifier to predict the associations between circRNAs and diseases. Experiments conducted on the CircR2Disease database demonstrate that the proposed MDGF-MCEC model achieves a high area under curve of 0.9744 and outperforms the state-of-the-art methods. Promising results are also obtained from experiments on the circ2Disease and circRNADisease databases. Furthermore, the predicted associated circRNAs for hepatocellular carcinoma and gastric cancer are supported by the literature. The code and dataset of this study are available at https://github.com/ABard0/MDGF-MCEC.

Protein structure alignment algorithms are often time-consuming, resulting in challenges for large-scale protein structure similarity-based retrieval. There is an urgent need for more efficient structure comparison approaches as the number of protein structures increases rapidly. In this paper, we propose an effective graph-based protein structure representation learning method, GraSR, for fast and accurate structure comparison. In GraSR, a graph is constructed based on the intra-residue distance derived from the tertiary structure. Then, deep graph neural networks (GNNs) with a short-cut connection learn graph representations of the tertiary structures under a contrastive learning framework. To further improve GraSR, a novel dynamic training data partition strategy and length-scaling cosine distance are introduced. We objectively evaluate our method GraSR on SCOPe v2.07 and a new released independent test set from PDB database with a designed comprehensive performance metric. Compared with other state-of-the-art methods, GraSR achieves about 7%-10% improvement on two benchmark datasets. GraSR is also much faster than alignment-based methods. We dig into the model and observe that the superiority of GraSR is mainly brought by the learned discriminative residue-level and global descriptors. The web-server and source code of GraSR are freely available at www.csbio.sjtu.edu.cn/bioinf/GraSR/ for academic use.

Identifying protein subcellular locations is an important topic in protein function prediction. Interacting proteins may share similar locations. Thus, it is imperative to infer protein subcellular locations by taking protein-protein interactions (PPIs)into account. In this study, we present a network embedding-based method, node2loc, to identify protein subcellular locations. node2loc first learns distributed embeddings of proteins in a protein-protein interaction (PPI)network using node2vec. Then the learned embeddings are further fed into a recurrent neural network (RNN). To resolve the severe class imbalance of different subcellular locations, Synthetic Minority Over-sampling Technique (SMOTE)is applied to artificially synthesize proteins for minority classes. node2loc is evaluated on our constructed human benchmark dataset with 16 subcellular locations and yields a Matthews correlation coefficient (MCC)value of 0.800, which is superior to baseline methods. In addition, node2loc yields a better performance on a Yeast benchmark dataset with 17 locations. The results demonstrate that the learned representations from a PPI network have certain discriminative ability for classifying protein subcellular locations. However, node2loc is a transductive method, it only works for proteins connected in a PPI network, and it needs to be retrained for new proteins. In addition, the PPI network needs be annotated to some extent with location information. node2loc is freely available at https://github.com/xypan1232/node2loc.

Circular RNAs (circRNAs) interact with RNA-binding proteins (RBPs) to play crucial roles in gene regulation and disease development. Computational approaches have attracted much attention to quickly predict highly potential RBP binding sites on circRNAs using the sequence or structure statistical binding knowledge. Deep learning is one of the popular learning models in this area but usually requires a lot of labeled training data. It would perform unsatisfactorily for the less characterized RBPs with a limited number of known target circRNAs. How to improve the prediction performance for such small-size labeled characterized RBPs is a challenging task for deep learning-based models. In this study, we propose an RBP-specific method iDeepC for predicting RBP binding sites on circRNAs from sequences. It adopts a Siamese neural network consisting of a lightweight attention module and a metric module. We have found that Siamese neural network effectively enhances the network capability of capturing mutual information between circRNAs with pairwise metric learning. To further deal with the small-sample size problem, we have performed the pretraining using available labeled data from other RBPs and also demonstrate the efficacy of this transfer-learning pipeline. We comprehensively evaluated iDeepC on the benchmark datasets of RBP-binding circRNAs, and the results suggest iDeepC achieving promising results on the poorly characterized RBPs. The source code is available at https://github.com/hehew321/iDeepC.

RNA-binding protein (RBP) is a class of proteins that bind to and accompany RNAs in regulating biological processes. An RBP may have multiple target RNAs, and its aberrant expression can cause multiple diseases. Methods have been designed to predict whether a specific RBP can bind to an RNA and the position of the binding site using binary classification model. However, most of the existing methods do not take into account the binding similarity and correlation between different RBPs. While methods employing multiple labels and Long Short Term Memory Network (LSTM) are proposed to consider binding similarity between different RBPs, the accuracy remains low due to insufficient feature learning and multi-label learning on RNA sequences. In response to this challenge, the concept of RNA-RBP Binding Network (RRBN) is proposed in this paper to provide theoretical support for multi-label learning to identify RBPs that can bind to RNAs. It is experimentally shown that the RRBN information can significantly improve the prediction of unknown RNA-RBP interactions. To further improve the prediction accuracy, we present the novel computational method iDeepMV which integrates multi-view deep learning technology under the multi-label learning framework. iDeepMV first extracts data from the views of amino acid sequence and dipeptide component based on the RNA sequences as the original view. Deep neural network models are then designed for the respective views to perform deep feature learning. The extracted deep features are fed into multi-label classifiers which are trained with the RNA-RBP interaction information for the three views. Finally, a voting mechanism is designed to make comprehensive decision on the results of the multi-label classifiers. Our experimental results show that the prediction performance of iDeepMV, which combines multi-view deep feature learning models with RNA-RBP interaction information, is significantly better than that of the state-of-the-art methods. iDeepMV is freely available at http://www.csbio.sjtu.edu.cn/bioinf/iDeepMV for academic use. The code is freely available at http://github.com/uchihayht/iDeepMV.

MOTIVATION: Long non-coding RNAs (lncRNAs) are generally expressed in a tissue-specific way, and subcellular localizations of lncRNAs depend on the tissues or cell lines that they are expressed. Previous computational methods for predicting subcellular localizations of lncRNAs do not take this characteristic into account, they train a unified machine learning model for pooled lncRNAs from all available cell lines. It is of importance to develop a cell-line-specific computational method to predict lncRNA locations in different cell lines. RESULTS: In this study, we present an updated cell-line-specific predictor lncLocator 2.0, which trains an end-to-end deep model per cell line, for predicting lncRNA subcellular localization from sequences. We first construct benchmark datasets of lncRNA subcellular localizations for 15 cell lines. Then we learn word embeddings using natural language models, and these learned embeddings are fed into convolutional neural network, long short-term memory and multilayer perceptron to classify subcellular localizations. lncLocator 2.0 achieves varying effectiveness for different cell lines and demonstrates the necessity of training cell-line-specific models. Furthermore, we adopt Integrated Gradients to explain the proposed model in lncLocator 2.0, and find some potential patterns that determine the subcellular localizations of lncRNAs, suggesting that the subcellular localization of lncRNAs is linked to some specific nucleotides. AVAILABILITYAND IMPLEMENTATION: The lncLocator 2.0 is available at www.csbio.sjtu.edu.cn/bioinf/lncLocator2 and the source code can be found at https://github.com/Yang-J-LIN/lncLocator2.

MOTIVATION: Genetically engineering food crops involves introducing proteins from other species into crop plant species or modifying already existing proteins with gene editing techniques. In addition, newly synthesized proteins can be used as therapeutic protein drugs against diseases. For both research and safety regulation purposes, being able to assess the potential toxicity of newly introduced/synthesized proteins is of high importance. RESULTS: In this study, we present ToxDL, a deep learning-based approach for in silico prediction of protein toxicity from sequence alone. ToxDL consists of (i) a module encompassing a convolutional neural network that has been designed to handle variable-length input sequences, (ii) a domain2vec module for generating protein domain embeddings and (iii) an output module that classifies proteins as toxic or non-toxic, using the outputs of the two aforementioned modules. Independent test results obtained for animal proteins and cross-species transferability results obtained for bacteria proteins indicate that ToxDL outperforms traditional homology-based approaches and state-of-the-art machine-learning techniques. Furthermore, through visualizations based on saliency maps, we are able to verify that the proposed network learns known toxic motifs. Moreover, the saliency maps allow for directed in silico modification of a sequence, thus making it possible to alter its predicted protein toxicity. AVAILABILITY AND IMPLEMENTATION: ToxDL is freely available at http://www.csbio.sjtu.edu.cn/bioinf/ToxDL/. The source code can be found at https://github.com/xypan1232/ToxDL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Knowledge of protein-ligand binding residues is important for understanding the functions of proteins and their interaction mechanisms. From experimentally solved protein structures, how to accurately identify its potential binding sites of a specific ligand on the protein is still a challenging problem. Compared with structure-alignment-based methods, machine learning algorithms provide an alternative flexible solution which is less dependent on annotated homogeneous protein structures. Several factors are important for an efficient protein-ligand prediction model, e.g. discriminative feature representation and effective learning architecture to deal with both the large-scale and severely imbalanced data. RESULTS: In this study, we propose a novel deep-learning-based method called DELIA for protein-ligand binding residue prediction. In DELIA, a hybrid deep neural network is designed to integrate 1D sequence-based features with 2D structure-based amino acid distance matrices. To overcome the problem of severe data imbalance between the binding and nonbinding residues, strategies of oversampling in mini-batch, random undersampling and stacking ensemble are designed to enhance the model. Experimental results on five benchmark datasets demonstrate the effectiveness of proposed DELIA pipeline. AVAILABILITY AND IMPLEMENTATION: The web server of DELIA is available at www.csbio.sjtu.edu.cn/bioinf/delia/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Long non-coding RNAs (lncRNAs) are important regulators in wide variety of biological processes, which are linked to many diseases. Compared to protein-coding genes (PCGs), the association between diseases and lncRNAs is still not well studied. Thus, inferring disease-associated lncRNAs on a genome-wide scale has become imperative. RESULTS: In this study, we propose a machine learning-based method, DislncRF, which infers disease-associated lncRNAs on a genome-wide scale based on tissue expression profiles. DislncRF uses random forest models trained on expression profiles of known disease-associated PCGs across human tissues to extract general patterns between expression profiles and diseases. These models are then applied to score associations between lncRNAs and diseases. DislncRF was benchmarked against a gold standard dataset and compared to other methods. The results show that DislncRF yields promising performance and outperforms the existing methods. The utility of DislncRF is further substantiated on two diseases in which we find that top scoring candidates are supported by literature or independent datasets. AVAILABILITY AND IMPLEMENTATION: https://github.com/xypan1232/DislncRF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: The long non-coding RNA (lncRNA) studies have been hot topics in the field of RNA biology. Recent studies have shown that their subcellular localizations carry important information for understanding their complex biological functions. Considering the costly and time-consuming experiments for identifying subcellular localization of lncRNAs, computational methods are urgently desired. However, to the best of our knowledge, there are no computational tools for predicting the lncRNA subcellular locations to date. Results: In this study, we report an ensemble classifier-based predictor, lncLocator, for predicting the lncRNA subcellular localizations. To fully exploit lncRNA sequence information, we adopt both k-mer features and high-level abstraction features generated by unsupervised deep models, and construct four classifiers by feeding these two types of features to support vector machine (SVM) and random forest (RF), respectively. Then we use a stacked ensemble strategy to combine the four classifiers and get the final prediction results. The current lncLocator can predict five subcellular localizations of lncRNAs, including cytoplasm, nucleus, cytosol, ribosome and exosome, and yield an overall accuracy of 0.59 on the constructed benchmark dataset. Availability and implementation: The lncLocator is available at www.csbio.sjtu.edu.cn/bioinf/lncLocator. Supplementary information: Supplementary data are available at Bioinformatics online.

Motivation: RNA-binding proteins (RBPs) take over 5-10% of the eukaryotic proteome and play key roles in many biological processes, e.g. gene regulation. Experimental detection of RBP binding sites is still time-intensive and high-costly. Instead, computational prediction of the RBP binding sites using patterns learned from existing annotation knowledge is a fast approach. From the biological point of view, the local structure context derived from local sequences will be recognized by specific RBPs. However, in computational modeling using deep learning, to our best knowledge, only global representations of entire RNA sequences are employed. So far, the local sequence information is ignored in the deep model construction process. Results: In this study, we present a computational method iDeepE to predict RNA-protein binding sites from RNA sequences by combining global and local convolutional neural networks (CNNs). For the global CNN, we pad the RNA sequences into the same length. For the local CNN, we split a RNA sequence into multiple overlapping fixed-length subsequences, where each subsequence is a signal channel of the whole sequence. Next, we train deep CNNs for multiple subsequences and the padded sequences to learn high-level features, respectively. Finally, the outputs from local and global CNNs are combined to improve the prediction. iDeepE demonstrates a better performance over state-of-the-art methods on two large-scale datasets derived from CLIP-seq. We also find that the local CNN runs 1.8 times faster than the global CNN with comparable performance when using GPUs. Our results show that iDeepE has captured experimentally verified binding motifs. Availability and implementation: https://github.com/xypan1232/iDeepE. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: RNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation. RESULTS: In viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs. Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications. CONCLUSION: The iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at http://www.csbio.sjtu.edu.cn/bioinf/iDeep.