The linear neighborhood propagation method for predicting long non-coding RNA–protein interactions

Protein subcellular localization prediction tools

Protein subcellular localization prediction is of great significance in bioinformatics and biological research. Most of the proteins do not have experimentally determined localization information, computational prediction methods and tools have been acting as an active research area for more than two decades now. Knowledge of the subcellular location of a protein provides valuable information about its functionalities, the functioning of the cell, and other possible interactions with proteins. Fast, reliable, and accurate predictors provides platforms to harness the abundance of sequence data to predict subcellular locations accordingly. During the last decade, there has been a considerable amount of research effort aimed at developing subcellular localization predictors. This paper reviews recent subcellular localization prediction tools in the Eukaryotic, Prokaryotic, and Virus-based categories followed by a detailed analysis. Each predictor is discussed based on its main features, strengths, weaknesses, algorithms used, prediction techniques, and analysis. This review is supported by prediction tools taxonomies that highlight their rele- vant area and examples for uncomplicated categorization and ease of understandability. These taxonomies help users find suitable tools according to their needs. Furthermore, recent research gaps and challenges are discussed to cover areas that need the utmost attention. This survey provides an in-depth analysis of the most recent prediction tools to facilitate readers and can be considered a quick guide for researchers to identify and explore the recent literature advancements.

NPI-DCGNN: An Accurate Tool for Identifying ncRNA-Protein Interactions Using a Dual-Channel Graph Neural Network

Noncoding RNA (NcRNA)-protein interactions (NPIs) play fundamentally important roles in carrying out cellular activities. Although various predictors based on molecular features and graphs have been published to boost the identification of NPIs, most of them often ignore the information between known NPIs or exhibit insufficient learning ability from graphs, posing a significant challenge in effectively identifying NPIs. To develop a more reliable and accurate predictor for NPIs, in this article, we propose NPI-DCGNN, an end-to-end NPI predictor based on a dual-channel graph neural network (DCGNN). NPI-DCGNN initially treats the known NPIs as an ncRNA-protein bipartite graph. Subsequently, for each ncRNA-protein pair, NPI-DCGNN extracts two local subgraphs centered around the ncRNA and protein, respectively, from the bipartite graph. After that, it utilizes a dual-channel graph representation learning layer based on GNN to generate high-level feature representations for the ncRNA-protein pair. Finally, it employs a fully connected network and output layer to predict whether an interaction exists between the pair of ncRNA and protein. Experimental results on four experimentally validated datasets demonstrate that NPI-DCGNN outperforms several state-of-the-art NPI predictors. Our case studies on the NPInter database further demonstrate the prediction power of NPI-DCGNN in predicting NPIs. With the availability of the source codes (https://github.com/zhangxin11111/NPI-DCGNN), we anticipate that NPI-DCGNN could facilitate the studies of ncRNA interactome by providing highly reliable NPI candidates for further experimental validation.

CBIL-VHPLI: a model for predicting viral-host protein-lncRNA interactions based on machine learning and transfer learning

Virus‒host protein‒lncRNA interaction (VHPLI) predictions are critical for decoding the molecular mechanisms of viral pathogens and host immune processes. Although VHPLI interactions have been predicted in both plants and animals, they have not been extensively studied in viruses. For the first time, we propose a new deep learning-based approach that consists mainly of a convolutional neural network and bidirectional long and short-term memory network modules in combination with transfer learning named CBIL‒VHPLI to predict viral-host protein‒lncRNA interactions. The models were first trained on large and diverse datasets (including plants, animals, etc.). Protein sequence features were extracted using a k-mer method combined with the one-hot encoding and composition-transition-distribution (CTD) methods, and lncRNA sequence features were extracted using a k-mer method combined with the one-hot encoding and Z curve methods. The results obtained on three independent external validation datasets showed that the pre-trained CBIL‒VHPLI model performed the best with an accuracy of approximately 0.9. Pretraining was followed by conducting transfer learning on a viral protein-human lncRNA dataset, and the fine-tuning results showed that the accuracy of CBIL‒VHPLI was 0.946, which was significantly greater than that of the previous models. The final case study results showed that CBIL‒VHPLI achieved a prediction reproducibility rate of 91.6% for the RIP-Seq experimental screening results. This model was then used to predict the interactions between human lncRNA PIK3CD-AS2 and the nonstructural protein 1 (NS1) of the H5N1 virus, and RNA pull-down experiments were used to prove the prediction readiness of the model in terms of prediction. The source code of CBIL‒VHPLI and the datasets used in this work are available at https://github.com/Liu-Lab-Lnu/CBIL-VHPLI for academic usage.

Fusion of multi-source relationships and topology to infer lncRNA-protein interactions

Long non-coding RNAs (lncRNAs) are important factors involved in biological regulatory networks. Accurately predicting lncRNA-protein interactions (LPIs) is vital for clarifying lncRNA's functions and pathogenic mechanisms. Existing deep learning models have yet to yield satisfactory results in LPI prediction. Recently, graph autoencoders (GAEs) have seen rapid development, excelling in tasks like link prediction and node classification. We employed GAE technology for LPI prediction, devising the FMSRT-LPI model based on path masking and degree regression strategies and thereby achieving satisfactory outcomes. This represents the first known integration of path masking and degree regression strategies into the GAE framework for potential LPI inference. The effectiveness of our FMSRT-LPI model primarily relies on four key aspects. First, within the GAE framework, our model integrates multi-source relationships of lncRNAs and proteins with LPN's topological data. Second, the implemented masking strategy efficiently identifies LPN's key paths, reconstructs the network, and reduces the impact of redundant or incorrect data. Third, the integrated degree decoder balances degree and structural information, enhancing node representation. Fourth, the PolyLoss function we introduced is more appropriate for LPI prediction tasks. The results on multiple public datasets further demonstrate our model's potential in LPI prediction.

Predicting Microbe-Disease Associations Based on a Linear Neighborhood Label Propagation Method with Multi-order Similarity Fusion Learning

Computational approaches employed for predicting potential microbe-disease associations often rely on similarity information between microbes and diseases. Therefore, it is important to obtain reliable similarity information by integrating multiple types of similarity information. However, existing similarity fusion methods do not consider multi-order fusion of similarity networks. To address this problem, a novel method of linear neighborhood label propagation with multi-order similarity fusion learning (MOSFL-LNP) is proposed to predict potential microbe-disease associations. Multi-order fusion learning comprises two parts: low-order global learning and high-order feature learning. Low-order global learning is used to obtain common latent features from multiple similarity sources. High-order feature learning relies on the interactions between neighboring nodes to identify high-order similarities and learn deeper interactive network structures. Coefficients are assigned to different high-order feature learning modules to balance the similarities learned from different orders and enhance the robustness of the fusion network. Overall, by combining low-order global learning with high-order feature learning, multi-order fusion learning can capture both the shared and unique features of different similarity networks, leading to more accurate predictions of microbe-disease associations. In comparison to six other advanced methods, MOSFL-LNP exhibits superior prediction performance in the leave-one-out cross-validation and 5-fold validation frameworks. In the case study, the predicted 10 microbes associated with asthma and type 1 diabetes have an accuracy rate of up to 90% and 100%, respectively.

Prediction of LncRNA-Protein Interactions Based on Kernel Combinations and Graph Convolutional Networks

The complexes of long non-coding RNAs bound to proteins can be involved in regulating life activities at various stages of organisms. However, in the face of the growing number of lncRNAs and proteins, verifying LncRNA-Protein Interactions (LPI) based on traditional biological experiments is time-consuming and laborious. Therefore, with the improvement of computing power, predicting LPI has met new development opportunity. In virtue of the state-of-the-art works, a framework called LncRNA-Protein Interactions based on Kernel Combinations and Graph Convolutional Networks (LPI-KCGCN) has been proposed in this article. We first construct kernel matrices by taking advantage of extracting both the lncRNAs and protein concerning the sequence features, sequence similarity features, expression features, and gene ontology. Then reconstruct the existent kernel matrices as the input of the next step. Combined with known LPI interactions, the reconstructed similarity matrices, which can be used as features of the topology map of the LPI network, are exploited in extracting potential representations in the lncRNA and protein space using a two-layer Graph Convolutional Network. The predicted matrix can be finally obtained by training the network to produce scoring matrices w.r.t. lncRNAs and proteins. Different LPI-KCGCN variants are ensemble to derive the final prediction results and testify on balanced and unbalanced datasets. The 5-fold cross-validation shows that the optimal feature information combination on a dataset with 15.5% positive samples has an AUC value of 0.9714 and an AUPR value of 0.9216. On another highly unbalanced dataset with only 5% positive samples, LPI-KCGCN also has outperformed the state-of-the-art works, which achieved an AUC value of 0.9907 and an AUPR value of 0.9267.

LPI-IBWA: Predicting lncRNA-protein interactions based on an improved Bi-Random walk algorithm

Many studies have shown that long-chain noncoding RNAs (lncRNAs) are involved in a variety of biological processes such as post-transcriptional gene regulation, splicing, and translation by combining with corresponding proteins. Predicting lncRNA-protein interactions is an effective approach to infer the functions of lncRNAs. The paper proposes a new computational model named LPI-IBWA. At first, LPI-IBWA uses similarity kernel fusion (SKF) to integrate various types of biological information to construct lncRNA and protein similarity networks. Then, a bounded matrix completion model and a weighted k-nearest known neighbors algorithm are utilized to update the initial sparse lncRNA-protein interaction matrix. Based on the updated lncRNA-protein interaction matrix, the lncRNA similarity network and the protein similarity network are integrated into a heterogeneous network. Finally, an improved Bi-Random walk algorithm is used to predict novel latent lncRNA-protein interactions. 5-fold cross-validation experiments on a benchmark dataset showed that the AUC and AUPR of LPI-IBWA reach 0.920 and 0.736, respectively, which are higher than those of other state-of-the-art methods. Furthermore, the experimental results of case studies on a novel dataset also illustrated that LPI-IBWA could efficiently predict potential lncRNA-protein interactions.

In silico protein function prediction: the rise of machine learning-based approaches

Proteins function as integral actors in essential life processes, rendering the realm of protein research a fundamental domain that possesses the potential to propel advancements in pharmaceuticals and disease investigation. Within the context of protein research, an imperious demand arises to uncover protein functionalities and untangle intricate mechanistic underpinnings. Due to the exorbitant costs and limited throughput inherent in experimental investigations, computational models offer a promising alternative to accelerate protein function annotation. In recent years, protein pre-training models have exhibited noteworthy advancement across multiple prediction tasks. This advancement highlights a notable prospect for effectively tackling the intricate downstream task associated with protein function prediction. In this review, we elucidate the historical evolution and research paradigms of computational methods for predicting protein function. Subsequently, we summarize the progress in protein and molecule representation as well as feature extraction techniques. Furthermore, we assess the performance of machine learning-based algorithms across various objectives in protein function prediction, thereby offering a comprehensive perspective on the progress within this field.

Graph Reasoning Method Based on Affinity Identification and Representation Decoupling for Predicting lncRNA-Disease Associations

An increasing number of studies have shown that dysregulation of lncRNAs is related to the occurrence of various diseases. Most of the previous methods, however, are designed based on homogeneity assumption that the representation of a target lncRNA (or disease) node should be updated by aggregating the attributes of its neighbor nodes. However, the assumption ignores the affinity nodes that are far from the target node. We present a novel prediction method, GAIRD, to fully leverage the heterogeneous information in the network and the decoupled node features. The first major innovation is a random walk strategy based on width-first searching and depth-first searching. Different from previous methods that only focus on homogeneous information, our new strategy learns both the homogeneous information within local neighborhoods and the heterogeneous information within higher-order neighborhoods. The second innovation is a representation decoupling module to extract the purer attributes and the purer topologies. Third, a module based on group convolution and deep separable convolution is developed to promote the pairwise intrachannel and interchannel feature learning. The experimental results show that GAIRD outperforms comparing state-of-the-art methods, and the ablation studies prove the contributions of major innovations. We also performed case studies on 3 diseases to further demonstrate the effectiveness of the GAIRD model in applications.

LncRNA-protein interaction prediction with reweighted feature selection

LncRNA-protein interactions are ubiquitous in organisms and play a crucial role in a variety of biological processes and complex diseases. Many computational methods have been reported for lncRNA-protein interaction prediction. However, the experimental techniques to detect lncRNA-protein interactions are laborious and time-consuming. Therefore, to address this challenge, this paper proposes a reweighting boosting feature selection (RBFS) method model to select key features. Specially, a reweighted apporach can adjust the contribution of each observational samples to learning model fitting; let higher weights are given more influence samples than those with lower weights. Feature selection with boosting can efficiently rank to iterate over important features to obtain the optimal feature subset. Besides, in the experiments, the RBFS method is applied to the prediction of lncRNA-protein interactions. The experimental results demonstrate that our method achieves higher accuracy and less redundancy with fewer features.

Non-coding RNA identification with pseudo RNA sequences and feature representation learning

Distinguishing non-coding RNAs (ncRNAs) from coding RNAs is very important in bioinformatics. Although many methods have been proposed for solving this task, it remains highly challenging to further improve the accuracy of ncRNA identification. In this paper, we propose a coding potential predictor using feature representation learning based on pseudo RNA sequences named CPPFLPS. In this method, we use the pseudo RNA sequences generated by simulating RNA sequence mutations as new samples for data augmentation, and six string operations simulating RNA sequence mutations are considered: base replacement, base insertion, base deletion, subsequence reversion, subsequence repetition and subsequence deletion. In the feature representation learning framework, different types of pseudo RNA sequences are added to the training set to form new training sets that can be used to train baseline classifiers, thus obtaining baseline models. The resulting labels of these baseline models are used as feature vectors to represent RNA sequences, and the resulting feature vectors acquired after feature selection are used to train a predictive model for distinguishing ncRNAs from coding RNAs. Our method achieves better performance compared with that of existing state-of-the-art methods. The implementation of the proposed method is available at https://github.com/chenxgscuec/CPPFLPS.

A Survey of Computational Methods and Databases for lncRNA-MiRNA Interaction Prediction

Long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) are two prevalent non-coding RNAs in current research. They play critical regulatory roles in the life processes of animals and plants. Studies have shown that lncRNAs can interact with miRNAs to participate in post-transcriptional regulatory processes, mainly involved in regulating cancer development, metastatic progression, and drug resistance. Additionally, these interactions have significant effects on plant growth, development, and responses to biotic and abiotic stresses. Deciphering the potential relationships between lncRNAs and miRNAs may provide new insights into our understanding of the biological functions of lncRNAs and miRNAs, and the pathogenesis of complex diseases. In contrast, gathering information on lncRNA-miRNA interactions (LMIs) through biological experiments is expensive and time-consuming. With the accumulation of multi-omics data, computational models are extremely attractive in systematically exploring potential LMIs. To the best of our knowledge, this is the first comprehensive review of computational methods for identifying LMIs. Specifically, we first summarized the available public databases for predicting animal and plant LMIs. Second, we comprehensively reviewed the computational methods for predicting LMIs and classified them into two categories, including network-based methods and sequence-based methods. Third, we analyzed the standard evaluation methods and metrics used in LMI prediction. Finally, we pointed out some problems in the current study and discuss future research directions. Relevant databases and the latest advances in LMI prediction are summarized in a GitHub repository https://github.com/sheng-n/lncRNA-miRNA-interaction-methods, and we'll keep it updated.

MSIF-LNP: microbial and human health association prediction based on matrix factorization noise reduction for similarity fusion and bidirectional linear neighborhood label propagation

Studies have shown that microbes are closely related to human health. Clarifying the relationship between microbes and diseases that cause health problems can provide new solutions for the treatment, diagnosis, and prevention of diseases, and provide strong protection for human health. Currently, more and more similarity fusion methods are available to predict potential microbe-disease associations. However, existing methods have noise problems in the process of similarity fusion. To address this issue, we propose a method called MSIF-LNP that can efficiently and accurately identify potential connections between microbes and diseases, and thus clarify the relationship between microbes and human health. This method is based on matrix factorization denoising similarity fusion (MSIF) and bidirectional linear neighborhood propagation (LNP) techniques. First, we use non-linear iterative fusion to obtain a similarity network for microbes and diseases by fusing the initial microbe and disease similarities, and then reduce noise by using matrix factorization. Next, we use the initial microbe-disease association pairs as label information to perform linear neighborhood label propagation on the denoised similarity network of microbes and diseases. This enables us to obtain a score matrix for predicting microbe-disease relationships. We evaluate the predictive performance of MSIF-LNP and seven other advanced methods through 10-fold cross-validation, and the experimental results show that MSIF-LNP outperformed the other seven methods in terms of AUC. In addition, the analysis of Cystic fibrosis and Obesity cases further demonstrate the predictive ability of this method in practical applications.

Docsubty: FLAncRPI-LGAT: Prediction of ncRNA-Protein Interactions with Line Graph Attention Network Framework

Identification of ncRNA-protein interactions (ncRPIs) through wet experiments is still time-consuming and highly-costly. Although several computational approaches have been developed to predict ncRPIs using the structure and sequence information of ncRNAs and proteins, the prediction accuracy needs to be improved, and the results lack interpretability. In this work, we proposed a novel computational method (called ncRPI-LGAT) to predict the ncRNA-Protein Interactions by transforming the link prediction (i.e., subgraph classification) task into a node classification task in the line network, and introducing a Line Graph ATtention network framework. ncRPI-LGAT first extracts the ncRNA/protein attributes using node2vec, and then generates the local enclosing subgraph of a target ncRNA-protein pair with SEAL. Because using the pooling operations in local enclosing subgraphs to learn a fixed-size feature vector for representing ncRNAs/proteins will cause the information loss, ncRPI-LGAT converts the local enclosing subgraphs into their corresponding line graphs, in which the node corresponds to the edge (i.e., ncRNA-protein pair) of the local enclosing subgraphs. Then, the attention mechanism-based graph neural network GATv2 is used on these line graphs to efficiently learn the embedding features of the target nodes (i.e., ncRNA-protein pairs) by focusing on learning the significance of one ncRNA-protein pair to another ncRNA-protein pair. These embedding features of one ncRNA-protein pair obtained from multi-head attention are concatenated in series and then fed them into a fully connected network to predict ncRPIs. Compared with other state-of-the-art methods in the 5CV test, ncRPI-LGAT shows superior performance on three benchmark datasets, demonstrating the effectiveness of our ncRPI-LGAT method in predicting ncRNA-protein interactions.

LPIH2V: LncRNA-protein interactions prediction using HIN2Vec based on heterogeneous networks model

LncRNA-protein interaction plays an important role in the development and treatment of many human diseases. As the experimental approaches to determine lncRNA-protein interactions are expensive and time-consuming, considering that there are few calculation methods, therefore, it is urgent to develop efficient and accurate methods to predict lncRNA-protein interactions. In this work, a model for heterogeneous network embedding based on meta-path, namely LPIH2V, is proposed. The heterogeneous network is composed of lncRNA similarity networks, protein similarity networks, and known lncRNA-protein interaction networks. The behavioral features are extracted in a heterogeneous network using the HIN2Vec method of network embedding. The results showed that LPIH2V obtains an AUC of 0.97 and ACC of 0.95 in the 5-fold cross-validation test. The model successfully showed superiority and good generalization ability. Compared to other models, LPIH2V not only extracts attribute characteristics by similarity, but also acquires behavior properties by meta-path wandering in heterogeneous networks. LPIH2V would be beneficial in forecasting interactions between lncRNA and protein.

Predicting lncRNA-protein interactions with bipartite graph embedding and deep graph neural networks

Background: Long non-coding RNAs (lncRNAs) play crucial roles in numerous biological processes. Investigation of the lncRNA-protein interaction contributes to discovering the undetected molecular functions of lncRNAs. In recent years, increasingly computational approaches have substituted the traditional time-consuming experiments utilized to crack the possible unknown associations. However, significant explorations of the heterogeneity in association prediction between lncRNA and protein are inadequate. It remains challenging to integrate the heterogeneity of lncRNA-protein interactions with graph neural network algorithms. Methods: In this paper, we constructed a deep architecture based on GNN called BiHo-GNN, which is the first to integrate the properties of homogeneous with heterogeneous networks through bipartite graph embedding. Different from previous research, BiHo-GNN can capture the mechanism of molecular association by the data encoder of heterogeneous networks. Meanwhile, we design the process of mutual optimization between homogeneous and heterogeneous networks, which can promote the robustness of BiHo-GNN. Results: We collected four datasets for predicting lncRNA-protein interaction and compared the performance of current prediction models on benchmarking dataset. In comparison with the performance of other models, BiHo-GNN outperforms existing bipartite graph-based methods. Conclusion: Our BiHo-GNN integrates the bipartite graph with homogeneous graph networks. Based on this model structure, the lncRNA-protein interactions and potential associations can be predicted and discovered accurately.

Predicting potential interactions between lncRNAs and proteins via combined graph auto-encoder methods

Long noncoding RNA (lncRNA) is a kind of noncoding RNA with a length of more than 200 nucleotide units. Numerous research studies have proven that although lncRNAs cannot be directly translated into proteins, lncRNAs still play an important role in human growth processes by interacting with proteins. Since traditional biological experiments often require a lot of time and material costs to explore potential lncRNA-protein interactions (LPI), several computational models have been proposed for this task. In this study, we introduce a novel deep learning method known as combined graph auto-encoders (LPICGAE) to predict potential human LPIs. First, we apply a variational graph auto-encoder to learn the low dimensional representations from the high-dimensional features of lncRNAs and proteins. Then the graph auto-encoder is used to reconstruct the adjacency matrix for inferring potential interactions between lncRNAs and proteins. Finally, we minimize the loss of the two processes alternately to gain the final predicted interaction matrix. The result in 5-fold cross-validation experiments illustrates that our method achieves an average area under receiver operating characteristic curve of 0.974 and an average accuracy of 0.985, which is better than those of existing six state-of-the-art computational methods. We believe that LPICGAE can help researchers to gain more potential relationships between lncRNAs and proteins effectively.

Predicting lncRNA-disease associations based on combining selective similarity matrix fusion and bidirectional linear neighborhood label propagation

Recent studies have revealed that long noncoding RNAs (lncRNAs) are closely linked to several human diseases, providing new opportunities for their use in detection and therapy. Many graph propagation and similarity fusion approaches can be used for predicting potential lncRNA-disease associations. However, existing similarity fusion approaches suffer from noise and self-similarity loss in the fusion process. To address these problems, a new prediction approach, termed SSMF-BLNP, based on organically combining selective similarity matrix fusion (SSMF) and bidirectional linear neighborhood label propagation (BLNP), is proposed in this paper to predict lncRNA-disease associations. In SSMF, self-similarity networks of lncRNAs and diseases are obtained by selective preprocessing and nonlinear iterative fusion. The fusion process assigns weights to each initial similarity network and introduces a unit matrix that can reduce noise and compensate for the loss of self-similarity. In BLNP, the initial lncRNA-disease associations are employed in both lncRNA and disease directions as label information for linear neighborhood label propagation. The propagation was then performed on the self-similarity network obtained from SSMF to derive the scoring matrix for predicting the relationships between lncRNAs and diseases. Experimental results showed that SSMF-BLNP performed better than seven other state of-the-art approaches. Furthermore, a case study demonstrated up to 100% and 80% accuracy in 10 lncRNAs associated with hepatocellular carcinoma and 10 lncRNAs associated with renal cell carcinoma, respectively. The source code and datasets used in this paper are available at: https://github.com/RuiBingo/SSMF-BLNP.

A GHKNN model based on the physicochemical property extraction method to identify SNARE proteins

There is a great deal of importance to SNARE proteins, and their absence from function can lead to a variety of diseases. The SNARE protein is known as a membrane fusion protein, and it is crucial for mediating vesicle fusion. The identification of SNARE proteins must therefore be conducted with an accurate method. Through extensive experiments, we have developed a model based on graph-regularized k-local hyperplane distance nearest neighbor model (GHKNN) binary classification. In this, the model uses the physicochemical property extraction method to extract protein sequence features and the SMOTE method to upsample protein sequence features. The combination achieves the most accurate performance for identifying all protein sequences. Finally, we compare the model based on GHKNN binary classification with other classifiers and measure them using four different metrics: SN, SP, ACC, and MCC. In experiments, the model performs significantly better than other classifiers.

WLLP: A weighted reconstruction-based linear label propagation algorithm for predicting potential therapeutic agents for COVID-19

The global coronavirus disease 2019 (COVID-19) pandemic caused by the severe acute respiratory syndrome coronavirus-2 (SARS-CoV) has led to a huge health and economic crises. However, the research required to develop new drugs and vaccines is very expensive in terms of labor, money, and time. Owing to recent advances in data science, drug-repositioning technologies have become one of the most promising strategies available for developing effective treatment options. Using the previously reported human drug virus database (HDVD), we proposed a model to predict possible drug regimens based on a weighted reconstruction-based linear label propagation algorithm (WLLP). For the drug–virus association matrix, we used the weighted K-nearest known neighbors method for preprocessing and label propagation of the network based on the linear neighborhood similarity of drugs and viruses to obtain the final prediction results. In the framework of 10 times 10-fold cross-validated area under the receiver operating characteristic (ROC) curve (AUC), WLLP exhibited excellent performance with an AUC of 0.8828 ± 0.0037 and an area under the precision-recall curve of 0.5277 ± 0.0053, outperforming the other four models used for comparison. We also predicted effective drug regimens against SARS-CoV-2, and this case study showed that WLLP can be used to suggest potential drugs for the treatment of COVID-19.

Finding lncRNA-Protein Interactions Based on Deep Learning With Dual-Net Neural Architecture

The identification of lncRNA-protein interactions (LPIs) is important to understand the biological functions and molecular mechanisms of lncRNAs. However, most computational models are evaluated on a unique dataset, thereby resulting in prediction bias. Furthermore, previous models have not uncovered potential proteins (or lncRNAs) interacting with a new lncRNA (or protein). Finally, the performance of these models can be improved. In this study, we develop a Deep Learning framework with Dual-net Neural architecture to find potential LPIs (LPI-DLDN). First, five LPI datasets are collected. Second, the features of lncRNAs and proteins are extracted by Pyfeat and BioTriangle, respectively. Third, these features are concatenated as a vector after dimension reduction. Finally, a deep learning model with dual-net neural architecture is designed to classify lncRNA-protein pairs. LPI-DLDN is compared with six state-of-the-art LPI prediction methods (LPI-XGBoost, LPI-HeteSim, LPI-NRLMF, PLIPCOM, LPI-CNNCP, and Capsule-LPI) under four cross validations. The results demonstrate the powerful LPI classification performance of LPI-DLDN. Case study analyses show that there may be interactions between RP11-439E19.10 and Q15717, and between RP11-196G18.22 and Q9NUL5. The novelty of LPI-DLDN remains, integrating various biological features, designing a novel deep learning-based LPI identification framework, and selecting the optimal LPI feature subset based on feature importance ranking.

Top-k Self-Adaptive Contrast Sequential Pattern Mining

For sequence classification, an important issue is to find discriminative features, where sequential pattern mining (SPM) is often used to find frequent patterns from sequences as features. To improve classification accuracy and pattern interpretability, contrast pattern mining emerges to discover patterns with high-contrast rates between different categories. To date, existing contrast SPM methods face many challenges, including excessive parameter selection and inefficient occurrences counting. To tackle these issues, this article proposes a top- k self-adaptive contrast SPM, which adaptively adjusts the gap constraints to find top- k self-adaptive contrast patterns (SCPs) from positive and negative sequences. One of the key tasks of the mining problem is to calculate the support (the number of occurrences) of a pattern in each sequence. To support efficient counting, we store all occurrences of a pattern in a special array in a Nettree, an extended tree structure with multiple roots and multiple parents. We employ the array to calculate the occurrences of all its superpatterns with one-way scanning to avoid redundant calculation. Meanwhile, because the contrast SPM problem does not satisfy the Apriori property, we propose Zero and Less strategies to prune candidate patterns and a Contrast-first mining strategy to select patterns with the highest contrast rate as the prefix subpattern and calculate the contrast rate of all its superpatterns. Experiments validate the efficiency of the proposed algorithm and show that contrast patterns significantly outperform frequent patterns for sequence classification. The algorithms and datasets can be downloaded from https://github.com/wuc567/Pattern-Mining/tree/master/SCP-Miner.

Artificial intelligence methods enhance the discovery of RNA interactions

Understanding how RNAs interact with proteins, RNAs, or other molecules remains a challenge of main interest in biology, given the importance of these complexes in both normal and pathological cellular processes. Since experimental datasets are starting to be available for hundreds of functional interactions between RNAs and other biomolecules, several machine learning and deep learning algorithms have been proposed for predicting RNA-RNA or RNA-protein interactions. However, most of these approaches were evaluated on a single dataset, making performance comparisons difficult. With this review, we aim to summarize recent computational methods, developed in this broad research area, highlighting feature encoding and machine learning strategies adopted. Given the magnitude of the effect that dataset size and quality have on performance, we explored the characteristics of these datasets. Additionally, we discuss multiple approaches to generate datasets of negative examples for training. Finally, we describe the best-performing methods to predict interactions between proteins and specific classes of RNA molecules, such as circular RNAs (circRNAs) and long non-coding RNAs (lncRNAs), and methods to predict RNA-RNA or RNA-RBP interactions independently of the RNA type.

Predicting ncRNA-protein interactions based on dual graph convolutional network and pairwise learning

Noncoding RNAs (ncRNAs) have recently attracted considerable attention due to their key roles in biology. The ncRNA-proteins interaction (NPI) is often explored to reveal some biological activities that ncRNA may affect, such as biological traits, diseases, etc. Traditional experimental methods can accomplish this work but are often labor-intensive and expensive. Machine learning and deep learning methods have achieved great success by exploiting sufficient sequence or structure information. Graph Neural Network (GNN)-based methods consider the topology in ncRNA-protein graphs and perform well on tasks like NPI prediction. Based on GNN, some pairwise constraint methods have been developed to apply on homogeneous networks, but not used for NPI prediction on heterogeneous networks. In this paper, we construct a pairwise constrained NPI predictor based on dual Graph Convolutional Network (GCN) called NPI-DGCN. To our knowledge, our method is the first to train a heterogeneous graph-based model using a pairwise learning strategy. Instead of binary classification, we use a rank layer to calculate the score of an ncRNA-protein pair. Moreover, our model is the first to predict NPIs on the ncRNA-protein bipartite graph rather than the homogeneous graph. We transform the original ncRNA-protein bipartite graph into two homogenous graphs on which to explore second-order implicit relationships. At the same time, we model direct interactions between two homogenous graphs to explore explicit relationships. Experimental results on the four standard datasets indicate that our method achieves competitive performance with other state-of-the-art methods. And the model is available at https://github.com/zhuoninnin1992/NPIPredict.

Multi-feature Fusion Method Based on Linear Neighborhood Propagation Predict Plant LncRNA-Protein Interactions

Long non-coding RNAs (lncRNAs) have attracted extensive attention due to their important roles in various biological processes, among which lncRNA-protein interaction plays an important regulatory role in plant immunity and life activities. Laboratory methods are time consuming and labor-intensive, so that many computational methods have gradually emerged as auxiliary tools to assist relevant research. However, there are relatively few methods to predict lncRNA-protein interaction of plant. Due to the lack of experimentally verified interactions data, there is an imbalance between known and unknown interaction samples in plant data sets. In this study, a multi-feature fusion method based on linear neighborhood propagation is developed to predict plant unobserved lncRNA-protein interaction pairs through known interaction pairs, called MPLPLNP. The linear neighborhood similarity of the feature space is calculated and the results are predicted by label propagation. Meanwhile, multiple feature training is integrated to better explore the potential interaction information in the data. The experimental results show that the proposed multi-feature fusion method can improve the performance of the model, and is superior to other state-of-the-art approaches. Moreover, the proposed approach has better performance and generalization ability on various plant datasets, which is expected to facilitate the related research of plant molecular biology.

Seq-BEL: Sequence-Based Ensemble Learning for Predicting Virus-Human Protein-Protein Interaction

Infectious diseases are currently the most important and widespread health problem, and identifying viral infection mechanisms is critical for controlling diseases caused by highly infectious viruses. Because of the lack of non-interactive protein pairs and serious imbalance between positive and negative sample ratios, the supervised learning algorithm is not suitable for prediction. At the same time, due to the lack of information on viral proteins and significant dissimilarity in sequence, some ensemble learning models have poor generalization ability. In this paper, we propose a Sequence-Based Ensemble Learning (Seq-BEL) method to predict the potential virus-human PPIs. Specifically, based on the amino acid sequence of proteins and the currently known virus-human PPI network, Seq-BEL calculates various features and similarities of human proteins and viral proteins, and then combines these similarities and features to score the potential of virus-human PPIs. The computational results show that Seq-BEL achieves success in predicting potential virus-human PPIs and outperforms other state-of-the-art methods. More importantly, Seq-BEL also has good predictive performance for new human proteins and new viral proteins. In addition, the model has the advantages of strong robustness and good generalization ability, and can be used as an effective tool for virus-human PPI prediction.

Predicting multiple types of MicroRNA-disease associations based on tensor factorization and label propagation

MicroRNAs (miRNAs) play important regulatory roles in the pathogenesis and progression of diseases. Most existing bioinformatics methods only study miRNA-disease binary association prediction. However, there are many types of associations between miRNA and disease. In addition, the miRNA-disease-type association dataset has inherent noise and incompleteness. In this paper, a novel method based on tensor factorization and label propagation (TFLP) is proposed to alleviate the above problems. First, as an effective tensor factorization method, tensor robust principal component analysis (TRPCA) is applied to the original multiple-type miRNA-disease associations to obtain a clean and complete low-rank prediction tensor. Second, the Gaussian interaction profile (GIP) kernel is used to describe the similarity of disease pairs and the similarity of miRNA pairs. Then, they are combined with disease semantic similarity and miRNA functional similarity to obtain an integrated disease similarity network and an integrated miRNA similarity network, respectively. Finally, the low-rank association tensor and the biological similarity as auxiliary information are introduced into label propagation. The prediction performance of the algorithm is improved by iterative propagation of labeled information to unlabeled samples. Extensive experiments reveal that the proposed TFLP method outperforms other state-of-the-art methods for predicting multiple types of miRNA-disease associations. The data and source codes are available at https://github.com/nayu0419/TFLP.

MILNP: Plant lncRNA-miRNA Interaction Prediction Based on Improved Linear Neighborhood Similarity and Label Propagation

Knowledge of the interactions between long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) is the basis of understanding various biological activities and designing new drugs. Previous computational methods for predicting lncRNA-miRNA interactions lacked for plants, and they suffer from various limitations that affect the prediction accuracy and their applicability. Research on plant lncRNA-miRNA interactions is still in its infancy. In this paper, we propose an accurate predictor, MILNP, for predicting plant lncRNA-miRNA interactions based on improved linear neighborhood similarity measurement and linear neighborhood propagation algorithm. Specifically, we propose a novel similarity measure based on linear neighborhood similarity from multiple similarity profiles of lncRNAs and miRNAs and derive more precise neighborhood ranges so as to escape the limits of the existing methods. We then simultaneously update the lncRNA-miRNA interactions predicted from both similarity matrices based on label propagation. We comprehensively evaluate MILNP on the latest plant lncRNA-miRNA interaction benchmark datasets. The results demonstrate the superior performance of MILNP than the most up-to-date methods. What's more, MILNP can be leveraged for isolated plant lncRNAs (or miRNAs). Case studies suggest that MILNP can identify novel plant lncRNA-miRNA interactions, which are confirmed by classical tools. The implementation is available on https://github.com/HerSwain/gra/tree/MILNP.

RLF-LPI: An ensemble learning framework using sequence information for predicting lncRNA-protein interaction based on AE-ResLSTM and fuzzy decision

Long non-coding RNAs (lncRNAs) play a regulatory role in many biological cells, and the recognition of lncRNA-protein interactions is helpful to reveal the functional mechanism of lncRNAs. Identification of lncRNA-protein interaction by biological techniques is costly and time-consuming. Here, an ensemble learning framework, RLF-LPI is proposed, to predict lncRNA-protein interactions. The RLF-LPI of the residual LSTM autoencoder module with fusion attention mechanism can extract the potential representation of features and capture the dependencies between sequences and structures by k-mer method. Finally, the relationship between lncRNA and protein is learned through the method of fuzzy decision. The experimental results show that the ACC of RLF-LPI is 0.912 on ATH948 dataset and 0.921 on ZEA22133 dataset. Thus, it is demonstrated that our proposed method performed better in predicting lncRNA-protein interaction than other methods.

EnANNDeep: An Ensemble-based lncRNA-protein Interaction Prediction Framework with Adaptive k-Nearest Neighbor Classifier and Deep Models

lncRNA-protein interactions (LPIs) prediction can deepen the understanding of many important biological processes. Artificial intelligence methods have reported many possible LPIs. However, most computational techniques were evaluated mainly on one dataset, which may produce prediction bias. More importantly, they were validated only under cross validation on lncRNA-protein pairs, and did not consider the performance under cross validations on lncRNAs and proteins, thus fail to search related proteins/lncRNAs for a new lncRNA/protein. Under an ensemble learning framework (EnANNDeep) composed of adaptive k-nearest neighbor classifier and Deep models, this study focuses on systematically finding underlying linkages between lncRNAs and proteins. First, five LPI-related datasets are arranged. Second, multiple source features are integrated to depict an lncRNA-protein pair. Third, adaptive k-nearest neighbor classifier, deep neural network, and deep forest are designed to score unknown lncRNA-protein pairs, respectively. Finally, interaction probabilities from the three predictors are integrated based on a soft voting technique. In comparing to five classical LPI identification models (SFPEL, PMDKN, CatBoost, PLIPCOM, and LPI-SKF) under fivefold cross validations on lncRNAs, proteins, and LPIs, EnANNDeep computes the best average AUCs of 0.8660, 0.8775, and 0.9166, respectively, and the best average AUPRs of 0.8545, 0.8595, and 0.9054, respectively, indicating its superior LPI prediction ability. Case study analyses indicate that SNHG10 may have dense linkage with Q15717. In the ensemble framework, adaptive k-nearest neighbor classifier can separately pick the most appropriate k for each query lncRNA-protein pair. More importantly, deep models including deep neural network and deep forest can effectively learn the representative features of lncRNAs and proteins.

PRIP: A Protein-RNA Interface Predictor Based on Semantics of Sequences

RNA–protein interactions play an indispensable role in many biological processes. Growing evidence has indicated that aberration of the RNA–protein interaction is associated with many serious human diseases. The precise and quick detection of RNA–protein interactions is crucial to finding new functions and to uncovering the mechanism of interactions. Although many methods have been presented to recognize RNA-binding sites, there is much room left for the improvement of predictive accuracy. We present a sequence semantics-based method (called PRIP) for predicting RNA-binding interfaces. The PRIP extracted semantic embedding by pre-training the Word2vec with the corpus. Extreme gradient boosting was employed to train a classifier. The PRIP obtained a SN of 0.73 over the five-fold cross validation and a SN of 0.67 over the independent test, outperforming the state-of-the-art methods. Compared with other methods, this PRIP learned the hidden relations between words in the context. The analysis of the semantics relationship implied that the semantics of some words were specific to RNA-binding interfaces. This method is helpful to explore the mechanism of RNA–protein interactions from a semantics point of view.

Predicting lncRNA–Protein Interactions by Heterogenous Network Embedding

lncRNA–protein interactions play essential roles in a variety of cellular processes. However, the experimental methods for systematically mapping of lncRNA–protein interactions remain time-consuming and expensive. Therefore, it is urgent to develop reliable computational methods for predicting lncRNA–protein interactions. In this study, we propose a computational method called LncPNet to predict potential lncRNA–protein interactions by embedding an lncRNA–protein heterogenous network. The experimental results indicate that LncPNet achieves promising performance on benchmark datasets extracted from the NPInter database with an accuracy of 0.930 and area under ROC curve (AUC) of 0.971. In addition, we further compare our method with other eight state-of-the-art methods, and the results illustrate that our method achieves superior prediction performance. LncPNet provides an effective method via a new perspective of representing lncRNA–protein heterogenous network, which will greatly benefit the prediction of lncRNA–protein interactions.

Hypergraph-based logistic matrix factorization for metabolite-disease interaction prediction

MOTIVATION

Function-related metabolites, the terminal products of the cell regulation, show a close association with complex diseases. The identification of disease-related metabolites is critical to the diagnosis, prevention and treatment of diseases. However, most existing computational approaches build networks by calculating pairwise relationships, which is inappropriate for mining higher-order relationships.

RESULTS

In this study, we presented a novel approach with hypergraph-based logistic matrix factorization, HGLMF, to predict the potential interactions between metabolites and disease. First, the molecular structures and gene associations of metabolites and the hierarchical structures and GO functional annotations of diseases were extracted to build various similarity measures of metabolites and diseases. Next, the kernel neighborhood similarity of metabolites (or diseases) was calculated according to the completed interactive network. Second, multiple networks of metabolites and diseases were fused, respectively, and the hypergraph structures of metabolites and diseases were built. Finally, a logistic matrix factorization based on hypergraph was proposed to predict potential metabolite-disease interactions. In computational experiments, HGLMF accurately predicted the metabolite-disease interaction, and performed better than other state-of-the-art methods. Moreover, HGLMF could be used to predict new metabolites (or diseases). As suggested from the case studies, the proposed method could discover novel disease-related metabolites, which has been confirmed in existing studies.

AVAILABILITY AND IMPLEMENTATION

The codes and dataset are available at: https://github.com/Mayingjun20179/HGLMF.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

LPI-EnEDT: an ensemble framework with extra tree and decision tree classifiers for imbalanced lncRNA-protein interaction data classification

BACKGROUND

Long noncoding RNAs (lncRNAs) have dense linkages with various biological processes. Identifying interacting lncRNA-protein pairs contributes to understand the functions and mechanisms of lncRNAs. Wet experiments are costly and time-consuming. Most computational methods failed to observe the imbalanced characterize of lncRNA-protein interaction (LPI) data. More importantly, they were measured based on a unique dataset, which produced the prediction bias.

RESULTS

In this study, we develop an Ensemble framework (LPI-EnEDT) with Extra tree and Decision Tree classifiers to implement imbalanced LPI data classification. First, five LPI datasets are arranged. Second, lncRNAs and proteins are separately characterized based on Pyfeat and BioTriangle and concatenated as a vector to represent each lncRNA-protein pair. Finally, an ensemble framework with Extra tree and decision tree classifiers is developed to classify unlabeled lncRNA-protein pairs. The comparative experiments demonstrate that LPI-EnEDT outperforms four classical LPI prediction methods (LPI-BLS, LPI-CatBoost, LPI-SKF, and PLIPCOM) under cross validations on lncRNAs, proteins, and LPIs. The average AUC values on the five datasets are 0.8480, 0,7078, and 0.9066 under the three cross validations, respectively. The average AUPRs are 0.8175, 0.7265, and 0.8882, respectively. Case analyses suggest that there are underlying associations between HOTTIP and Q9Y6M1, NRON and Q15717.

CONCLUSIONS

Fusing diverse biological features of lncRNAs and proteins and exploiting an ensemble learning model with Extra tree and decision tree classifiers, this work focus on imbalanced LPI data classification as well as interaction information inference for a new lncRNA (or protein).

LPI-HyADBS: a hybrid framework for lncRNA-protein interaction prediction integrating feature selection and classification

Background

Long noncoding RNAs (lncRNAs) have dense linkages with a plethora of important cellular activities. lncRNAs exert functions by linking with corresponding RNA-binding proteins. Since experimental techniques to detect lncRNA-protein interactions (LPIs) are laborious and time-consuming, a few computational methods have been reported for LPI prediction. However, computation-based LPI identification methods have the following limitations: (1) Most methods were evaluated on a single dataset, and researchers may thus fail to measure their generalization ability. (2) The majority of methods were validated under cross validation on lncRNA-protein pairs, did not investigate the performance under other cross validations, especially for cross validation on independent lncRNAs and independent proteins. (3) lncRNAs and proteins have abundant biological information, how to select informative features need to further investigate.

Results

Under a hybrid framework (LPI-HyADBS) integrating feature selection based on AdaBoost, and classification models including deep neural network (DNN), extreme gradient Boost (XGBoost), and SVM with a penalty Coefficient of misclassification (C-SVM), this work focuses on finding new LPIs. First, five datasets are arranged. Each dataset contains lncRNA sequences, protein sequences, and an LPI network. Second, biological features of lncRNAs and proteins are acquired based on Pyfeat. Third, the obtained features of lncRNAs and proteins are selected based on AdaBoost and concatenated to depict each LPI sample. Fourth, DNN, XGBoost, and C-SVM are used to classify lncRNA-protein pairs based on the concatenated features. Finally, a hybrid framework is developed to integrate the classification results from the above three classifiers. LPI-HyADBS is compared to six classical LPI prediction approaches (LPI-SKF, LPI-NRLMF, Capsule-LPI, LPI-CNNCP, LPLNP, and LPBNI) on five datasets under 5-fold cross validations on lncRNAs, proteins, lncRNA-protein pairs, and independent lncRNAs and independent proteins. The results show LPI-HyADBS has the best LPI prediction performance under four different cross validations. In particular, LPI-HyADBS obtains better classification ability than other six approaches under the constructed independent dataset. Case analyses suggest that there is relevance between ZNF667-AS1 and Q15717.

Conclusions

Integrating feature selection approach based on AdaBoost, three classification techniques including DNN, XGBoost, and C-SVM, this work develops a hybrid framework to identify new linkages between lncRNAs and proteins.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04485-x.

Prediction of Hormone-Binding Proteins Based on K-mer Feature Representation and Naive Bayes

Hormone binding protein (HBP) is a soluble carrier protein that interacts selectively with different types of hormones and has various effects on the body's life activities. HBPs play an important role in the growth process of organisms, but their specific role is still unclear. Therefore, correctly identifying HBPs is the first step towards understanding and studying their biological function. However, due to their high cost and long experimental period, it is difficult for traditional biochemical experiments to correctly identify HBPs from an increasing number of proteins, so the real characterization of HBPs has become a challenging task for researchers. To measure the effectiveness of HBPs, an accurate and reliable prediction model for their identification is desirable. In this paper, we construct the prediction model HBP_NB. First, HBPs data were collected from the UniProt database, and a dataset was established. Then, based on the established high-quality dataset, the k-mer (K = 3) feature representation method was used to extract features. Second, the feature selection algorithm was used to reduce the dimensionality of the extracted features and select the appropriate optimal feature set. Finally, the selected features are input into Naive Bayes to construct the prediction model, and the model is evaluated by using 10-fold cross-validation. The final results were 95.45% accuracy, 94.17% sensitivity and 96.73% specificity. These results indicate that our model is feasible and effective.

NegStacking: Drug-Target Interaction Prediction Based on Ensemble Learning and Logistic Regression

Drug-target interactions (DTIs) identification is an important issue of drug research, and many methods proposed to predict potential DTIs based on machine learning treat it as a binary classification problem. However, the number of known interacting drug-target pairs (positive samples) is far less than that of non-interacting pairs (negative samples). Most methods do not utilize these large numbers of negative samples sufficiently, which limits their prediction performance. To address this problem, we proposed a stacking framework named NegStacking. First, it uses sampling to obtain multiple completely different negative sample sets. Then, each weak learner is trained with a different negative sample set and the same positive sample set, and the logistic regression (LR) is used as a meta-learner to adaptively combine these weak learners. Moreover, in the training process, feature subspacing and hyperparameter perturbation are applied to increase ensemble diversity. Finally, the trained model could be used to predict new samples. We compared NegStacking with other methods, and the experimental results show that our model is superior. NegStacking can improve the performance of predictive DTIs, and it has broad application prospects for improving the drug discovery process. The source code and datasets are available at https://github.com/Open-ss/NegStacking.

LGFC-CNN: Prediction of lncRNA-Protein Interactions by Using Multiple Types of Features through Deep Learning

Long noncoding RNA (lncRNA) plays a crucial role in many critical biological processes and participates in complex human diseases through interaction with proteins. Considering that identifying lncRNA–protein interactions through experimental methods is expensive and time-consuming, we propose a novel method based on deep learning that combines raw sequence composition features, hand-designed features and structure features, called LGFC-CNN, to predict lncRNA–protein interactions. The two sequence preprocessing methods and CNN modules (GloCNN and LocCNN) are utilized to extract the raw sequence global and local features. Meanwhile, we select hand-designed features by comparing the predictive effect of different lncRNA and protein features combinations. Furthermore, we obtain the structure features and unifying the dimensions through Fourier transform. In the end, the four types of features are integrated to comprehensively predict the lncRNA–protein interactions. Compared with other state-of-the-art methods on three lncRNA–protein interaction datasets, LGFC-CNN achieves the best performance with an accuracy of 94.14%, on RPI21850; an accuracy of 92.94%, on RPI7317; and an accuracy of 98.19% on RPI1847. The results show that our LGFC-CNN can effectively predict the lncRNA–protein interactions by combining raw sequence composition features, hand-designed features and structure features.

LPI-deepGBDT: a multiple-layer deep framework based on gradient boosting decision trees for lncRNA-protein interaction identification

Background

Long noncoding RNAs (lncRNAs) play important roles in various biological and pathological processes. Discovery of lncRNA–protein interactions (LPIs) contributes to understand the biological functions and mechanisms of lncRNAs. Although wet experiments find a few interactions between lncRNAs and proteins, experimental techniques are costly and time-consuming. Therefore, computational methods are increasingly exploited to uncover the possible associations. However, existing computational methods have several limitations. First, majority of them were measured based on one simple dataset, which may result in the prediction bias. Second, few of them are applied to identify relevant data for new lncRNAs (or proteins). Finally, they failed to utilize diverse biological information of lncRNAs and proteins.

Results

Under the feed-forward deep architecture based on gradient boosting decision trees (LPI-deepGBDT), this work focuses on classify unobserved LPIs. First, three human LPI datasets and two plant LPI datasets are arranged. Second, the biological features of lncRNAs and proteins are extracted by Pyfeat and BioProt, respectively. Thirdly, the features are dimensionally reduced and concatenated as a vector to represent an lncRNA–protein pair. Finally, a deep architecture composed of forward mappings and inverse mappings is developed to predict underlying linkages between lncRNAs and proteins. LPI-deepGBDT is compared with five classical LPI prediction models (LPI-BLS, LPI-CatBoost, PLIPCOM, LPI-SKF, and LPI-HNM) under three cross validations on lncRNAs, proteins, lncRNA–protein pairs, respectively. It obtains the best average AUC and AUPR values under the majority of situations, significantly outperforming other five LPI identification methods. That is, AUCs computed by LPI-deepGBDT are 0.8321, 0.6815, and 0.9073, respectively and AUPRs are 0.8095, 0.6771, and 0.8849, respectively. The results demonstrate the powerful classification ability of LPI-deepGBDT. Case study analyses show that there may be interactions between GAS5 and Q15717, RAB30-AS1 and O00425, and LINC-01572 and P35637.

Conclusions

Integrating ensemble learning and hierarchical distributed representations and building a multiple-layered deep architecture, this work improves LPI prediction performance as well as effectively probes interaction data for new lncRNAs/proteins.

A novel lncRNA-protein interaction prediction method based on deep forest with cascade forest structure

Long noncoding RNAs (lncRNAs) regulate many biological processes by interacting with corresponding RNA-binding proteins. The identification of lncRNA-protein Interactions (LPIs) is significantly important to well characterize the biological functions and mechanisms of lncRNAs. Existing computational methods have been effectively applied to LPI prediction. However, the majority of them were evaluated only on one LPI dataset, thereby resulting in prediction bias. More importantly, part of models did not discover possible LPIs for new lncRNAs (or proteins). In addition, the prediction performance remains limited. To solve with the above problems, in this study, we develop a Deep Forest-based LPI prediction method (LPIDF). First, five LPI datasets are obtained and the corresponding sequence information of lncRNAs and proteins are collected. Second, features of lncRNAs and proteins are constructed based on four-nucleotide composition and BioSeq2vec with encoder-decoder structure, respectively. Finally, a deep forest model with cascade forest structure is developed to find new LPIs. We compare LPIDF with four classical association prediction models based on three fivefold cross validations on lncRNAs, proteins, and LPIs. LPIDF obtains better average AUCs of 0.9012, 0.6937 and 0.9457, and the best average AUPRs of 0.9022, 0.6860, and 0.9382, respectively, for the three CVs, significantly outperforming other methods. The results show that the lncRNA FTX may interact with the protein P35637 and needs further validation.

Recent advances in predicting protein-lncRNA interactions using machine learning methods

Long non-coding RNAs (LncRNAs) are a type of RNA with little or no protein-coding ability. Their length is more than 200 nucleotides. A large number of studies have indicated that lncRNAs play a significant role in various biological processes, including chromatin organizations, epigenetic programmings, transcriptional regulations, post-transcriptional processing, and circadian mechanism at the cellular level. Since lncRNAs perform vast functions through their interactions with proteins, identifying lncRNA-protein interaction is crucial to the understandings of the lncRNA molecular functions. However, due to the high cost and time-consuming disadvantage of experimental methods, a variety of computational methods have emerged. Recently, many effective and novel machine learning methods have been developed. In general, these methods fall into two categories: semi-supervised learning methods and supervised learning methods. The latter category can be further classified into the deep learning-based method, the ensemble learning-based method, and the hybrid method. In this paper, we focused on supervised learning methods. We summarized the state-of-the-art methods in predicting lncRNA-protein interactions. Furthermore, the performance and the characteristics of different methods have also been compared in this work. Considering the limits of the existing models, we analyzed the problems and discussed future research potentials.

A Survey of Current Resources to Study lncRNA-Protein Interactions

Phenotypes are driven by regulated gene expression, which in turn are mediated by complex interactions between diverse biological molecules. Protein-DNA interactions such as histone and transcription factor binding are well studied, along with RNA-RNA interactions in short RNA silencing of genes. In contrast, lncRNA-protein interaction (LPI) mechanisms are comparatively unknown, likely directed by the difficulties in studying LPI. However, LPI are emerging as key interactions in epigenetic mechanisms, playing a role in development and disease. Their importance is further highlighted by their conservation across kingdoms. Hence, interest in LPI research is increasing. We therefore review the current state of the art in lncRNA-protein interactions. We specifically surveyed recent computational methods and databases which researchers can exploit for LPI investigation. We discovered that algorithm development is heavily reliant on a few generic databases containing curated LPI information. Additionally, these databases house information at gene-level as opposed to transcript-level annotations. We show that early methods predict LPI using molecular docking, have limited scope and are slow, creating a data processing bottleneck. Recently, machine learning has become the strategy of choice in LPI prediction, likely due to the rapid growth in machine learning infrastructure and expertise. While many of these methods have notable limitations, machine learning is expected to be the basis of modern LPI prediction algorithms.

Capsule-LPI: a LncRNA-protein interaction predicting tool based on a capsule network

BACKGROUND

Long noncoding RNAs (lncRNAs) play important roles in multiple biological processes. Identifying LncRNA-protein interactions (LPIs) is key to understanding lncRNA functions. Although some LPIs computational methods have been developed, the LPIs prediction problem remains challenging. How to integrate multimodal features from more perspectives and build deep learning architectures with better recognition performance have always been the focus of research on LPIs.

RESULTS

We present a novel multichannel capsule network framework to integrate multimodal features for LPI prediction, Capsule-LPI. Capsule-LPI integrates four groups of multimodal features, including sequence features, motif information, physicochemical properties and secondary structure features. Capsule-LPI is composed of four feature-learning subnetworks and one capsule subnetwork. Through comprehensive experimental comparisons and evaluations, we demonstrate that both multimodal features and the architecture of the multichannel capsule network can significantly improve the performance of LPI prediction. The experimental results show that Capsule-LPI performs better than the existing state-of-the-art tools. The precision of Capsule-LPI is 87.3%, which represents a 1.7% improvement. The F-value of Capsule-LPI is 92.2%, which represents a 1.4% improvement.

CONCLUSIONS

This study provides a novel and feasible LPI prediction tool based on the integration of multimodal features and a capsule network. A webserver ( http://csbg-jlu.site/lpc/predict ) is developed to be convenient for users.

NPI-GNN: Predicting ncRNA-protein interactions with deep graph neural networks

Noncoding RNAs (ncRNAs) play crucial roles in many biological processes. Experimental methods for identifying ncRNA-protein interactions (NPIs) are always costly and time-consuming. Many computational approaches have been developed as alternative ways. In this work, we collected five benchmarking datasets for predicting NPIs. Based on these datasets, we evaluated and compared the prediction performances of existing machine-learning based methods. Graph neural network (GNN) is a recently developed deep learning algorithm for link predictions on complex networks, which has never been applied in predicting NPIs. We constructed a GNN-based method, which is called Noncoding RNA-Protein Interaction prediction using Graph Neural Networks (NPI-GNN), to predict NPIs. The NPI-GNN method achieved comparable performance with state-of-the-art methods in a 5-fold cross-validation. In addition, it is capable of predicting novel interactions based on network information and sequence information. We also found that insufficient sequence information does not affect the NPI-GNN prediction performance much, which makes NPI-GNN more robust than other methods. As far as we can tell, NPI-GNN is the first end-to-end GNN predictor for predicting NPIs. All benchmarking datasets in this work and all source codes of the NPI-GNN method have been deposited with documents in a GitHub repo (https://github.com/AshuiRUA/NPI-GNN).

A Fast Linear Neighborhood Similarity-Based Network Link Inference Method to Predict MicroRNA-Disease Associations

Increasing evidences revealed that microRNAs (miRNAs) play critical roles in important biological processes. The identification of disease-related miRNAs is critical to understand the molecular mechanisms of human diseases. Most existing computational methods require diverse features to predict miRNA-disease associations. However, diverse features are not available for all miRNAs or diseases. In addition, most methods can't predict links for miRNAs or diseases without association information. In this paper, we propose a fast linear neighborhood similarity-based network link inference method, named FLNSNLI, to predict miRNA-disease associations. First, known miRNA-disease associations are formulated as a bipartite network, and miRNAs (or diseases) are expressed as association profiles. Second, miRNA-miRNA similarity and disease-disease similarity are calculated by fast linear neighborhood similarity measure and association profiles. Third, the label propagation algorithm is respectively implemented on two sides to score candidate miRNA-disease associations. Finally, FLNSNLI adopts the weighted average strategy and makes predictions. Moreover, we develop a link complementing approach, and extend FLNSNLI to predict links for miRNAs (or diseases) without known associations. In computational experiments, FLNSNLI produces high-accuracy performances, and outperforms other state-of-the-art methods. More importantly, FLNSNLI requires less information but performs well. Case studies on three popular diseases show that FLNSNLI is useful for the microRNA-disease association prediction.

Feature extraction approaches for biological sequences: a comparative study of mathematical features

As consequence of the various genomic sequencing projects, an increasing volume of biological sequence data is being produced. Although machine learning algorithms have been successfully applied to a large number of genomic sequence-related problems, the results are largely affected by the type and number of features extracted. This effect has motivated new algorithms and pipeline proposals, mainly involving feature extraction problems, in which extracting significant discriminatory information from a biological set is challenging. Considering this, our work proposes a new study of feature extraction approaches based on mathematical features (numerical mapping with Fourier, entropy and complex networks). As a case study, we analyze long non-coding RNA sequences. Moreover, we separated this work into three studies. First, we assessed our proposal with the most addressed problem in our review, e.g. lncRNA and mRNA; second, we also validate the mathematical features in different classification problems, to predict the class of lncRNA, e.g. circular RNAs sequences; third, we analyze its robustness in scenarios with imbalanced data. The experimental results demonstrated three main contributions: first, an in-depth study of several mathematical features; second, a new feature extraction pipeline; and third, its high performance and robustness for distinct RNA sequence classification. Availability:  https://github.com/Bonidia/FeatureExtraction_BiologicalSequences.

DeepLPI: a multimodal deep learning method for predicting the interactions between lncRNAs and protein isoforms

BACKGROUND

Long non-coding RNAs (lncRNAs) regulate diverse biological processes via interactions with proteins. Since the experimental methods to identify these interactions are expensive and time-consuming, many computational methods have been proposed. Although these computational methods have achieved promising prediction performance, they neglect the fact that a gene may encode multiple protein isoforms and different isoforms of the same gene may interact differently with the same lncRNA.

RESULTS

In this study, we propose a novel method, DeepLPI, for predicting the interactions between lncRNAs and protein isoforms. Our method uses sequence and structure data to extract intrinsic features and expression data to extract topological features. To combine these different data, we adopt a hybrid framework by integrating a multimodal deep learning neural network and a conditional random field. To overcome the lack of known interactions between lncRNAs and protein isoforms, we apply a multiple instance learning (MIL) approach. In our experiment concerning the human lncRNA-protein interactions in the NPInter v3.0 database, DeepLPI improved the prediction performance by 4.7% in term of AUC and 5.9% in term of AUPRC over the state-of-the-art methods. Our further correlation analyses between interactive lncRNAs and protein isoforms also illustrated that their co-expression information helped predict the interactions. Finally, we give some examples where DeepLPI was able to outperform the other methods in predicting mouse lncRNA-protein interactions and novel human lncRNA-protein interactions.

CONCLUSION

Our results demonstrated that the use of isoforms and MIL contributed significantly to the improvement of performance in predicting lncRNA and protein interactions. We believe that such an approach would find more applications in predicting other functional roles of RNAs and proteins.