LPI-CNNCP: Prediction of lncRNA-protein interactions by using convolutional neural network with the copy-padding trick

A comprehensive survey on deep learning-based identification and predicting the interaction mechanism of long non-coding RNAs

Long noncoding RNAs (lncRNAs) have been discovered to be extensively involved in eukaryotic epigenetic, transcriptional, and post-transcriptional regulatory processes with the advancements in sequencing technology and genomics research. Therefore, they play crucial roles in the body's normal physiology and various disease outcomes. Presently, numerous unknown lncRNA sequencing data require exploration. Establishing deep learning-based prediction models for lncRNAs provides valuable insights for researchers, substantially reducing time and costs associated with trial and error and facilitating the disease-relevant lncRNA identification for prognosis analysis and targeted drug development as the era of artificial intelligence progresses. However, most lncRNA-related researchers lack awareness of the latest advancements in deep learning models and model selection and application in functional research on lncRNAs. Thus, we elucidate the concept of deep learning models, explore several prevalent deep learning algorithms and their data preferences, conduct a comprehensive review of recent literature studies with exemplary predictive performance over the past 5 years in conjunction with diverse prediction functions, critically analyze and discuss the merits and limitations of current deep learning models and solutions, while also proposing prospects based on cutting-edge advancements in lncRNA research.

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.

LPI-SKMSC: Predicting LncRNA-Protein Interactions with Segmented k-mer Frequencies and Multi-space Clustering

 Long noncoding RNAs (lncRNAs) have significant regulatory roles in gene expression. Interactions with proteins are one of the ways lncRNAs play their roles. Since experiments to determine lncRNA-protein interactions (LPIs) are expensive and time-consuming, many computational methods for predicting LPIs have been proposed as alternatives. In the LPIs prediction problem, there commonly exists the imbalance in the distribution of positive and negative samples. However, there are few existing methods that give specific consideration to this problem. In this paper, we proposed a new clustering-based LPIs prediction method using segmented k-mer frequencies and multi-space clustering (LPI-SKMSC). It was dedicated to handling the imbalance of positive and negative samples. We constructed segmented k-mer frequencies to obtain global and local features of lncRNA and protein sequences. Then, the multi-space clustering was applied to LPI-SKMSC. The convolutional neural network (CNN)-based encoders were used to map different features of a sample to different spaces. It used multiple spaces to jointly constrain the classification of samples. Finally, the distances between the output features of the encoder and the cluster center in each space were calculated. The sum of distances in all spaces was compared with the cluster radius to predict the LPIs. We performed cross-validation on 3 public datasets and LPI-SKMSC showed the best performance compared to other existing methods. Experimental results showed that LPI-SKMSC could predict LPIs more effectively when faced with imbalanced positive and negative samples. In addition, we illustrated that our model was better at uncovering potential lncRNA-protein interaction pairs.

RPI-EDLCN: An Ensemble Deep Learning Framework Based on Capsule Network for ncRNA-Protein Interaction Prediction

Noncoding RNAs (ncRNAs) play crucial roles in many cellular life activities by interacting with proteins. Identification of ncRNA-protein interactions (ncRPIs) is key to understanding the function of ncRNAs. Although a number of computational methods for predicting ncRPIs have been developed, the problem of predicting ncRPIs remains challenging. It has always been the focus of ncRPIs research to select suitable feature extraction methods and develop a deep learning architecture with better recognition performance. In this work, we proposed an ensemble deep learning framework, RPI-EDLCN, based on a capsule network (CapsuleNet) to predict ncRPIs. In terms of feature input, we extracted the sequence features, secondary structure sequence features, motif information, and physicochemical properties of ncRNA/protein. The sequence and secondary structure sequence features of ncRNA/protein are encoded by the conjoint k-mer method and then input into an ensemble deep learning model based on CapsuleNet by combining the motif information and physicochemical properties. In this model, the encoding features are processed by convolution neural network (CNN), deep neural network (DNN), and stacked autoencoder (SAE). Then the advanced features obtained from the processing are input into the CapsuleNet for further feature learning. Compared with other state-of-the-art methods under 5-fold cross-validation, the performance of RPI-EDLCN is the best, and the accuracy of RPI-EDLCN on RPI1807, RPI2241, and NPInter v2.0 data sets was 93.8%, 88.2%, and 91.9%, respectively. The results of the independent test indicated that RPI-EDLCN can effectively predict potential ncRPIs in different organisms. In addition, RPI-EDLCN successfully predicted hub ncRNAs and proteins in Mus musculus ncRNA-protein networks. Overall, our model can be used as an effective tool to predict ncRPIs and provides some useful guidance for future biological studies.

Prediction of LncRNA-protein Interactions Using Auto-Encoder, SE-ResNet Models and Transfer Learning

BACKGROUND

Long non-coding RNA (lncRNA) plays a crucial role in various biological processes, and mutations or imbalances of lncRNAs can lead to several diseases, including cancer, Prader-Willi syndrome, autism, Alzheimer's disease, cartilage-hair hypoplasia, and hearing loss. Understanding lncRNA-protein interactions (LPIs) is vital for elucidating basic cellular processes, human diseases, viral replication, transcription, and plant pathogen resistance. Despite the development of several LPI calculation methods, predicting LPI remains challenging, with the selection of variables and deep learning structure being the focus of LPI research.

METHODS

We propose a deep learning framework called AR-LPI, which extracts sequence and secondary structure features of proteins and lncRNAs. The framework utilizes an auto-encoder for feature extraction and employs SE-ResNet for prediction. Additionally, we apply transfer learning to the deep neural network SE-ResNet for predicting small-sample datasets.

RESULTS

Through comprehensive experimental comparison, we demonstrate that the AR-LPI architecture performs better in LPI prediction. Specifically, the accuracy of AR-LPI increases by 2.86% to 94.52%, while the F-value of AR-LPI increases by 2.71% to 94.73%.

CONCLUSION

Our experimental results show that the overall performance of AR-LPI is better than that of other LPI prediction tools.

iDHS-FFLG: Identifying DNase I Hypersensitive Sites by Feature Fusion and Local-Global Feature Extraction Network

The DNase I hypersensitive sites (DHSs) are active regions on chromatin that have been found to be highly sensitive to DNase I. These regions contain various cis-regulatory elements, including promoters, enhancers and silencers. Accurate identification of DHSs helps researchers better understand the transcriptional machinery of DNA and deepen the knowledge of functional DNA elements in non-coding sequences. Researchers have developed many methods based on traditional experiments and machine learning to identify DHSs. However, low prediction accuracy and robustness limit their application in genetics research. In this paper, a novel computational approach based on deep learning is proposed by feature fusion and local-global feature extraction network to identify DHSs in mouse, named iDHS-FFLG. First of all, multiple binary features of nucleotides are fused to better express sequence information. Then, a network consisting of the convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM) and self-attention mechanism is designed to extract local features and global contextual associations. In the end, the prediction module is applied to distinguish between DHSs and non-DHSs. The results of several experiments demonstrate the superior performances of iDHS-FFLG compared to the latest methods.

PmliHFM: Predicting Plant miRNA-lncRNA Interactions with Hybrid Feature Mining Network

Due to the crucial role of interactions between microRNAs (miRNAs) and long non-coding RNAs (lncRNAs) in biological processes, the study of their biological functions is necessary. So far, the various computational methods have been employed to make predictions of the miRNA-lncRNA interaction, which compensate for the inadequacy of biological experiments. However, the existing methods do not consider the differences between miRNA and lncRNA in feature extraction. In this paper, we propose a hybrid feature mining network, named PmliHFM, for predicting plant miRNA-lncRNA interactions. Firstly, miRNA and lncRNA with different sequence lengths are encoded by different encodings, which can reduce the loss of information caused by using the same coding approach. Then, a hybrid feature mining network is designed to adapt to different encoding methods and extract more useful feature information than a single network. Finally, an ensemble module is utilized to integrate the training results of the hybrid feature mining network, while a prediction module is employed to determine whether there are interactions. By testing on multiple test sets, PmliHFM outperforms several state-of-the-art approaches. The results show that the AUC of PmliHFM achieves 0.8[Formula: see text], 3.1[Formula: see text] and 0.4[Formula: see text] improvement respectively on three balanced datasets, and achieves 2.1[Formula: see text] and 1.8[Formula: see text] improvement respectively on two imbalanced datasets. These experiments demonstrate the feasibility of the proposed method.

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.

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.

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.

Long non-coding RNA and RNA-binding protein interactions in cancer: Experimental and machine learning approaches

Understanding the complex and specific roles played by non-coding RNAs (ncRNAs), which comprise the bulk of the genome, is important for understanding virtually every hallmark of cancer. This large group of molecules plays pivotal roles in key regulatory mechanisms in various cellular processes. Regulatory mechanisms, mediated by long non-coding RNA (lncRNA) and RNA-binding protein (RBP) interactions, are well documented in several types of cancer. Their effects are enabled through networks affecting lncRNA and RBP stability, RNA metabolism including N⁶-methyladenosine (m⁶A) and alternative splicing, subcellular localization, and numerous other mechanisms involved in cancer. In this review, we discuss the reciprocal interplay between lncRNAs and RBPs and their involvement in epigenetic regulation via histone modifications, as well as their key role in resistance to cancer therapy. Other aspects of RBPs including their structural domains, provide a deeper knowledge on how lncRNAs and RBPs interact and exert their biological functions. In addition, current state-of-the-art knowledge, facilitated by machine and deep learning approaches, unravels such interactions in better details to further enhance our understanding of the field, and the potential to harness RNA-based therapeutics as an alternative treatment modality for cancer are discussed.

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.

BoT-Net: a lightweight bag of tricks-based neural network for efficient LncRNA–miRNA interaction prediction

Background and objective:

Interactions of long non-coding ribonucleic acids (lncRNAs) with micro-ribonucleic acids (miRNAs) play an essential role in gene regulation, cellular metabolic, and pathological processes. Existing purely sequence based computational approaches lack robustness and efficiency mainly due to the high length variability of lncRNA sequences. Hence, the prime focus of the current study is to find optimal length trade-offs between highly flexible length lncRNA sequences.

Method

The paper at hand performs in-depth exploration of diverse copy padding, sequence truncation approaches, and presents a novel idea of utilizing only subregions of lncRNA sequences to generate fixed-length lncRNA sequences. Furthermore, it presents a novel bag of tricks-based deep learning approach “Bot-Net” which leverages a single layer long-short-term memory network regularized through DropConnect to capture higher order residue dependencies, pooling to retain most salient features, normalization to prevent exploding and vanishing gradient issues, learning rate decay, and dropout to regularize precise neural network for lncRNA–miRNA interaction prediction.

Results

BoT-Net outperforms the state-of-the-art lncRNA–miRNA interaction prediction approach by 2%, 8%, and 4% in terms of accuracy, specificity, and matthews correlation coefficient. Furthermore, a case study analysis indicates that BoT-Net also outperforms state-of-the-art lncRNA–protein interaction predictor on a benchmark dataset by accuracy of 10%, sensitivity of 19%, specificity of 6%, precision of 14%, and matthews correlation coefficient of 26%.

Conclusion

In the benchmark lncRNA–miRNA interaction prediction dataset, the length of the lncRNA sequence varies from 213 residues to 22,743 residues and in the benchmark lncRNA–protein interaction prediction dataset, lncRNA sequences vary from 15 residues to 1504 residues. For such highly flexible length sequences, fixed length generation using copy padding introduces a significant level of bias which makes a large number of lncRNA sequences very much identical to each other and eventually derail classifier generalizeability. Empirical evaluation reveals that within 50 residues of only the starting region of long lncRNA sequences, a highly informative distribution for lncRNA–miRNA interaction prediction is contained, a crucial finding exploited by the proposed BoT-Net approach to optimize the lncRNA fixed length generation process.

Availability:

BoT-Net web server can be accessed at https://sds_genetic_analysis.opendfki.de/lncmiRNA/.

Graphic Abstract

RASSF8-AS1 displays low expression in colorectal cancer and up-regulates RASSF8 to suppress cell invasion and migration

BACKGROUND

Colorectal cancer (CRC) is among the most prevalent cancers. Long non-coding RNAs (lncRNAs) are important participant in various cancers. Based on the literature, lncRNA RASSF8-AS1 inhibits laryngeal squamous cell carcinoma (LSCC) malignant progression. However, the role of RASSF8-AS1 in CRC remains unclear.

PURPOSE

This study centered on uncovering the role of RASSF8-AS1 and its related regulatory mechanisms in CRC cells.

METHODS

RT-qPCR and western blot were performed to examine the expression of target genes. Functional assays were conducted to determine the effect of target genes on the migration and invasion of CRC cells. Mechanism assays were also carried out to figure out the specific downstream mechanisms of RASSF8-AS1. In vivo assays were also involved.

RESULTS

The expression of RASSF8-AS1 and RASSF8 was positively correlated in CRC, and the two genes were down-regulated in CRC cells and tissues. Moreover, CRC cell invasion and migration as well as xenograft CRC tumor growth suppressed by RASSF8-AS1 overexpression were entirely recovered by RASSF8 knockdown or partially rescued by miR-33a-5p augment. As for the downstream mechanism, RASSF8-AS1 sponged miR-33a-5p to up-regulate RASSF8, or recruited HNRNPC to stabilize RASSF8 mRNA.

CONCLUSION

RASSF8-AS1 modulates miR-33a-5p/HNRNPC/RASSF8 axis to further impede CRC cell invasion and migration.

AVAILABILITY OF DATA

The research data is confidential.

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.

NPI-RGCNAE: Fast predicting ncRNA-protein interactions using the Relational Graph Convolutional Network Auto-Encoder

- ncRNAs play important roles in a variety of biological processes by interacting with RNA-binding proteins. Therefore, identifying ncRNA-protein interactions is important to understanding the biological functions of ncRNAs. Since experimental methods to determine ncRNA-protein interactions are always costly and time-consuming, computational methods have been proposed as alternative approaches. We developed a novel method NPI-RGCNAE (predicting ncRNA-Protein Interactions by the Relational Graph Convolutional Network Auto-Encoder). With a reliable negative sample selection strategy, we applied the Relational Graph Convolutional Network encoder and the DistMult decoder to predict ncRNA-protein interactions in an accurate and efficient way. By using the 5-fold cross-validation, we found that our method achieved a comparable performance to all state-of-the-art methods. Our method requires less than 10% training time of all state-of-the-art methods. It is a more efficient choice with large datasets in practice. All datasets and source codes of NPI-RGCNAE have been deposited in a public Github repository (https://github.com/Angelia0hh/NPI-RGCNAE).

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.

Accurate prediction of protein-ATP binding residues using position-specific frequency matrix

Knowledge of protein-ATP interaction can help for protein functional annotation and drug discovery. Accurately identifying protein-ATP binding residues is an important but challenging task to gain the knowledge of protein-ATP interactions, especially for the case where only protein sequence information is given. In this study, we propose a novel method, named DeepATPseq, to predict protein-ATP binding residues without using any information about protein three-dimension structure or sequence-derived structural information. In DeepATPseq, the HHBlits-generated position-specific frequency matrix (PSFM) profile is first employed to extract the feature information of each residue. Then, for each residue, the PSFM-based feature is fed into two prediction models, which are generated by the algorithms of deep convolutional neural network (DCNN) and support vector machine (SVM) separately. The final ATP-binding probability of the corresponding residue is calculated by the weighted sum of the outputted values of DCNN-based and SVM-based models. Experimental results on the independent validation data set demonstrate that DeepATPseq could achieve an accuracy of 77.71%, covering 57.42% of all ATP-binding residues, while achieving a Matthew's correlation coefficient value (0.655) that is significantly higher than that of existing sequence-based methods and comparable to that of the state-of-the-art structure-based predictors. Detailed data analysis show that the major advantage of DeepATPseq lies at the combination utilization of DCNN and SVM that helps dig out more discriminative information from the PSFM profiles. The online server and standalone package of DeepATPseq are freely available at: https://jun-csbio.github.io/DeepATPseq/for academic use.

EDLMFC: an ensemble deep learning framework with multi-scale features combination for ncRNA-protein interaction prediction

Background

Non-coding RNA (ncRNA) and protein interactions play essential roles in various physiological and pathological processes. The experimental methods used for predicting ncRNA–protein interactions are time-consuming and labor-intensive. Therefore, there is an increasing demand for computational methods to accurately and efficiently predict ncRNA–protein interactions.

Results

In this work, we presented an ensemble deep learning-based method, EDLMFC, to predict ncRNA–protein interactions using the combination of multi-scale features, including primary sequence features, secondary structure sequence features, and tertiary structure features. Conjoint k-mer was used to extract protein/ncRNA sequence features, integrating tertiary structure features, then fed into an ensemble deep learning model, which combined convolutional neural network (CNN) to learn dominating biological information with bi-directional long short-term memory network (BLSTM) to capture long-range dependencies among the features identified by the CNN. Compared with other state-of-the-art methods under five-fold cross-validation, EDLMFC shows the best performance with accuracy of 93.8%, 89.7%, and 86.1% on RPI1807, NPInter v2.0, and RPI488 datasets, respectively. The results of the independent test demonstrated that EDLMFC can effectively predict potential ncRNA–protein interactions from different organisms. Furtherly, EDLMFC is also shown to predict hub ncRNAs and proteins presented in ncRNA–protein networks of Mus musculus successfully.

Conclusions

In general, our proposed method EDLMFC improved the accuracy of ncRNA–protein interaction predictions and anticipated providing some helpful guidance on ncRNA functions research. The source code of EDLMFC and the datasets used in this work are available at https://github.com/JingjingWang-87/EDLMFC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04069-9.

Prediction of enhancer-promoter interactions using the cross-cell type information and domain adversarial neural network

BACKGROUND

Enhancer-promoter interactions (EPIs) play key roles in transcriptional regulation and disease progression. Although several computational methods have been developed to predict such interactions, their performances are not satisfactory when training and testing data from different cell lines. Currently, it is still unclear what extent a across cell line prediction can be made based on sequence-level information.

RESULTS

In this work, we present a novel Sequence-based method (called SEPT) to predict the enhancer-promoter interactions in new cell line by using the cross-cell information and Transfer learning. SEPT first learns the features of enhancer and promoter from DNA sequences with convolutional neural network (CNN), then designing the gradient reversal layer of transfer learning to reduce the cell line specific features meanwhile retaining the features associated with EPIs. When the locations of enhancers and promoters are provided in new cell line, SEPT can successfully recognize EPIs in this new cell line based on labeled data of other cell lines. The experiment results show that SEPT can effectively learn the latent import EPIs-related features between cell lines and achieves the best prediction performance in terms of AUC (the area under the receiver operating curves).

CONCLUSIONS

SEPT is an effective method for predicting the EPIs in new cell line. Domain adversarial architecture of transfer learning used in SEPT can learn the latent EPIs shared features among cell lines from all other existing labeled data. It can be expected that SEPT will be of interest to researchers concerned with biological interaction prediction.