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

Abstract

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.

HAC-Net: A Hybrid Attention-Based Convolutional Neural Network for Highly Accurate Protein–Ligand Binding Affinity Prediction

“…CNNs comprise a class of deep learning architectures where the model learns weights for multiple convolutional filters that scan over the input dataset, transforming it into an output feature map. Many CNNs for binding affinity prediction operate on dimensionality-reduced data and come in the form of either 1- or 2-dimensional CNNs. − The requirement of lower-dimensional data is removed by the use of 3-dimensional CNNs (3D-CNNs), which utilize a 3-dimensional voxel representation of protein–ligand complexes where each voxel corresponds to an atomic feature vector. Many groups have employed some form of 3D-CNN for binding affinity prediction. − There have also been successful efforts to predict binding affinity utilizing graph convolutional networks (GCNs). − In the case of GCNs, protein–ligand complexes are represented as graphs, where nodes usually correspond to atoms and edges are pathways for information transfer between pairs of nodes.…”

Deep Learning Approaches for lncRNA-Mediated Mechanisms: A Comprehensive Review of Recent Developments

“…The third group is characterized by models that use deep learning frameworks with different architectures or hybrid approaches. These include DeepLPI [ 60 ], DFRPI [ 61 ], LPI–deepGBDT [ 66 ], LPI–DLDN [ 67 ], LPI–HyADBS [ 68 ], and RLF–LPI [ 71 ]. These models demonstrated high performance due to their unique approaches.…”

“…BiHo-GNN, using bipartite graph embedding [58]; Capsule-LPI, a multichannel capsule network for lncRNA-protein interaction prediction [59]; DeepLPI, a multimodal deep learning method for lncRNA-protein isoform interactions [60]; DFRPI, deep autoencoder and marginal Fisher analysis [61]; EnANNDeep, ensemble-based framework with adaptive k-nearest neighbor for the lncRNA-protein interaction [62]; iEssLnc, graph neural network-based estimation of lncRNA gene essentiality [63];…”

A Survey of Current Resources to Study lncRNA-Protein Interactions

“…Only a few deep learning approaches exist: DeepBind [ 70 ], LPI-CNNCP (lncRNA-protein interactions convolutional neural network copy-padding trick) [ 71 ] and DeepLPI (deep lncRNA-protein interactions) [ 72 ]. DeepBind was one of the first applications of deep learning to predict nucleic acid–protein binding, and is applicable to LPI.…”