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

Abstract

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.

A parallel model of DenseCNN and ordered‐neuron LSTM for generic and species‐specific succinylation site prediction

“…Then, 10% of the obtained sequences were randomly selected as an independent testing set, with the remaining used as a training set. Because the sequence fragment data after cutting were considerably imbalanced, which would induce a preference for negative samples and lead to bias (Y. Li et al, 2021), we used random subsampling to construct balanced data sets (Table S1 of the Supporting Information Material).…”

Discovery and Validation of Clinically Relevant Long Non-Coding RNAs in Colorectal Cancer

“…Given that a patient’s prognosis is a strong determinant of the therapeutic action that follows, prognostic and clinicopathological testing is incredibly important in defining the clinical significance of lncRNAs [ 69 , 71 , 72 ].…”

“…The regulatory significance of target lncRNAs is also highly dependent on their binding partners and network interactions. Proteins and mRNAs that are coexpressed with lncRNA targets can be predicted through bioinformatic softwares, including RPIseq, lncPRO, lncBASE, and Capsule-LPI, but also through techniques such as RNA-Seq [ 72 , 73 , 74 , 75 ]. The expression profiles of these predicted partners in CRC can then be examined through Western blots, dual luciferase assay, and RNA immunoprecipitation/RNA pull down [ 76 , 77 ].…”

Artificial intelligence methods enhance the discovery of RNA interactions

“…Several datasets have been derived from NPInter2.0 by selecting subsets of interactions with characteristics of interest. More specifically, the most widely used non-structure-based dataset for the development and testing of RPI prediction models is a subset of this database (namely NPInter10412) first assembled by Suresh et al, (2015), and subsequently used in numerous other works (Li et al, 2021;Wang et al, 2021;Zhao et al, 2021). NPInter10412 contains 10,412 ncRNA-protein…”