Related Experiment Video
Updated: Nov 21, 2025
07:24
Identification of RNAs Engaged in Direct RNA-RNA Interaction with a Long Non-Coding RNA
Published on: July 9, 2021
2.6K
DeepLPI: a multimodal deep learning method for predicting the interactions between lncRNAs and protein isoforms
Dipan Shaw1, Hao Chen2, Minzhu Xie3
1Department of Computer Science and Engineering, University of California, Riverside, CA, 92521, USA. dshaw003@ucr.edu.
BMC Bioinformatics
|January 19, 2021
Summary
This study introduces DeepLPI, a novel computational method for predicting long non-coding RNA (lncRNA) and protein isoform interactions. DeepLPI improves prediction accuracy by integrating sequence, structure, and expression data, outperforming existing methods.
Area of Science:
- Computational Biology
- Genomics
- Bioinformatics
Background:
- Long non-coding RNAs (lncRNAs) play crucial roles in biological processes through interactions with proteins.
- Experimental identification of these interactions is costly and time-consuming.
- Existing computational methods often overlook the complexity of protein isoforms and their distinct interactions with lncRNAs.
Purpose of the Study:
- To develop a novel computational method, DeepLPI, for accurately predicting interactions between lncRNAs and specific protein isoforms.
- To leverage multimodal data, including sequence, structure, and expression, for enhanced prediction.
- To address the challenge of limited data for lncRNA-protein isoform interactions using a multiple instance learning (MIL) approach.
Main Methods:
- DeepLPI employs a hybrid framework combining a multimodal deep learning neural network and a conditional random field.
- It integrates intrinsic features from sequence and structure data with topological features from expression data.
- A multiple instance learning (MIL) approach is utilized to handle the scarcity of known lncRNA-protein isoform interactions.
Main Results:
- DeepLPI achieved a 4.7% improvement in AUC and a 5.9% improvement in AUPRC for human lncRNA-protein interactions compared to state-of-the-art methods.
- Correlation analyses confirmed that co-expression information between lncRNAs and protein isoforms aids in predicting their interactions.
- The method demonstrated superior performance in predicting mouse lncRNA-protein interactions and novel human interactions.
Conclusions:
- The integration of protein isoforms and the MIL approach significantly enhances the performance of lncRNA-protein interaction prediction.
- DeepLPI offers a promising advancement in understanding lncRNA-protein interactions.
- The developed approach has potential applications in predicting other functional roles of RNAs and proteins.
Related Concept Videos
02:26Protein Networks
4.3K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.3K
02:26Protein Networks
2.6K
2.6K
02:39lncRNA - Long Non-coding RNAs
9.4K
In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA...
9.4K
02:39lncRNA - Long Non-coding RNAs
3.1K
3.1K
02:04Protein-protein Interfaces
14.2K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
14.2K
01:19Interactions Between Signaling Pathways
6.9K
Signaling cascades usually lack linearity. Multiple pathways interact and regulate one another, allowing cells to integrate and respond to diverse environmental stimuli.
Convergence and divergence, and cross-talk between signaling pathways
Two distinct signaling pathways can converge on a single functional unit, which may either be a single protein or a complex of proteins. The response is either functionally distinct or synergistic between the two pathways but different from the response...
Convergence and divergence, and cross-talk between signaling pathways
Two distinct signaling pathways can converge on a single functional unit, which may either be a single protein or a complex of proteins. The response is either functionally distinct or synergistic between the two pathways but different from the response...
6.9K