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 int...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Molecular Biosciences |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmolb.2022.1000205/full |
| _version_ | 1811227066434060288 |
|---|---|
| author | G Pepe R Appierdo C Carrino F Ballesio M Helmer-Citterich PF Gherardini |
| author_facet | G Pepe R Appierdo C Carrino F Ballesio M Helmer-Citterich PF Gherardini |
| author_sort | G Pepe |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-12T09:36:16Z |
| format | Article |
| id | doaj.art-fc904e44499e4fdf8f2403b40ce418ba |
| institution | Directory Open Access Journal |
| issn | 2296-889X |
| language | English |
| last_indexed | 2024-04-12T09:36:16Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Molecular Biosciences |
| spelling | doaj.art-fc904e44499e4fdf8f2403b40ce418ba2022-12-22T03:38:14ZengFrontiers Media S.A.Frontiers in Molecular Biosciences2296-889X2022-10-01910.3389/fmolb.2022.10002051000205Artificial intelligence methods enhance the discovery of RNA interactionsG Pepe0R Appierdo1C Carrino2F Ballesio3M Helmer-Citterich4PF Gherardini5Department of Biology, University of Rome “Tor Vergata”, Rome, ItalyDepartment of Biology, University of Rome “Tor Vergata”, Rome, ItalyPhD Program in Cellular and Molecular Biology, Department of Biology, University of Rome “Tor Vergata”, Rome, ItalyPhD Program in Cellular and Molecular Biology, Department of Biology, University of Rome “Tor Vergata”, Rome, ItalyDepartment of Biology, University of Rome “Tor Vergata”, Rome, ItalyDepartment of Biology, University of Rome “Tor Vergata”, Rome, ItalyUnderstanding 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.https://www.frontiersin.org/articles/10.3389/fmolb.2022.1000205/fullRNARNA interaction predictorsnatural language processingdeep learningmachine learningembedding |
| spellingShingle | G Pepe R Appierdo C Carrino F Ballesio M Helmer-Citterich PF Gherardini Artificial intelligence methods enhance the discovery of RNA interactions Frontiers in Molecular Biosciences RNA RNA interaction predictors natural language processing deep learning machine learning embedding |
| title | Artificial intelligence methods enhance the discovery of RNA interactions |
| title_full | Artificial intelligence methods enhance the discovery of RNA interactions |
| title_fullStr | Artificial intelligence methods enhance the discovery of RNA interactions |
| title_full_unstemmed | Artificial intelligence methods enhance the discovery of RNA interactions |
| title_short | Artificial intelligence methods enhance the discovery of RNA interactions |
| title_sort | artificial intelligence methods enhance the discovery of rna interactions |
| topic | RNA RNA interaction predictors natural language processing deep learning machine learning embedding |
| url | https://www.frontiersin.org/articles/10.3389/fmolb.2022.1000205/full |
| work_keys_str_mv | AT gpepe artificialintelligencemethodsenhancethediscoveryofrnainteractions AT rappierdo artificialintelligencemethodsenhancethediscoveryofrnainteractions AT ccarrino artificialintelligencemethodsenhancethediscoveryofrnainteractions AT fballesio artificialintelligencemethodsenhancethediscoveryofrnainteractions AT mhelmercitterich artificialintelligencemethodsenhancethediscoveryofrnainteractions AT pfgherardini artificialintelligencemethodsenhancethediscoveryofrnainteractions |