RNA Secondary Structure Prediction Using a Genetic Algorithm with a Selection Method Based on Free Energy Value and Topological Index
Benedetti, G.
Show abstract
This paper presents a genetic algorithm designed to predict RNA secondary structures, which utilizes selection criteria based on free energy (fitness) and topological similarity. This approach represents structural information using a simple number, facilitating comparisons between foldings. The simplified graph representation identifies similarities between structures that have the same type of branches. The results demonstrate that the algorithm identifies the final secondary structure with the same level of precision as the commonly used dynamic programming, but with the advantage of producing more optimal structures with different topologies. This approach maintains high population diversity and allows for the exploration of many suboptimal structures in parallel, avoiding the possibility of getting stuck in a local minimum. This permits the investigation of not only the structure with the minimum free energy, but also of other low-energy structures with different topologies that are closer to the natural fold.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- SARS-CoV-2 protein structure and sequence mutations: evolutionary analysis and effects on virus variants SARS-CoV-2 protein structure and sequence mutations: 94%
- GenomeBits insight into omicron and delta variants of coronavirus pathogen 93%
- DeLUCS: Deep Learning for Unsupervised Clustering of DNA Sequences 93%
Similar papers in this journal
Similar papers in this journal
- SubFeat: Feature Subspacing Ensemble Classifier for Function Prediction of DNA, RNA and Protein Sequences 95%
- Computational study and design of effective siRNAs to silence structural proteins associated genes of Indian SARS-CoV-2 strains 93%
- ProS-GNN: Predicting effects of mutations on protein stability using graph neural networks 92%
Similar papers in this journal
- Feature Extraction Approaches for Biological Sequences: A Comparative Study of Mathematical Models 95%
- DBpred: A deep learning method for the prediction of DNA interacting residues in protein sequences 95%
- sincFold: end-to-end learning of short- and long-range interactions in RNA secondary structure 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.