Can geometric combinatorics improve RNA branching predictions?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916663486578688 |
|---|---|
| author | Poznanović, Svetlana Cardwell, Owen Heitsch, Christine |
| author_facet | Poznanović, Svetlana Cardwell, Owen Heitsch, Christine |
| contents | Prior results for tRNA and 5S rRNA demonstrated that secondary structure prediction accuracy can be significantly improved by modifying the parameters in the multibranch loop entropic penalty function. However, for reasons not well understood at the time, the scale of improvement possible across both families was well below the level for each family when considered separately. We resolve this dichotomy here by showing that each family has a characteristic target region geometry, which is distinct from the other and significantly different from their own dinucleotide shuffles. This required a much more efficient approach to computing the necessary information from the branching parameter space, and a new theoretical characterization of the region geometries. The insights gained point strongly to considering multiple possible secondary structures generated by varying the multiloop parameters. We provide proof-of-principle results that this significantly improves prediction accuracy across all 8 additional families in the Archive II benchmarking dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20977 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can geometric combinatorics improve RNA branching predictions? Poznanović, Svetlana Cardwell, Owen Heitsch, Christine Biomolecules 92C40, 92D20 Prior results for tRNA and 5S rRNA demonstrated that secondary structure prediction accuracy can be significantly improved by modifying the parameters in the multibranch loop entropic penalty function. However, for reasons not well understood at the time, the scale of improvement possible across both families was well below the level for each family when considered separately. We resolve this dichotomy here by showing that each family has a characteristic target region geometry, which is distinct from the other and significantly different from their own dinucleotide shuffles. This required a much more efficient approach to computing the necessary information from the branching parameter space, and a new theoretical characterization of the region geometries. The insights gained point strongly to considering multiple possible secondary structures generated by varying the multiloop parameters. We provide proof-of-principle results that this significantly improves prediction accuracy across all 8 additional families in the Archive II benchmarking dataset. |
| title | Can geometric combinatorics improve RNA branching predictions? |
| topic | Biomolecules 92C40, 92D20 |
| url | https://arxiv.org/abs/2503.20977 |