Metraipolis › archive › dc_58d90cd8e361
Differentiable RNA Secondary Structure Extraction for Deep Learning — arXiv:2609.30752
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30752
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:10:41.999Z
- SHA-256 of the archived text
8b25492545b7fb00eb64832c6c473727d12424e89760fa7f6db2a249215701bc- Stable URL of this page
https://metraipolis.com/documento/dc_58d90cd8e361
How to cite
Differentiable RNA Secondary Structure Extraction for Deep Learning — arXiv:2609.30752 — arXiv (en), https://arxiv.org/abs/2609.30752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58d90cd8e361 (Metraipolis archive dc_58d90cd8e361, sha256 8b25492545b7fb00eb64832c6c473727d12424e89760fa7f6db2a249215701bc)
BibTeX
@misc{dc58d90cd8e361,
title = {Differentiable RNA Secondary Structure Extraction for Deep Learning — arXiv:2609.30752},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30752},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58d90cd8e361; sha256 8b25492545b7fb00eb64832c6c473727d12424e89760fa7f6db2a249215701bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many deep learning approaches to RNA secondary structure prediction have recently been proposed. They typically output a weight matrix $W$ where $W_{ij}$ is an arbitrary weight for base $i$ pairing with base $j$. Converting this matrix to a predicted secondary structure or base-pairing probability matrix typically involves ad hoc and problematic downstream algorithms. Despite the importance of this conversion step, which we refer to as structure extraction, it has received relatively little attention in the literature. In this work, we analyze how the congruence between training and extraction methods affects prediction performance. To do this, we compare four extraction algorithms: a Nussinov-like dynamic programming method, maximum-weight graph matching and the greedy extraction algorithms used by SPOT-RNA and RiNALMo. These are evaluated on outputs from the pretrained RiNALMo model and three toy models trained in this paper: a differentiable Nussinov-like model, a binary cross-entropy (BCE) baseline, and a model that incorporates a novel symmetric doubly stochastic matrix (SDSM) normalization algorithm during training which allows it to output base-pairing probability matrices directly, without a separate extraction step. This SDSM normalization algorithm is differentiable and can be added inline to any deep learning model during training and evaluation. We find that the performance of each extraction method depends strongly on how the corresponding model was trained. Considering the toy models themselves, the SDSM model showed the strongest overall performance: it outperformed the BCE baseline under all four extraction algorithms and produced pre-extraction outputs closest to the ground truth. These results suggest that SDSM normalization is a tractable alternative to traditional structure extraction.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.30752 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T01:43:06.696Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).