Integrating experimental feedback improves generative models for biological sequences
Nucleic Acids Research · 27.08.2025 · 53 (16)
DOI: 10.1093/nar/gkaf832 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nucleic Acids Research, online erschienen am 03.09.2025. Verfasst von Francesco Calvanese und 4 weiteren Autor:innen. Beteiligte Einrichtung: Sorbonne Université, CNRS, Department of Computational, Quantitative and Synthetic Biology-CQSB, 75005 Paris, France. Hauptthemen laut MEDLINE: RNA, Catalytic. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: France 2030 PEPR Origins, EU Horizon 2020.
Abstract (Originalsprache)
Generative probabilistic models have shown promise in designing artificial RNA and protein sequences but often suffer from high rates of false positives, where sequences predicted as functional fail experimental validation. To address this critical limitation, we explore the impact of reintegrating experimental feedback into the model design process. We propose a likelihood-based reintegration scheme, which we test through extensive computational experiments on both RNA and protein datasets, as well as through wet-lab experiments on the self-splicing ribozyme from the Group I intron RNA family where our approach demonstrates particular efficacy. We show that integrating recent experimental data enhances the model’s capacity of generating functional sequences (e.g. from 6.7% to 63.7% of active designs at 45 mutations). This feedback-driven approach thus provides a significant improvement in the design of biomolecular sequences by directly tackling the false-positive challenge.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Sorbonne Université, CNRS, Department of Computational, Quantitative and Synthetic Biology-CQSB, 75005 Paris, France.
- Laboratoire de Biophysique et Evolution, UMR CNRS-ESPCI 8231 Chimie Biologie Innovation, PSL University, 75005 Paris, France.
- Politecnico di Torino, DISAT, Torino 10129, Italy.
ORCID-Profile: Martin Weigt
Förderung
- France 2030 PEPR Origins
- EU Horizon 2020
Zitieren
APA
Calvanese, F., Peinetti, G., Pavlinova, P., Nghe, P., & Weigt, M. (2025). Integrating experimental feedback improves generative models for biological sequences. Nucleic Acids Research, 53(16). https://doi.org/10.1093/nar/gkaf832
Vancouver
Calvanese F, Peinetti G, Pavlinova P, Nghe P, Weigt M. Integrating experimental feedback improves generative models for biological sequences. Nucleic Acids Research. 2025;53(16). doi:10.1093/nar/gkaf832
BibTeX
@article{Calvanese2025,
author = {Calvanese, Francesco and Peinetti, Giovanni and Pavlinova, Polina and Nghe, Philippe and Weigt, Martin},
title = {Integrating experimental feedback improves generative models for biological sequences},
journal = {Nucleic Acids Research},
year = {2025},
volume = {53},
number = {16},
doi = {10.1093/nar/gkaf832}
}
EUVIMED