CleaveSmart: deciphering the puzzle of rational 10–23 DNAzyme selection through interpretable AI insights
- 1Department of Pharmaceutical Biotechnology, Faculty of Pharmacy and Pharmaceutical Sciences, Isfahan University of Medical Sciences
- 2Department of Cell and Molecular Biology & Microbiology, Faculty of Biological Science and Technology, University of Isfahan
- 3Department of Bioinformatics, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences
Abstract
The 10–23 DNAzyme is a versatile platform for programmable RNA cleavage in gene regulation and diagnostics; however, its practical efficacy remains limited by the absence of precise selection criteria for optimal enzyme–substrate pairs. While machine learning (ML) offers a robust framework for addressing this complexity, previous computational approaches have lacked sufficient predictive power and generalizability. Here, we present a feature-centric ML framework developed using a comprehensive dataset of 38 DNAzyme–substrate interactions. By engineering an expanded suite of physicochemical descriptors—integrating binding energy, DNAzyme internal and homodimer energies, and RNA cost energy—we evaluated multiple algorithms, with the Random Forest model demonstrating superior performance. Our optimized model accurately predicts sustained catalytic activity (60-minute cleavage), as validated on an independent experimental dataset of 11 samples (Accuracy = 0.91, F1-score = 0.95). Notably, a significant decline in predictive power for rapid activity (10-minute) suggests a mechanistic divergence: while sustained catalysis is primarily governed by thermodynamic stability, early-phase cleavage is likely dominated by transient kinetic factors. We integrated these insights into CleaveSmart (cleavesmart.streamlit.app). This transparent, open-access pipeline replaces empirical trial-and-error with data-driven selection, significantly facilitating the identification of high-potency DNAzymes.
Related
- Molecular insights into the regulation of coenzyme selection in NADP-specific glutamate dehydrogenase from Saccharomyces cerevisiae
- Deciphering molecular mechanisms of synergistic growth reduction in kinase inhibitor combinations
- Deciphering the molecular regulatory mechanisms of seed oil in soybean for higher-oil breeding
- Deciphering photosynthetic protein networks: a crosslinking‐ MS strategy for studying functional thylakoid membranes
- Deciphering the Immune–Bone Interaction Network in Diabetic Bone Fragility: Inflammatory Mechanisms and Precision Therapeutics
BibTeX
@article{rahimpour2026cleavesmart,
title = {{CleaveSmart: deciphering the puzzle of rational 10–23 DNAzyme selection through interpretable AI insights}},
author = {Fatemeh Rahimpour and Fatemeh Javadi-Zarnaghi and Elahe Mousavi and Vajihe Akbari},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-59371-4},
url = {https://doi.org/10.1038/s41598-026-59371-4},
note = {CC BY},
}
RIS
TY - JOUR
TI - CleaveSmart: deciphering the puzzle of rational 10–23 DNAzyme selection through interpretable AI insights
AU - Fatemeh Rahimpour
AU - Fatemeh Javadi-Zarnaghi
AU - Elahe Mousavi
AU - Vajihe Akbari
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-59371-4
UR - https://doi.org/10.1038/s41598-026-59371-4
AB - The 10–23 DNAzyme is a versatile platform for programmable RNA cleavage in gene regulation and diagnostics; however, its practical efficacy remains limited by the absence of precise selection criteria for optimal enzyme–substrate pairs. While machine learning (ML) offers a robust framework for addressing this complexity, previous computational approaches have lacked sufficient predictive power and generalizability. Here, we present a feature-centric ML framework developed using a comprehensive dataset of 38 DNAzyme–substrate interactions. By engineering an expanded suite of physicochemical descriptors—integrating binding energy, DNAzyme internal and homodimer energies, and RNA cost energy—we evaluated multiple algorithms, with the Random Forest model demonstrating superior performance. Our optimized model accurately predicts sustained catalytic activity (60-minute cleavage), as validated on an independent experimental dataset of 11 samples (Accuracy = 0.91, F1-score = 0.95). Notably, a significant decline in predictive power for rapid activity (10-minute) suggests a mechanistic divergence: while sustained catalysis is primarily governed by thermodynamic stability, early-phase cleavage is likely dominated by transient kinetic factors. We integrated these insights into CleaveSmart (cleavesmart.streamlit.app). This transparent, open-access pipeline replaces empirical trial-and-error with data-driven selection, significantly facilitating the identification of high-potency DNAzymes.
SN - 2045-2322
ER -