A5043497269- Smart Grid Security and Resilience
- RNA and protein synthesis mechanisms
- Adversarial Robustness in Machine Learning
- RNA modifications and cancer
- Power System Optimization and Stability
- RNA Research and Splicing
- Cancer-related molecular mechanisms research
- Antimicrobial Peptides and Activities
- Infrastructure Resilience and Vulnerability Analysis
Informatique, BioInformatique, Systèmes Complexes
2023-2025
Université Paris-Saclay
2025
Université d'Évry Val-d'Essonne
2024
The accurate prediction of RNA secondary structure, and pseudoknots in particular, is great importance understanding the functions RNAs since they give insights into their folding three-dimensional space. However, existing approaches often face computational challenges or lack precision when dealing with long sequences and/or pseudoknots. To address this, we propose a divide-and-conquer method based on deep learning, called DivideFold, for predicting structures including RNAs. Our approach...
We propose a new adversarial training approach for injecting robustness when designing controllers upcoming cyber-physical power systems. Previous approaches relying deeply on simulations are not able to cope with the rising complexity and too costly used online in terms of computation budget. In comparison, our method proves be computationally efficient while displaying useful properties. To do so we model an framework, implementation fixed opponent policy test it L2RPN (Learning Run Power...
The accurate prediction of RNA secondary structure, and pseudoknots in particular, is great importance understanding the functions RNAs since they give insights into their folding three-dimensional space. However, existing approaches often face computational challenges or lack precision when dealing with long sequences and/or pseudoknots. To address this, we propose a divide-and-conquer method based on deep learning, called DivideFold, for predicting structures including RNAs. Our approach...
Accurately predicting the secondary structure of RNA, particularly for long non-coding has direct implications in healthcare, where it can be used diagnostic, therapeutic, and drug discovery purposes. However, majority previous approaches are too costly terms computation budget to cope with increasing complexity RNAs, ones that scale RNAs lack accuracy reliably predict their structures. We propose a new approach combining recursive cutting machine learning techniques structures RNAs. In...
We propose a new adversarial training approach for injecting robustness when designing controllers upcoming cyber-physical power systems. Previous approaches relying deeply on simulations are not able to cope with the rising complexity and too costly used online in terms of computation budget. In comparison, our method proves be computationally efficient while displaying useful properties. To do so we model an framework, implementation fixed opponent policy test it L2RPN (Learning Run Power...