End-to-end robust system discovery in electrical dynamical systems using scientific machine learning. [PDF]
Chakravorty J, Ripamonti N, Laneryd T.
europepmc +1 more source
A Generative Neuro‐Symbolic AI for Protein Sequence Design
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne +12 more
wiley +1 more source
FunDiff: diffusion models over function spaces for physics-informed generative modeling. [PDF]
Wang S, Dou Z, Shan S, Liu TR, Lu L.
europepmc +1 more source
Engineering of the 148‐germline (148‐GL) antibody reveals a roadmap for overcoming SARS‐CoV‐2 viral escape. By introducing four specific somatic hypermutations, the resulting 148‐M4 variant restores potent neutralization against Omicron BA.1 and BA.4/5.
Huibin Lv +14 more
wiley +1 more source
Paul Hertz' contribution to proof theory: normal-form results for deductions. [PDF]
Bodner M.
europepmc +1 more source
NbOx Mott Memristor‐Based Oscillatory P‐trit for Ternary Potts Machine
A ternary Potts machine utilizing NbOx‐based probabilistic trits (p‐trits) is demonstrated for efficient combinatorial optimization. By leveraging the electro‐thermal switching dynamics of NbOx memristors, this architecture generates three‐state stochastic fluctuations.
Hakseung Rhee +10 more
wiley +1 more source
Development and implementation of a unified curriculum in math, statistics, computing, and informatics with financial considerations for medical physics graduate programs. [PDF]
Chang J, Vaccarelli MJ.
europepmc +1 more source
A covalently integrated single‐component photocatalyst is constructed by anchoring selenoviologen to platinum nanoparticles via robust N‐heterocyclic carbene ligands. The resulting Pt─C covalent bonds function dually as protective structural scaffolds and direct channels for ultrafast intramolecular electron transfer This precise interfacial ...
Wenxi He +8 more
wiley +1 more source
How AI Can Advance Mathematical Biology: Opportunities, Challenges, and Future Directions. [PDF]
Rabiei K +3 more
europepmc +1 more source
Artificial Intelligence‐Driven Inverse Design of Singlet Fission Candidates in the Acene family
In this work, we describe an AI‐driven inverse design platform predicting S1 and T1 energies across acenes with high accuracy. Using Hammett σ constants as descriptors and RNN models coupled with optimization algorithms, it efficiently explores ≈1014 structures, uncovering novel SF candidates from benzene to pentacene. Freely accessible at https://alba.
Rafael G. Uceda +9 more
wiley +1 more source

