MolMiner: Toward Controllable, Three‐Dimensional‐Aware, Fragment‐Based Molecular Design
MolMiner is a fragment‐based, geometry‐aware, and order‐agnostic generative model for molecular design with strong inductive biases. Using symmetry‐aware fragment assembly, dynamic three‐dimensional geometry, and multi‐property conditioning, MolMiner enables interpretable and controllable molecular generation.
Raul Ortega‐Ochoa +2 more
wiley +1 more source
Stability analysis and numerical simulation of nonlocal extended epidemic models using positivity-preserving scheme. [PDF]
Yousuf M, Alshakhoury N.
europepmc +1 more source
Data‐Efficient Cycle‐Level Capacity Prediction Using 1D Deep Convolutional Network
We introduce DeepBat, a deep learning framework featuring a 1D convolutional backbone designed to extract latent degradation patterns from a microstructurally diverse electrode dataset. By learning complex formulation–performance relationships, the model accurately predicts long‐term specific discharge capacity using limited early‐cycle data, providing
Tao Huang +16 more
wiley +1 more source
Intelligent computing and sensitivity analysis of unsteady darcy-forchheimer nanofluid flow over an inclined permeable disk subject to thompson-troian slip conditions. [PDF]
Aldhafeeri AA +3 more
europepmc +1 more source
Crystal Structure Prediction of Inorganic Materials: A Benchmark and Modern Evaluation
Predicting a crystal’s structure from composition alone is a long‐standing challenge in materials discovery. The CSP180 benchmark of 180 inorganic crystals evaluates thirteen crystal structure prediction algorithms requiring no density functional theory (DFT) against DFT‐based baselines across twelve metrics.
Lai Wei +9 more
wiley +1 more source
Some new results on interval-valued volterra integro-differential equations for caputo fractional derivative. [PDF]
Noureen S, Zehra A, Tolasa FT.
europepmc +1 more source
Neuro‐evolution can boost machine‐learning optimization of chiral metasurfaces. By integrating the NEAT algorithm into a deep‐learning framework, we enable the efficient design of visible‐spectrum chiroptical responses. NEAT autonomously evolves neural‐network architectures and weights, reducing manual tuning.
Davide Filippozzi, Arash Rahimi‐Iman
wiley +1 more source
Systematic comparison of inverse Langevin function approximations in stochastic dumbbell dynamics. [PDF]
Cromer M, Vasquez PA.
europepmc +1 more source
Interpretable Short‐Term Electric Load Forecasting
A temporal fusion transformer is implemented to generate day‐ahead forecasts of the hourly electrical load of a departmentbuilding at an Italian university. A forecasting performance improvement of more than 25% compared with established benchmark models and a provision of inherent robust interpretability insights reveal the potential of this model for
Alessandro Nicola +6 more
wiley +1 more source
Deterministic, stochastic, and mean-field PDE models in neuroscience. [PDF]
Çetin C +5 more
europepmc +1 more source

