@article{18820,
  abstract     = {Feature selection is essential in the analysis of molecular systems and many other fields, but several uncertainties remain: What is the optimal number of features for a simplified, interpretable model that retains essential information? How should features with different units be aligned, and how should their relative importance be weighted? Here, we introduce the Differentiable Information Imbalance (DII), an automated method to rank information content between sets of features. Using distances in a ground truth feature space, DII identifies a low-dimensional subset of features that best preserves these relationships. Each feature is scaled by a weight, which is optimized by minimizing the DII through gradient descent. This allows simultaneously performing unit alignment and relative importance scaling, while preserving interpretability. DII can also produce sparse solutions and determine the optimal size of the reduced feature space. We demonstrate the usefulness of this approach on two benchmark molecular problems: (1) identifying collective variables that describe conformations of a biomolecule, and (2) selecting features for training a machine-learning force field. These results show the potential of DII in addressing feature selection challenges and optimizing dimensionality in various applications. The method is available in the Python library DADApy.},
  author       = {Wild, Romina and Wodaczek, Felix and Del Tatto, Vittorio and Cheng, Bingqing and Laio, Alessandro},
  issn         = {2041-1723},
  journal      = {Nature Communications},
  publisher    = {Springer Nature},
  title        = {{Automatic feature selection and weighting in molecular systems using Differentiable Information Imbalance}},
  doi          = {10.1038/s41467-024-55449-7},
  volume       = {16},
  year         = {2025},
}

@article{14425,
  abstract     = {Water adsorption and dissociation processes on pristine low-index TiO2 interfaces are important but poorly understood outside the well-studied anatase (101) and rutile (110). To understand these, we construct three sets of machine learning potentials that are simultaneously applicable to various TiO2 surfaces, based on three density-functional-theory approximations. Here we show the water dissociation free energies on seven pristine TiO2 surfaces, and predict that anatase (100), anatase (110), rutile (001), and rutile (011) favor water dissociation, anatase (101) and rutile (100) have mostly molecular adsorption, while the simulations of rutile (110) sensitively depend on the slab thickness and molecular adsorption is preferred with thick slabs. Moreover, using an automated algorithm, we reveal that these surfaces follow different types of atomistic mechanisms for proton transfer and water dissociation: one-step, two-step, or both. These mechanisms can be rationalized based on the arrangements of water molecules on the different surfaces. Our finding thus demonstrates that the different pristine TiO2 surfaces react with water in distinct ways, and cannot be represented using just the low-energy anatase (101) and rutile (110) surfaces.},
  author       = {Zeng, Zezhu and Wodaczek, Felix and Liu, Keyang and Stein, Frederick and Hutter, Jürg and Chen, Ji and Cheng, Bingqing},
  issn         = {2041-1723},
  journal      = {Nature Communications},
  publisher    = {Springer Nature},
  title        = {{Mechanistic insight on water dissociation on pristine low-index TiO2 surfaces from machine learning molecular dynamics simulations}},
  doi          = {10.1038/s41467-023-41865-8},
  volume       = {14},
  year         = {2023},
}

@article{13216,
  abstract     = {Physical catalysts often have multiple sites where reactions can take place. One prominent example is single-atom alloys, where the reactive dopant atoms can preferentially locate in the bulk or at different sites on the surface of the nanoparticle. However, ab initio modeling of catalysts usually only considers one site of the catalyst, neglecting the effects of multiple sites. Here, nanoparticles of copper doped with single-atom rhodium or palladium are modeled for the dehydrogenation of propane. Single-atom alloy nanoparticles are simulated at 400–600 K, using machine learning potentials trained on density functional theory calculations, and then the occupation of different single-atom active sites is identified using a similarity kernel. Further, the turnover frequency for all possible sites is calculated for propane dehydrogenation to propene through microkinetic modeling using density functional theory calculations. The total turnover frequencies of the whole nanoparticle are then described from both the population and the individual turnover frequency of each site. Under operating conditions, rhodium as a dopant is found to almost exclusively occupy (111) surface sites while palladium as a dopant occupies a greater variety of facets. Undercoordinated dopant surface sites are found to tend to be more reactive for propane dehydrogenation compared to the (111) surface. It is found that considering the dynamics of the single-atom alloy nanoparticle has a profound effect on the calculated catalytic activity of single-atom alloys by several orders of magnitude.},
  author       = {Bunting, Rhys and Wodaczek, Felix and Torabi, Tina and Cheng, Bingqing},
  issn         = {1520-5126},
  journal      = {Journal of the American Chemical Society},
  keywords     = {Colloid and Surface Chemistry, Biochemistry, General Chemistry, Catalysis},
  number       = {27},
  pages        = {14894--14902},
  publisher    = {American Chemical Society},
  title        = {{Reactivity of single-atom alloy nanoparticles: Modeling the dehydrogenation of propane}},
  doi          = {10.1021/jacs.3c04030},
  volume       = {145},
  year         = {2023},
}