---
DOAJ_listed: '1'
OA_place: publisher
OA_type: gold
_id: '18820'
abstract:
- lang: eng
  text: '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.'
acknowledgement: The authors thank Dr. Matteo Carli for providing the CLN025 replica
  exchange MD trajectory and Matteo Allione for the fruitful discussions connected
  with the idea of the linear scaling estimator. This work was partially funded by
  NextGenerationEU through the Italian National Centre for HPC, Big Data, and Quantum
  Computing (Grant No. CN00000013 received by A.L.). A.L. also acknowledges financial
  support by the region Friuli Venezia Giulia (project F53C22001770002 received by
  A.L.).
article_number: '270'
article_processing_charge: Yes
article_type: original
author:
- first_name: Romina
  full_name: Wild, Romina
  last_name: Wild
- first_name: Felix
  full_name: Wodaczek, Felix
  id: 8b4b6a9f-32b0-11ee-9fa8-bbe85e26258e
  last_name: Wodaczek
  orcid: 0009-0000-1457-795X
- first_name: Vittorio
  full_name: Del Tatto, Vittorio
  last_name: Del Tatto
- first_name: Bingqing
  full_name: Cheng, Bingqing
  id: cbe3cda4-d82c-11eb-8dc7-8ff94289fcc9
  last_name: Cheng
  orcid: 0000-0002-3584-9632
- first_name: Alessandro
  full_name: Laio, Alessandro
  last_name: Laio
citation:
  ama: Wild R, Wodaczek F, Del Tatto V, Cheng B, Laio A. Automatic feature selection
    and weighting in molecular systems using Differentiable Information Imbalance.
    <i>Nature Communications</i>. 2025;16. doi:<a href="https://doi.org/10.1038/s41467-024-55449-7">10.1038/s41467-024-55449-7</a>
  apa: Wild, R., Wodaczek, F., Del Tatto, V., Cheng, B., &#38; Laio, A. (2025). Automatic
    feature selection and weighting in molecular systems using Differentiable Information
    Imbalance. <i>Nature Communications</i>. Springer Nature. <a href="https://doi.org/10.1038/s41467-024-55449-7">https://doi.org/10.1038/s41467-024-55449-7</a>
  chicago: Wild, Romina, Felix Wodaczek, Vittorio Del Tatto, Bingqing Cheng, and Alessandro
    Laio. “Automatic Feature Selection and Weighting in Molecular Systems Using Differentiable
    Information Imbalance.” <i>Nature Communications</i>. Springer Nature, 2025. <a
    href="https://doi.org/10.1038/s41467-024-55449-7">https://doi.org/10.1038/s41467-024-55449-7</a>.
  ieee: R. Wild, F. Wodaczek, V. Del Tatto, B. Cheng, and A. Laio, “Automatic feature
    selection and weighting in molecular systems using Differentiable Information
    Imbalance,” <i>Nature Communications</i>, vol. 16. Springer Nature, 2025.
  ista: Wild R, Wodaczek F, Del Tatto V, Cheng B, Laio A. 2025. Automatic feature
    selection and weighting in molecular systems using Differentiable Information
    Imbalance. Nature Communications. 16, 270.
  mla: Wild, Romina, et al. “Automatic Feature Selection and Weighting in Molecular
    Systems Using Differentiable Information Imbalance.” <i>Nature Communications</i>,
    vol. 16, 270, Springer Nature, 2025, doi:<a href="https://doi.org/10.1038/s41467-024-55449-7">10.1038/s41467-024-55449-7</a>.
  short: R. Wild, F. Wodaczek, V. Del Tatto, B. Cheng, A. Laio, Nature Communications
    16 (2025).
das_tickbox: '1'
dataavailabilitystatement: 'The data generated by feature selection in this study
  have been deposited on OSF at the following URL: https://osf.io/swtg5. The processed
  molecular dynamics and H2O structure data are also available at OSF. The data files
  necessary for carrying out all analyses and source data are available at the same
  OSF URL. Source data are provided with this paper.'
date_created: 2025-01-12T23:04:00Z
date_published: 2025-01-02T00:00:00Z
date_updated: 2026-08-07T09:43:12Z
day: '02'
ddc:
- '570'
department:
- _id: AnSa
- _id: BiCh
doi: 10.1038/s41467-024-55449-7
external_id:
  isi:
  - '001389959100009'
  pmid:
  - '39747013'
file:
- access_level: open_access
  checksum: b3d0f3568d9a87c494cf231a5324029a
  content_type: application/pdf
  creator: dernst
  date_created: 2025-01-14T06:59:25Z
  date_updated: 2025-01-14T06:59:25Z
  file_id: '18846'
  file_name: 2025_NatureComm_Wild.pdf
  file_size: 1216738
  relation: main_file
  success: 1
file_date_updated: 2025-01-14T06:59:25Z
fulldoi: https://doi.org/10.1038/s41467-024-55449-7
has_accepted_license: '1'
intvolume: '        16'
isi: 1
language:
- iso: eng
license: https://creativecommons.org/licenses/by-nc-nd/4.0/
month: '01'
oa: 1
oa_version: Published Version
pmid: 1
publication: Nature Communications
publication_identifier:
  eissn:
  - 2041-1723
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
researchdata_availability: yes
scopus_import: '1'
status: public
supplementarymaterial: no
title: Automatic feature selection and weighting in molecular systems using Differentiable
  Information Imbalance
tmp:
  image: /images/cc_by_nc_nd.png
  legal_code_url: https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode
  name: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
    (CC BY-NC-ND 4.0)
  short: CC BY-NC-ND (4.0)
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 16
year: '2025'
...
---
_id: '14425'
abstract:
- lang: eng
  text: '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.'
acknowledgement: F.S., J.H., and B.C. thank the Swiss National Supercomputing Centre
  (CSCS) for the generous allocation of CPU hours via production project s1108 at
  the Piz Daint supercomputer. B.C. acknowledges resources provided by the Cambridge
  Tier-2 system operated by the University of Cambridge Research Computing Service
  funded by EPSRC Tier-2 capital grant EP/P020259/1. J.C. acknowledges the Beijing
  Natural Science Foundation for support under grant No. JQ22001. F.S., and J.H. thank
  the Swiss Platform for Advanced Scientific Computing (PASC) via the 2021-2024 “Ab
  Initio Molecular Dynamics at the Exa-Scale” project. This project has received funding
  from the European Union’s Horizon 2020 research and innovation programme under the
  Marie Skłodowska-Curie grant agreement No 101034413.
article_number: '6131'
article_processing_charge: Yes
article_type: original
arxiv: 1
author:
- first_name: Zezhu
  full_name: Zeng, Zezhu
  id: 54a2c730-803f-11ed-ab7e-95b29d2680e7
  last_name: Zeng
  orcid: 0000-0001-5126-4928
- first_name: Felix
  full_name: Wodaczek, Felix
  id: 8b4b6a9f-32b0-11ee-9fa8-bbe85e26258e
  last_name: Wodaczek
  orcid: 0009-0000-1457-795X
- first_name: Keyang
  full_name: Liu, Keyang
  last_name: Liu
- first_name: Frederick
  full_name: Stein, Frederick
  last_name: Stein
- first_name: Jürg
  full_name: Hutter, Jürg
  last_name: Hutter
- first_name: Ji
  full_name: Chen, Ji
  last_name: Chen
- first_name: Bingqing
  full_name: Cheng, Bingqing
  id: cbe3cda4-d82c-11eb-8dc7-8ff94289fcc9
  last_name: Cheng
  orcid: 0000-0002-3584-9632
citation:
  ama: Zeng Z, Wodaczek F, Liu K, et al. Mechanistic insight on water dissociation
    on pristine low-index TiO2 surfaces from machine learning molecular dynamics simulations.
    <i>Nature Communications</i>. 2023;14. doi:<a href="https://doi.org/10.1038/s41467-023-41865-8">10.1038/s41467-023-41865-8</a>
  apa: Zeng, Z., Wodaczek, F., Liu, K., Stein, F., Hutter, J., Chen, J., &#38; Cheng,
    B. (2023). Mechanistic insight on water dissociation on pristine low-index TiO2
    surfaces from machine learning molecular dynamics simulations. <i>Nature Communications</i>.
    Springer Nature. <a href="https://doi.org/10.1038/s41467-023-41865-8">https://doi.org/10.1038/s41467-023-41865-8</a>
  chicago: Zeng, Zezhu, Felix Wodaczek, Keyang Liu, Frederick Stein, Jürg Hutter,
    Ji Chen, and Bingqing Cheng. “Mechanistic Insight on Water Dissociation on Pristine
    Low-Index TiO2 Surfaces from Machine Learning Molecular Dynamics Simulations.”
    <i>Nature Communications</i>. Springer Nature, 2023. <a href="https://doi.org/10.1038/s41467-023-41865-8">https://doi.org/10.1038/s41467-023-41865-8</a>.
  ieee: Z. Zeng <i>et al.</i>, “Mechanistic insight on water dissociation on pristine
    low-index TiO2 surfaces from machine learning molecular dynamics simulations,”
    <i>Nature Communications</i>, vol. 14. Springer Nature, 2023.
  ista: Zeng Z, Wodaczek F, Liu K, Stein F, Hutter J, Chen J, Cheng B. 2023. Mechanistic
    insight on water dissociation on pristine low-index TiO2 surfaces from machine
    learning molecular dynamics simulations. Nature Communications. 14, 6131.
  mla: Zeng, Zezhu, et al. “Mechanistic Insight on Water Dissociation on Pristine
    Low-Index TiO2 Surfaces from Machine Learning Molecular Dynamics Simulations.”
    <i>Nature Communications</i>, vol. 14, 6131, Springer Nature, 2023, doi:<a href="https://doi.org/10.1038/s41467-023-41865-8">10.1038/s41467-023-41865-8</a>.
  short: Z. Zeng, F. Wodaczek, K. Liu, F. Stein, J. Hutter, J. Chen, B. Cheng, Nature
    Communications 14 (2023).
corr_author: '1'
das_tickbox: '1'
dataavailabilitystatement: "The machine learning potentials, training sets, sample
  DFT and metadynamics input files, PYTHON data analysis scripts and other necessary
  source data files generated for this study are available in the SI repository (https://github.com/BingqingCheng/TiO2-water)
  see ref 58.\r\n58. Zeng, Z. et al. Source data for Mechanistic insight on water
  dissociation on pristine low-index TiO2 surfaces from machine learning molecular
  dynamics simulations, Zenodo, https://zenodo.org/record/8301965 (2023)."
date_created: 2023-10-15T22:01:10Z
date_published: 2023-10-02T00:00:00Z
date_updated: 2026-08-07T11:00:29Z
day: '02'
ddc:
- '540'
- '000'
department:
- _id: BiCh
- _id: GradSch
doi: 10.1038/s41467-023-41865-8
ec_funded: 1
external_id:
  arxiv:
  - '2303.07433'
  isi:
  - '001084354900008'
  pmid:
  - '37783698'
file:
- access_level: open_access
  checksum: 7d1dffd36b672ec679f08f70ce79da87
  content_type: application/pdf
  creator: dernst
  date_created: 2023-10-16T07:34:49Z
  date_updated: 2023-10-16T07:34:49Z
  file_id: '14432'
  file_name: 2023_NatureComm_Zeng.pdf
  file_size: 3194116
  relation: main_file
  success: 1
file_date_updated: 2023-10-16T07:34:49Z
fulldoi: https://doi.org/10.1038/s41467-023-41865-8
has_accepted_license: '1'
intvolume: '        14'
isi: 1
language:
- iso: eng
month: '10'
oa: 1
oa_version: Published Version
pmid: 1
project:
- _id: fc2ed2f7-9c52-11eb-aca3-c01059dda49c
  call_identifier: H2020
  grant_number: '101034413'
  name: 'IST-BRIDGE: International postdoctoral program'
publication: Nature Communications
publication_identifier:
  eissn:
  - 2041-1723
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
related_material:
  link:
  - relation: software
    url: https://github.com/BingqingCheng/TiO2-water
researchdata_availability: yes
scopus_import: '1'
status: public
supplementarymaterial: yes
title: Mechanistic insight on water dissociation on pristine low-index TiO2 surfaces
  from machine learning molecular dynamics simulations
tmp:
  image: /images/cc_by.png
  legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
  name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
  short: CC BY (4.0)
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 14
year: '2023'
...
---
_id: '13216'
abstract:
- lang: eng
  text: 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.
acknowledgement: "B.C. acknowledges resources provided by the Cambridge Tier2 system
  operated by the University of Cambridge Research\r\nComputing Service funded by
  EPSRC Tier-2 capital grant EP/\r\nP020259/1."
article_processing_charge: Yes (via OA deal)
article_type: original
author:
- first_name: Rhys
  full_name: Bunting, Rhys
  id: 91deeae8-1207-11ec-b130-c194ad5b50c6
  last_name: Bunting
  orcid: 0000-0001-6928-074X
- first_name: Felix
  full_name: Wodaczek, Felix
  id: 8b4b6a9f-32b0-11ee-9fa8-bbe85e26258e
  last_name: Wodaczek
  orcid: 0009-0000-1457-795X
- first_name: Tina
  full_name: Torabi, Tina
  last_name: Torabi
- first_name: Bingqing
  full_name: Cheng, Bingqing
  id: cbe3cda4-d82c-11eb-8dc7-8ff94289fcc9
  last_name: Cheng
  orcid: 0000-0002-3584-9632
citation:
  ama: 'Bunting R, Wodaczek F, Torabi T, Cheng B. Reactivity of single-atom alloy
    nanoparticles: Modeling the dehydrogenation of propane. <i>Journal of the American
    Chemical Society</i>. 2023;145(27):14894-14902. doi:<a href="https://doi.org/10.1021/jacs.3c04030">10.1021/jacs.3c04030</a>'
  apa: 'Bunting, R., Wodaczek, F., Torabi, T., &#38; Cheng, B. (2023). Reactivity
    of single-atom alloy nanoparticles: Modeling the dehydrogenation of propane. <i>Journal
    of the American Chemical Society</i>. American Chemical Society. <a href="https://doi.org/10.1021/jacs.3c04030">https://doi.org/10.1021/jacs.3c04030</a>'
  chicago: 'Bunting, Rhys, Felix Wodaczek, Tina Torabi, and Bingqing Cheng. “Reactivity
    of Single-Atom Alloy Nanoparticles: Modeling the Dehydrogenation of Propane.”
    <i>Journal of the American Chemical Society</i>. American Chemical Society, 2023.
    <a href="https://doi.org/10.1021/jacs.3c04030">https://doi.org/10.1021/jacs.3c04030</a>.'
  ieee: 'R. Bunting, F. Wodaczek, T. Torabi, and B. Cheng, “Reactivity of single-atom
    alloy nanoparticles: Modeling the dehydrogenation of propane,” <i>Journal of the
    American Chemical Society</i>, vol. 145, no. 27. American Chemical Society, pp.
    14894–14902, 2023.'
  ista: 'Bunting R, Wodaczek F, Torabi T, Cheng B. 2023. Reactivity of single-atom
    alloy nanoparticles: Modeling the dehydrogenation of propane. Journal of the American
    Chemical Society. 145(27), 14894–14902.'
  mla: 'Bunting, Rhys, et al. “Reactivity of Single-Atom Alloy Nanoparticles: Modeling
    the Dehydrogenation of Propane.” <i>Journal of the American Chemical Society</i>,
    vol. 145, no. 27, American Chemical Society, 2023, pp. 14894–902, doi:<a href="https://doi.org/10.1021/jacs.3c04030">10.1021/jacs.3c04030</a>.'
  short: R. Bunting, F. Wodaczek, T. Torabi, B. Cheng, Journal of the American Chemical
    Society 145 (2023) 14894–14902.
corr_author: '1'
das_tickbox: '0'
date_created: 2023-07-12T09:16:40Z
date_published: 2023-06-30T00:00:00Z
date_updated: 2026-08-07T11:37:26Z
day: '30'
ddc:
- '540'
department:
- _id: MaIb
- _id: BiCh
doi: 10.1021/jacs.3c04030
external_id:
  isi:
  - '001020623900001'
  pmid:
  - '37390457'
file:
- access_level: open_access
  checksum: e07d5323f9c0e5cbd1ad6453f29440ab
  content_type: application/pdf
  creator: cchlebak
  date_created: 2023-07-12T10:22:04Z
  date_updated: 2023-07-12T10:22:04Z
  file_id: '13219'
  file_name: 2023_JACS_Bunting.pdf
  file_size: 3155843
  relation: main_file
  success: 1
file_date_updated: 2023-07-12T10:22:04Z
fulldoi: https://doi.org/10.1021/jacs.3c04030
has_accepted_license: '1'
intvolume: '       145'
isi: 1
issue: '27'
keyword:
- Colloid and Surface Chemistry
- Biochemistry
- General Chemistry
- Catalysis
language:
- iso: eng
month: '06'
oa: 1
oa_version: Published Version
page: 14894-14902
pmid: 1
publication: Journal of the American Chemical Society
publication_identifier:
  eissn:
  - 1520-5126
  issn:
  - 0002-7863
publication_status: published
publisher: American Chemical Society
quality_controlled: '1'
researchdata_availability: no
scopus_import: '1'
status: public
supplementarymaterial: yes
title: 'Reactivity of single-atom alloy nanoparticles: Modeling the dehydrogenation
  of propane'
tmp:
  image: /images/cc_by.png
  legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
  name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
  short: CC BY (4.0)
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 145
year: '2023'
...