CoChat
Sign Up
Cited by 114Machine Learning in Materials ScienceAdvanced Chemical Physics StudiesComputational Drug Discovery Methods

Designing in the Face of Uncertainty: Exploiting Electronic Structure and Machine Learning Models for Discovery in Inorganic Chemistry

Open access
Janet, Jon Paul, Liu, Fang, Nandy, Aditya, Duan, Chenru, Yang, Tzuhsiung, Lin, Sean, Kulik, Heather J.·2019·Inorganic Chemistry
DOI 10.1021/acs.inorgchem.9b00109
Open this paper in CoChat — free accountOpen PDF

Abstract

Recent transformative advances in computing power and algorithms have made computational chemistry central to the discovery and design of new molecules and materials. First-principles simulations are increasingly accurate and applicable to large systems with the speed needed for high-throughput computational screening. Despite these strides, the combinatorial challenges associated with the vastness of chemical space mean that more than just fast and accurate computational tools are needed for accelerated chemical discovery. In transition-metal chemistry and catalysis, unique challenges arise. The variable spin, oxidation state, and coordination environments favored by elements with well-localized d or f electrons provide great opportunity for tailoring properties in catalytic or functional (e.g., magnetic) materials but also add layers of uncertainty to any design strategy. We outline five key mandates for realizing computationally driven accelerated discovery in inorganic chemistry: (i) fully automated simulation of new compounds, (ii) knowledge of prediction sensitivity or accuracy, (iii) faster-than-fast property prediction methods, (iv) maps for rapid chemical space traversal, and (v) a means to reveal design rules on the kilocompound scale. Through case studies in open-shell transition-metal chemistry, we describe how advances in methodology and software in each of these areas bring about new chemical insights. We conclude with our outlook on the next steps in this process toward realizing fully autonomous discovery in inorganic chemistry using computational chemistry.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1021/acs.inorgchem.9b00109

Cites

163 of 163 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Identifying key descriptors or features in a structure-property relationship mapping has been demonstrated as an approach to revealing design principles and enabling iterative design.

    “Identifying key descriptors or features in a structure-property relationship mapping has been demonstrated as an approach to revealing design principles (18,22,32,52) and enabling iterative design (70).”

    From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [52]

    Section 3e (Results and Discussion; page unavailable) reports that selecting important structural features reveals design rules, and gives examples of using those rules to tune properties of transition-metal complexes. It proposes that these principles could guide ligand and metal substitutions, but does not demonstrate an iterative design cycle, which is the part of the citing sentence attributed to this source. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • An ANN trained on topological descriptors to predict DFT metal-ligand bond lengths was used to classify experimental spin states and even to correct DFT-based energetic predictions of spin states.

    “An ANN trained on topological descriptors to predict DFT metal-ligand bond lengths (52) was used to classify experimental spin states (85) and even to correct DFT-based energetic predictions of spin states.”

    From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [52]

    The Results and Discussion section describes an ANN using connectivity and topology-related descriptors to predict DFT metal–ligand bond lengths and high- versus low-spin splitting. It reports 97% agreement on qualitative ground-state spin against DFT results, but explicitly says the model learns DFT answers, not experimental observations. The passages do not show the ANN correcting DFT-based spin-state energetics. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • ML models, analysis of their key features, and dimensionality reduction represent important tools for building structure-property relationships and mapping chemical space.

    “ML models, analysis of their key features (32,52), and dimensionality reduction (i.e., unsupervised learning) (53-56) represent important tools for building structure-property relationships and mapping chemical space (57).”

    From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [52]

  • Beyond trial-and-error or ad hoc selection of descriptors, rigorous feature selection with ML models has emerged as a powerful tool for inferring design principles.

    “Beyond trial-and-error or ad hoc selection of descriptors, rigorous feature selection with ML models has emerged as a powerful tool for inferring design principles (22,32,43,52,72,90,91).”

    From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [52]

  • Conversely, other properties, such as the frontier orbital energies, band gap, or ionization/redox potential, depend much more on the global structure of the molecule.

    “Conversely, other properties, such as the frontier orbital energies (22), band gap (44, 105), or ionization/redox potential (32,52), depend much more on the global structure of the molecule (Figure 5).”

    From Machine Learning for the Discovery, Design, and Engineering of Materials. (2022) · cites this paper as [52]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 4

  1. Strategies for Two-Electron Integral Evaluation. J. Chem. Theory Comput. 2008, 4, 222-231.
  2. J. Chem. Phys. 2005, 122, 044110.
  3. Spin-Crossover Complex with Reparametrized Density Functionals. Inorg. Chem. 2002, 41, 6928-6935.
  4. J. Chem. Phys. 2004, 120, 9473-9486.

Cited by

Sorted by citations

Related

Authors
Janet, J. P., Liu, F., Nandy, A., Duan, C., Yang, T., Lin, S., & Kulik, H. J.
Affiliations
Massachusetts Institute of Technology (US)
Corresponding author
Kulik, Heather J.
ORCID
Venue
Inorganic Chemistry
Publisher
American Chemical Society (ACS)
Published
2019-03-05
Volume
58
Issue
16
Pages
10592-10606
ISSN
  • 0020-1669 (ISSN-L)
  • 1520-510X
DOI
10.1021/acs.inorgchem.9b00109
OpenAlex
W2920327541
Cited by
114
References
163
Citations by year
2026: 7 · 2025: 12 · 2024: 6 · 2023: 15 · 2022: 16 · 2021: 23 · 2020: 22 · 2019: 12 · 2018: 1
FWCI
6.60
Type
journal article
Language
en
Open access
Licence
Locations
  • Inorganic Chemistry (publishedVersion, other-oa)
  • PubMed (publishedVersion)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
Funders
  • Office of Naval Research (N00014-17-1-2956, N00014-18-1-2434)
  • Division of Chemical, Bioengineering, Environmental, and Transport Systems (CBET-1704266)
  • Defense Advanced Research Projects Agency (D18AP00039)
  • Burroughs Wellcome Fund (NA)
  • Basic Energy Sciences (DE-SC0018096)
  • Massachusetts Institute of Technology (NA)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
Keywords
transition metal chemistry, open-shell systems, electronic structure, machine learning property prediction, chemical space mapping, design rules, high-throughput computational screening, catalysis, magnetic materials, forecast uncertainty

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review