Many-body expansion based machine learning models for octahedral transition metal complexes
Graph-based machine learning (ML) models for material properties show great potential to accelerate virtual high-throughput screening of large chemical spaces. However, in their simplest forms, graph-based models do not include any 3D information and are unable to distinguish stereoisomers such as t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad9f22 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558798096924672 |
|---|---|
| author | Ralf Meyer Daniel B K Chu Heather J Kulik |
| author_facet | Ralf Meyer Daniel B K Chu Heather J Kulik |
| author_sort | Ralf Meyer |
| collection | DOAJ |
| description | Graph-based machine learning (ML) models for material properties show great potential to accelerate virtual high-throughput screening of large chemical spaces. However, in their simplest forms, graph-based models do not include any 3D information and are unable to distinguish stereoisomers such as those arising from different orderings of ligands around a metal center in coordination complexes. In this work we present a modification to revised autocorrelation descriptors, a molecular graph featurization method, for predicting spin state dependent properties of octahedral transition metal complexes (TMCs). Inspired by analytical semi-empirical models for TMCs, the new modeling strategy is based on the many-body expansion (MBE) and allows one to tune the captured stereoisomer information by changing the truncation order of the MBE. We present the necessary modifications to include this approach in two commonly used ML methods, kernel ridge regression and feed-forward neural networks. On a test set composed of all possible isomers of binary TMCs, the best MBE models achieve mean absolute errors (MAEs) of 2.75 kcal mol ^−1 on spin-splitting energies and 0.26 eV on frontier orbital energy gaps, a 30%–40% reduction in error compared to models based on our previous approach. We also observe improved generalization to previously unseen ligands where the best-performing models exhibit MAEs of 4.00 kcal mol ^−1 (i.e. a 0.73 kcal mol ^−1 reduction) on the spin-splitting energies and 0.53 eV (i.e. a 0.10 eV reduction) on the frontier orbital energy gaps. Because the new approach incorporates insights from electronic structure theory, such as ligand additivity relationships, these models exhibit systematic generalization from homoleptic to heteroleptic complexes, allowing for efficient screening of TMC search spaces. |
| format | Article |
| id | doaj-art-d1cef69681664e91abf0b8e415c454e4 |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-d1cef69681664e91abf0b8e415c454e42025-01-06T05:36:00ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-015404508010.1088/2632-2153/ad9f22Many-body expansion based machine learning models for octahedral transition metal complexesRalf Meyer0https://orcid.org/0000-0003-2236-0261Daniel B K Chu1https://orcid.org/0000-0002-2427-3906Heather J Kulik2https://orcid.org/0000-0001-9342-0191Department of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139, United States of AmericaDepartment of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139, United States of AmericaDepartment of Chemical Engineering, Massachusetts Institute of Technology , Cambridge, MA 02139, United States of America; Department of Chemistry, Massachusetts Institute of Technology , Cambridge, MA 02139, United States of AmericaGraph-based machine learning (ML) models for material properties show great potential to accelerate virtual high-throughput screening of large chemical spaces. However, in their simplest forms, graph-based models do not include any 3D information and are unable to distinguish stereoisomers such as those arising from different orderings of ligands around a metal center in coordination complexes. In this work we present a modification to revised autocorrelation descriptors, a molecular graph featurization method, for predicting spin state dependent properties of octahedral transition metal complexes (TMCs). Inspired by analytical semi-empirical models for TMCs, the new modeling strategy is based on the many-body expansion (MBE) and allows one to tune the captured stereoisomer information by changing the truncation order of the MBE. We present the necessary modifications to include this approach in two commonly used ML methods, kernel ridge regression and feed-forward neural networks. On a test set composed of all possible isomers of binary TMCs, the best MBE models achieve mean absolute errors (MAEs) of 2.75 kcal mol ^−1 on spin-splitting energies and 0.26 eV on frontier orbital energy gaps, a 30%–40% reduction in error compared to models based on our previous approach. We also observe improved generalization to previously unseen ligands where the best-performing models exhibit MAEs of 4.00 kcal mol ^−1 (i.e. a 0.73 kcal mol ^−1 reduction) on the spin-splitting energies and 0.53 eV (i.e. a 0.10 eV reduction) on the frontier orbital energy gaps. Because the new approach incorporates insights from electronic structure theory, such as ligand additivity relationships, these models exhibit systematic generalization from homoleptic to heteroleptic complexes, allowing for efficient screening of TMC search spaces.https://doi.org/10.1088/2632-2153/ad9f22machine learningmany body expansiontransition metal complexesdensity functional theory |
| spellingShingle | Ralf Meyer Daniel B K Chu Heather J Kulik Many-body expansion based machine learning models for octahedral transition metal complexes Machine Learning: Science and Technology machine learning many body expansion transition metal complexes density functional theory |
| title | Many-body expansion based machine learning models for octahedral transition metal complexes |
| title_full | Many-body expansion based machine learning models for octahedral transition metal complexes |
| title_fullStr | Many-body expansion based machine learning models for octahedral transition metal complexes |
| title_full_unstemmed | Many-body expansion based machine learning models for octahedral transition metal complexes |
| title_short | Many-body expansion based machine learning models for octahedral transition metal complexes |
| title_sort | many body expansion based machine learning models for octahedral transition metal complexes |
| topic | machine learning many body expansion transition metal complexes density functional theory |
| url | https://doi.org/10.1088/2632-2153/ad9f22 |
| work_keys_str_mv | AT ralfmeyer manybodyexpansionbasedmachinelearningmodelsforoctahedraltransitionmetalcomplexes AT danielbkchu manybodyexpansionbasedmachinelearningmodelsforoctahedraltransitionmetalcomplexes AT heatherjkulik manybodyexpansionbasedmachinelearningmodelsforoctahedraltransitionmetalcomplexes |