PhD candidate
Research group | Hylleraas Centre for Quantum Molecular Sciences RT5
Main supervisor | David Balcells
Co-supervisors | R. De Bin & T.B. Pedersen
Affiliation | Department of Chemistry, UiO
Contact | hanneskn@uio.no
Short bio
My academic background is computational physics with a focus on computational statistics and quantum chemistry. In my master thesis I worked on genetic algorithms for optimizing molecular properties in a given chemical space.
Research interests and hobbies
My main research interests lie in the development and employment of predictive as well as generative machine learning models for chemical applications based on quantum chemistry data.
CompSci project
Catalyst discovery by combining computational chemistry with machine learning
The starting point of this project is the tmQM data set which consists of approximately 86k data points of transition metal complexes, each featuring electronic structure data and quantum property data. Using this data set machine learning approaches shall be applied in order to build predictive as well as generative models for transition metal complexes. One of the main aspects therein is the generation of appropriate representations of molecules in terms of graphs that incorporate the relevant physics in an efficient way. These graph representations in turn call for special neural network architectures (message passing neural networks) that can handle such structurally diverse data structures. Corresponding preliminary work for organic molecules exists and one open research question is how the performance for transition metal complexes compares to these results.
Doctoral thesis
Complex Learning: Machine learning approaches for transition metal complexes
Transition metal complexes (TMCs) are essential for a large range of different applications in renewable energies, energy storage, medicinal chemistry and more. Finding TMCs that have optimal properties for such applications is an expensive and time-consuming task as it traditionally requires experiments. Computer-based methods can accelerate this process by screening a large number of TMCs for promising candidates beforehand. Particularly machine learning approaches that leverage existing data have recently drawn a lot of attention. However, most research in this field focuses on small organic molecules which are easier to handle due to their simpler chemistry.
In this thesis Kneiding presents four different and novel machine learning approaches, specifically designed for their application to TMCs. In particular they are: (1) a neural network leveraging quantum chemistry informed graph representations, (2) a genetic algorithm performing directional and multi-objective optimization, (3) a set of autocorrelation descriptors capturing bond-bond and atom-bond relationships, and (4) a generative neural network for the generation of novel ligands with specific properties. In addition to these methods Kneiding also presents two TMC datasets and discusses how they can be exploited for the computer-aided discovery of TMCs.
Publications
CompSci publications
- Hannes Kneiding, Ruslan Lukin, Lucas Lang, Simen Reine, Thomas Bondo Pedersen, Riccardo De Bin, and David Balcells (2023) “Deep learning metal complex properties with natural quantum graphs” Digital Discovery 2 (3) 618–633
https://doi.org/10.1039/D2DD00129B | Full text in Research Archive - Hannes Kneiding and David Balcells (2023) “Deep graph learning for molecules and materials” Nordic Machine Intelligence 3 (2) 8-14
https://doi.org/10.5617/nmi.10517 | Full text in Research Archive - Hannes Kneiding, Ainara Nova, and David Balcells (2024) “Directional multiobjective optimization of metal complexes at the billion-system scale” Nature Computational Science 4, 263-273
https://doi.org/10.1038/s43588-024-00616-5 | Full text in Research Archive - Hannes Kneiding and David Balcells (2024) “Augmenting genetic algorithms with machine learning for inverse molecular design” Chemical Science 15 (38) 15522-15539
https://doi.org/10.1039/D4SC02934H | Full text in Research Archive - Lucía Morán-González, Jørn Eirik Betten, Hannes Kneiding, and David Balcells (2024) “AABBA graph Kernel: Atom-Atom, Bond-Bond, and Bond-Atom autocorrelations for machine learning” Journal of Chemical Information and Modeling 64 (23) 8756-8769
https://doi.org/10.1021/acs.jcim.4c01583 | Full text in Research Archive - Magnus Strandgaard, Trond Linjordet, Hannes Kneiding, Arron L. Burnage, Ainara Nova, Jan Halborg Jensen, and David Balcells (2025) “A deep generative model for the inverse design of transition metal ligands and complexes” JACS Au 5 (5) 2294–2308
https://doi.org/10.1021/jacsau.5c00242 | Full text in Research Archive - Arron L. Burnage, Hannes Kneiding, Ainara Nova, and David Balcells (2025) “Cross-coupling catalysts for inactive substrates from a three-dimensional virtual screening” Journal of Catalysis 452, 116446
https://doi.org/10.1016/j.jcat.2025.116446 | Full text in Research Archive - Hannes Kneiding and David Balcells (2025) “tmQMg* Data Set: Excited state properties of 74k transition metal complexes” Journal of Chemical Information and Modeling 65 (21) 11777
https://doi.org/10.1021/acs.jcim.5c01958 | Full text in Research Archive
Previous publications
None.
