Calculating the "fingerprints" of molecules with artificial intelligence

The graphical neural network GNN receives small molecules as input with the task of determining their spectral responses. By matching them with the known spectra, the GNN programme learns to calculate spectra reliably.

The graphical neural network GNN receives small molecules as input with the task of determining their spectral responses. By matching them with the known spectra, the GNN programme learns to calculate spectra reliably. © K. Singh, A. Bande/HZB

With conventional methods, it is extremely time-consuming to calculate the spectral fingerprint of larger molecules. But this is a prerequisite for correctly interpreting experimentally obtained data. Now, a team at HZB has achieved very good results in significantly less time using self-learning graphical neural networks.

"Macromolecules but also quantum dots, which often consist of thousands of atoms, can hardly be calculated in advance using conventional methods such as DFT," says PD Dr. Annika Bande at HZB. With her team she has now investigated how the computing time can be shortened by using methods from artificial intelligence.

The idea: a computer programme from the group of "graphical neural networks" or GNN receives small molecules as input with the task of determining their spectral responses. In the next step, the GNN programme compares the calculated spectra with the known target spectra (DFT or experimental) and corrects the calculation path accordingly. Round after round, the result becomes better. The GNN programme thus learns on its own how to calculate spectra reliably with the help of known spectra.

"We have trained five newer GNNs and found that enormous improvements can be achieved with one of them, the SchNet model: The accuracy increases by 20% and this is done in a fraction of the computation time," says first author Kanishka Singh. Singh participates in the HEIBRiDS graduate school and is supervised by two experts from different backgrounds: computer science expert Prof. Ulf Leser from Humboldt University Berlin and theoretical chemist Annika Bande.

"Recently developed GNN frameworks could do even better," she says. "And the demand is very high. We therefore want to strengthen this line of research and are planning to create a new postdoctoral position for it from summer onwards as part of the Helmholtz project "eXplainable Artificial Intelligence for X-ray Absorption Spectroscopy"."

 

Annotation:

The work was carried out within the framework of the HEIBRiDS graduate school and is being supported by the Helmholtz project "eXplainable Artificial Intelligence for X-ray Absorption Spectroscopy" (XAI-4-XAS).

The core of the project is to extend GNN, as used at HZB, to very large molecules in combination with the probabilistic analysis of molecular motifs developed at HEREON. It is used to capture only the relevant part of the configuration phase space of the molecules, which is necessary for the accurate prediction of X-ray spectra. The results of the ML predictions allow a rigorous interpretation of XAS experiments, so that characteristic parts of the spectrum of an extended material can be assigned 1:1 to its specific structural subgroups.

 

arö

You might also be interested in

  • Humboldt Fellow Alexander Gray comes to HZB
    News
    12.08.2022
    Humboldt Fellow Alexander Gray comes to HZB
    Alexander Gray from Temple University in Philadelphia, USA, is working with HZB physicist Florian Kronast to investigate novel 2D quantum materials at BESSY II. With the fellowship from the Alexander von Humboldt Foundation, he can now deepen this cooperation. At BESSY II, he wants to further develop depth-resolved X-ray microscopic and spectroscopic methods in order to investigate 2D quantum materials and devices for new information technologies even more thoroughly.
  • Green hydrogen: Nanostructured nickel silicide shines as a catalyst
    Science Highlight
    11.08.2022
    Green hydrogen: Nanostructured nickel silicide shines as a catalyst
    Electrical energy from wind or sun can be stored as chemical energy in hydrogen, an excellent fuel and energy carrier. The prerequisite for this, however, is efficient electrolysis of water with inexpensive catalysts. For the oxygen evolution reaction at the anode, nanostructured nickel silicide now promises a significant increase in efficiency. This was demonstrated by a group from the HZB, Technical University of Berlin and the Freie Universität Berlin as part of the CatLab research platform with measurements among others at BESSY II.
  • RBB Abendschau on visit at CatLab
    News
    01.08.2022
    RBB Abendschau on visit at CatLab
    CatLab got a visit from the rbb Abendschau.
    Under the title "Der Weg weg vom Erdgas" (The way away from natural gas), the programme was broadcast on Sunday, 31st July in the rbb Abendschau and will be available in the rbb media library for 7 days.