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

  • Green hydrogen: How photoelectrochemical water splitting may become competitive
    Science Highlight
    20.03.2023
    Green hydrogen: How photoelectrochemical water splitting may become competitive
    Sunlight can be used to produce green hydrogen directly from water in photoelectrochemical (PEC) cells. So far, systems based on this "direct approach" have not been energetically competitive. However, the balance changes as soon as some of the hydrogen in such PEC cells is used in-situ for a catalytic hydrogenation reaction, resulting in the co-production of chemicals used in the chemical and pharmaceutical industries. The energy payback time of photoelectrochemical "green" hydrogen production can be reduced dramatically, the study shows.
  • Perovskite solar cells from the slot die coater - a step towards industrial production
    Science Highlight
    16.03.2023
    Perovskite solar cells from the slot die coater - a step towards industrial production
    Solar cells made from metal halide perovskites achieve high efficiencies and their production from liquid inks requires only a small amount of energy. A team led by Prof. Dr. Eva Unger at Helmholtz-Zentrum Berlin is investigating the production process. At the X-ray source BESSY II, the group has analyzed the optimal composition of precursor inks for the production of high-quality FAPbI3 perovskite thin films by slot-die coating. The solar cells produced with these inks were tested under real life conditions in the field for a year and scaled up to mini-module size.
  • Superstore MXene: New proton hydration structure determined
    Science Highlight
    13.03.2023
    Superstore MXene: New proton hydration structure determined
    MXenes are able to store large amounts of electrical energy like batteries and to charge and discharge rather quickly like a supercapacitor. They combine both talents and thus are a very interesting class of materials for energy storage. The material is structured like a kind of puff pastry, with the MXene layers separated by thin water films. A team at HZB has now investigated how protons migrate in the water films confined between the layers of the material and enable charge transport. Their results have been published in the renowned journal Nature Communications and may accelerate the optimisation of these kinds of energy storage materials.