Stay in touch
Prime news from our network.
#read
Drug discovery with imaging methods and AI
In the "ImageTox" project, the Helmholtz Institute for Pharmaceutical Research Saarland (HIPS) and the CISPA Helmholtz Centre for Information Security are pooling their expertise in the fields of drug research and artificial intelligence, according to the institute. Using state-of-the-art machine learning methods, the Saarbrücken-based institutions aim to make research into the modes of action of new potential drugs more efficient. The project is an initiative of the Helmholtz Medical Security, Privacy, and AI Research Centre (HMSP) and is being funded with 200,000 euros by Helmholtz Imaging, an initiative to promote research using imaging methods.
20/02/2023
Researchers all over the world are searching for new antibiotics or antivirals that can keep multi-resistant pathogens in check or combat new pathogens. If an active substance looks promising, it not only has to be put through its paces literally before being authorised for humans and animals - the process starts in the test tube. However, research on living organisms will become essential at a later stage in order to avoid the occurrence of undesirable side effects in humans.
In drug and toxicity testing, zebrafish larvae could serve as a meaningful test model. The special thing about larvae is that they develop an organ system with kidneys and liver in the first 120 hours after fertilisation. Whether an active substance can be broken down by the organism or shows toxic side effects can therefore be tested much better on them than on simple cell culture models”, says Dr Jennifer Herrmann, Team Leader Biology at HIPS. The HIPS is a site of the Helmholtz Centre for Infection Research in collaboration with Saarland University.
Due to their good comparability with more highly developed species, the studies on larvae can partly replace animal experiments in the early preclinical development of drugs. At the HIPS, larvae are already being used successfully on a small scale in drug research. The institute's zebrafish team was honoured with the "Alternatives to Animal Testing" research prize by the Saarland Ministry of the Environment in the summer.
The problem: so far, the method can only be used for a limited number of tests. This is because each larva still has to be examined under the microscope twice a day by the researchers. Changes in the development of the larvae caused by treatment with drug candidates are often difficult to recognise with the naked eye. If pathological changes or influences on the development of the larvae occur, the rapid development of the larvae makes it almost impossible to trace exactly when these occurred. The process is also very time-consuming and therefore cannot yet be used on a large scale.
Together, HIPS and CISPA want to change this. We will develop machine learning methods that can predict the development of larvae after testing and recognise anomalies based on images at a very early stage. This means that many test series can be terminated prematurely, saving time and money. In addition, we can achieve a high degree of automation of the experiments. We also suspect that such algorithms can even surpass the human ability to analyse and interpret microscopy data," explains CISPA faculty Prof. Dr Mario Fritz.
If the researchers succeed in combining the biological model system of the HIPS with the modern machine learning approaches of the CISPA, their safety could be efficiently tested at a very early stage in the development of new drugs. As part of the project, the knowledge gained will also be extended to more complex development stages, such as the detection of heartbeat rates and arrhythmias, thus enabling a comprehensive toxicological assessment of drug candidates.
The above texts, or parts thereof, were automatically translated from the original language text using a translation system (DeepL API).
Despite careful machine processing, translation errors cannot be ruled out.