Researchers on the forefront of creating machine studying strategies for chemical discovery

The discovery and formulation of recent medication, antivirals, antibiotics and generally chemical compounds with tailor-made properties is a protracted and painstaking course of. Interdisciplinary analysis on the crossroads of biochemistry, physics and pc science can change this. The growth of machine studying (ML) strategies, mixed with first ideas of quantum and statistical mechanics and educated on more and more obtainable molecular huge datasets, has the potential to revolutionise the method of chemical discovery.

“Chemical discovery and machine learning are bound to evolve together, but achieving true synergy between them requires solving many outstanding challenges,” says Alexandre Tkatchenko, Professor of Theoretical Chemical Physics on the University.

Machine studying to assist establish drug candidates

The University initiated a collaboration with Belgian firm Janssen Pharmaceuticals in spring 2020 to develop novel ML strategies for figuring out compounds which have a powerful therapeutic potential (additionally referred to as drug candidates). So far, ML approaches have been developed for small molecules. This analysis challenge goals to increase the structure and transferability of quantum mechanics-based machine studying approaches to massive molecules of pharmaceutical significance.

“The generation of novel chemicals with activity on relevant biological targets is the core business of pharmaceutical companies. Machine learning approaches have the potential to speed up the process and reduce failure rates in drug discovery. Having been approached by a leading pharmaceutical company to work together in identifying drug candidates is a gratifying sign of the industrial recognition of our expertise,” feedback Dr. Leonardo Medrano-Sandonas, a postdoctoral researcher in Prof. Tkatchenko’s group.

Partner in an Innovative Training Network funded by the European Commission

Together with three massive European pharma corporations (Bayer, AstraZeneca, Janssen), the chemical firm Enamine and ten tutorial companions with experience in computational drug design, Prof. Tkatchenko has been granted the Marie Sk?odowska-Curie Actions – Innovative Training Network grant for the challenge Advanced machine studying for Innovative Drug Discovery (AIDD) for the interval 2021 – 2023. This challenge goals to develop revolutionary ML strategies to contribute to an built-in “One Chemistry” mannequin that may predict outcomes starting from molecule era to synthesis and perceive how you can intertwine chemistry and biology to develop new medication.

Here scientific experience joins forces with medicinal and artificial chemistry experience of the commercial companions, and advantages from massive precious datasets. For the primary time, all methodological developments will likely be obtainable open supply. The coaching community will put together a era of scientists who’ve expertise each in machine studying and chemistry to advance medicinal chemistry.

“Making accurate predictions using machine learning critically depends on access to large collections of high-quality data and domain expertise to analyse them,” explains Prof. Tkatchenko. “Putting our forces together is a first step towards chemical discovery revolution driven by machine learning”.

The discipline of machine studying for chemical discovery is rising and substantial advances are anticipated to occur within the close to future. Prof. Tkatchenko has lately printed an article within the journal Nature Communications during which he discusses current breakthroughs on this discipline and highlights the challenges for the years to come back. The article is obtainable on-line.


Contact: Laura Bianchi, T. (+352) 46 66 44 9451, E.

About the University of Luxembourg The University of Luxembourg is a global analysis college with a distinctly multilingual and interdisciplinary character. The University was based in 2003 and counts greater than 6,700 college students and greater than 2,000 workers from all over the world. The University’s colleges and interdisciplinary centres give attention to analysis within the areas of Computer Science and ICT Security, Materials Science, European and International Law, Finance and Financial Innovation, Education, Contemporary and Digital History. In addition, the University focuses on cross-disciplinary analysis within the areas of Data Modelling and Simulation in addition to Health and System Biomedicine. Times Higher Education ranks the University of Luxembourg #three worldwide for its “international outlook,” #12 within the Young University Ranking 2019 and among the many prime 250 universities worldwide.

Disclaimer: AAAS and EurekAlert! are usually not accountable for the accuracy of stories releases posted to EurekAlert! by contributing establishments or for using any info via the EurekAlert system.


Please enter your comment!
Please enter your name here