Afnan holds a bachelor’s degree in “biomedical sciences” with specialization in “computational biology” from the University of Science and Technology at Zewail City. She finished her master’s degree in “bioinformatics” at Saarland University. She joined our lab in October 2023 as a PhD candidate in collaboration project with BASF. She will work on the development of deep learning models, especially, transformer models, to predict molecular properties of small molecules and generate molecules with specific non-toxic properties.
Read more
We are happy to annouce that Katharina successfully submitted her bachelor thesis ‘Novel Kinase Ligand Generation using Subpocket-Based Docking’. Within this thesis, we developed an approach to automatically and efficiently generated novel kinase inhibitors using the structural information of the protein kinase target of interest. We make use of the prior knowledge about kinase ligands and the information on functional important subpockets/regions of the highly conserved kinase binding pocket.
Katharina will continue her work as a student researcher at the Volkamer Lab to refine and improve the pipeline, e.
Read more
This year’s RDKit user group meeting was held in Mainz from 20th-22nd of September 2023. We presented the TeachOpenCADD Deep Learning extension at the poster session, in addition to Andrea giving a lightning talk about the project. Michael and Joschka (from Prof. Verena Wolf’s lab) presented their current project Kinodata-3D in a lightning talk. It was a great opportunity to hear about RDKit updates and meet the community.
Read more
This year’s EUROPIN Summer School on Drug Design was organized by the Pharmacoinformatics research group in Vienna from 10th-15th of September 2023. Floriane and Paula attended and presented the TeachOpenCADD Deep Learning extension at the poster session. In addition, as part of the EUROPIN PhD program, they both gave their introductory talks presenting their current research projects. Floriane talked about her machine learning approach for endocrine activity prediction using morphological fingerprints.
Read more
We are thrilled to announce the release of TeachOpenCADD Deep Learning (DL) Edition, an expansion of TeachOpenCADD platform! If you are not familiar with TeachOpenCADD platform, more information is provided on its website or here.
The DL edition offers a comprehensive introduction to various deep learning topics with a focus on its application to drug discovery tasks. It empowers learners to explore and understand various concepts in DL field accomodating beginner users to advanced levels.
Read more
Our Berlin team members had the long-awaited opportunity to visit Saarbrücken. Volkamer lab team finally met face-to-face, moving beyond the realm of virtual meetings and creating bonds that strengthens our collaborations and will enrich our work dynamics.
More is yet to come!
Read more
Have a look on our newest publication presenting a method to generate and validate Virtual Control Groups (VCGs) in systemic toxicity studies. This paper highlights the impact of anesthetics on measured electrolytes in animals and presents how these anesthetic protocols can affect the performance of virtual control groups.
This article was published by Alexander, our PhD student at Bayer Pharmaceuticals as a member of the eTRANSAFE Virtual Control Groups team.
Read more
Great collaborative work with IBM research and ETH Zürich is now published in Digital discovery. The model for molecular property prediction is validated on the large proprietary toxicity dataset from our previous study (Webel, 2020), uses uncertainty to improve reliability, reveals cytotoxic motifs via attention and outperforms existing approaches!
You can check the paper on Born, 2023 and the code of the model is available here.
Read more
Floriane holds a bachelor’s degree in life science and bioinformatics and a master’s degree in bioinformatics and in Silico drug design from the University of Paris. She joined our lab in February 2023 as a PhD candidate to be part of the BMBF-funded MORPHEUS project. She will work on the development of deep learning models to predict the effects of substances and identify characteristic fingerprints based on morphological (cell painting) and molecular input data.
Read more
Take a look at our newest opinion paper Machine learning for small molecule drug discovery in academia and industry.
Great collaboration with academic and industry colleagues discussing advances and challenges in molecular machine learning. Despite common overarching goals, we highlight the differences between academic and industry to improve models for e.g. drug selection and share ideas to improve collaborations.
Thanks to all co-authors for working together on this project with such enthusiasm!
Read more