Alternatieve media zijn overal, maar zinnig onderzoek ernaar is schaars. Onlangs las ik een wetenschappelijk artikel waarin werd beweerd dat het erg ingewikkeld is geworden om te bepalen wat journalis...

In recognition of her pioneering research in chemical structure analysis, visionary educational leadership, and enduring dedication to advancing scientific collaboration, Professor Val Gillet has been awarded the 2025 Mike Lynch Award by the Trustees of the CSA Trust. The Trustees are proud to honor Professor Gillet for her outstanding and innovative contributions to the field of Chemoinformatics. Her influential body of work – widely cited and highly regarded – has shaped the Chemoinformatics landscape and driven progress in pharmaceutical research and development. In parallel with her research achievements, Professor Gillet has played a central role in building and refining the Chemoinformatics educational program at the University of Sheffield. Under her supervision, the program has earned international recognition as a hub of excellence for research and training. She is also co-author of a foundational textbook that remains a key reference in the field. Beyond her academic accomplishments, Professor Gillet has been instrumental in fostering collaboration and visibility within Chemoinformatics. Her longstanding support of the Cheminformatics Conference in Sheffield and the International Conference on Chemical Structures in Noordwijkerhout has helped elevate them to the field’s most prominent international gatherings. Val Gillet is a Professor of Chemoinformatics at the University of Sheffield, where she leads the Chemoinformatics Research Group within School of Information, Journalism and Communication. https://www.linkedin.com/in/val-gillet-15a60429/ https://www.sheffield.ac.uk/ijc/people/val-gillet The CSA Trust is an internationally recognized, registered charity that promotes education, research, and development in fields related to chemical structures and cheminformatics. ### Share this: * Click to share on X (Opens in new window) X * Click to share on Facebook (Opens in new window) Facebook * Like Loading... ### _Related_

Het kabinet zou bij de bouw van duurzame energieprojecten een uitzondering moeten maken op de stikstofregels, vinden betrokken bedrijven.

Protest hoort bij het Praesidium Libertatis. Maar als Joodse studenten niet meer naar college durven, botst dat met alle academische idealen en vrijheden, betoogt Sense Jan van der Molen.

Het college van bestuur wil dat beurs- en buitenpromovendi een vast bedrag gaan betalen. Ook worden PhD’s die te weinig geld meebrengen geweerd. ‘Wordt dit gebruikt om de gehate bezuinigingen op te va...

Learn to program, gain knowledge of AI methods, or use it in a research project at the LACDR. With the introduction of the innovative digital learning environment ‘Digital Labcoat’, Biopharmaceutical ...

More than three billion years of evolution have produced an image of biology encoded into the space of natural proteins. Here we show that language models trained at scale on evolutionary data can gen...

The Faculty of Science and the Leiden Academic Center for Drug Research are looking for a Technician in Artificial Intelligence and computational drug discovery (0.8-1.0 fte) Project description Withi...

Researchers in the MIT Jameel Clinic for Machine Learning in Health developed a fully open-source biomolecular structure prediction model that achieves state-of-the-art performance, at the level of Al...

Het gerechtshof concludeert dat niet bewezen kan worden dat de dierenactivisten de staldeuren hebben geforceerd om binnen te komen.

In rational drug discovery, both free energy of binding and the binding half-life (koff) are important factors in determining the efficacy of drugs. Numerous computational methods have been developed ...

Building reliable and robust quantitative structure–property relationship (QSPR) models is a challenging task. First, the experimental data needs to be obtained, analyzed and curated. Second, the numb...

Crystallographic fragment screening has become highly efficient, overcoming previous challenges of low throughput and time consumption, due to advances in synchrotron technology and the establishment...

Recent advancements in deep learning and generative models have significantly expanded the applications of virtual screening for drug-like compounds. Here, we introduce a multitarget transformer model, PCMol, that leverages the latent protein embeddings derived from AlphaFold2 as a means of conditioning a de novo generative model on different targets. Incorporating rich protein representations allows the model to capture their structural relationships, enabling the chemical space interpolation of active compounds and target-side generalization to new proteins based on embedding similarities. In this work, we benchmark against other existing target-conditioned transformer models to illustrate the validity of using AlphaFold protein representations over raw amino acid sequences. We show that low-dimensional projections of these protein embeddings cluster appropriately based on target families and that model performance declines when these representations are intentionally corrupted. We also show that the PCMol model generates diverse, potentially active molecules for a wide array of proteins, including those with sparse ligand bioactivity data. The generated compounds display higher similarity known active ligands of held-out targets and have comparable molecular docking scores while maintaining novelty. Additionally, we demonstrate the important role of data augmentation in bolstering the performance of generative models in low-data regimes. Software package and AlphaFold protein embeddings are freely available at https://github.com/CDDLeiden/PCMol.