The 28th European Congress of Endocrinology (ECE) starts tomorrow
Meeting Announcement
Now in its 28th year, the European Congress of Endocrinology (ECE) 2026 commences on Saturday 9 May and runs until Tuesday 12 May. The Congress will bring together endocrine specialists from across Europe and the rest of the world to meet, collaborate and celebrate endocrinology at the Prague Congress Centre in Prague, Czech Republic. This year’s Congress will also celebrate the 20th Anniversary of the European Society of Endocrinology (ESE) since the formation of the Society in 2006.
"Ultra-Processed Food and Health: From Mechanisms to Actions” brought together many of the world’s leading experts to examine one of the most pressing topics in nutrition science.
The symposium convened an international group of researchers, clinicians and policy experts to explore the rapidly evolving science surrounding ultra-processed foods and their impact on human health. Discussions spanned the biological mechanisms linking ultra-processed foods to chronic disease, the gaps in available research, the role of the food environment and industry practices, and opportunities for policy and public health action.
Insilico Medicine announced that its research paper, “When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs,” has been accepted for presentation at the International Conference on Machine Learning 2026. The study challenges conventional retrosynthesis benchmarking approaches that rely on single “ground-truth” answers and Top-K accuracy metrics, which may not reflect the multi-solution nature of real-world chemistry.
The paper introduces ChemCensor, a chemistry-aware evaluation metric designed to assess model performance based on reaction centers and functional groups, aligning more closely with expert human reasoning. Additional contributions include the CREED dataset, comprising 6.4 million validated reactions; benchmarking results from the C3LM model; and the URSA-expert-2026 dataset, an expert-annotated benchmark designed to reduce data leakage and improve evaluation rigor.
The research supports the development of more realistic and scalable training and evaluation frameworks for AI-driven retrosynthesis and drug discovery. Supporting materials will be made publicly available to promote transparency and reproducibility.