@MoritzRSchfer1, @PythonFZ, and team introduce APAX, a high-performance JAX-based framework for building machine-learned interatomic potentials with active learning. Learn more about APAX and how they use DVC in their workflow. 👇🏽 hubs.la/Q03Pkljm0

Exciting new developments in computational chemistry! Link: esat2024.exordo.com/programm… Marcelle Spera and her team from the @Uni_Stuttgart presented a poster at the 𝟑𝟑𝐫𝐝 𝐄𝐮𝐫𝐨𝐩𝐞𝐚𝐧 𝐒𝐲𝐦𝐩𝐨𝐬𝐢𝐮𝐦 𝐨𝐧 𝐀𝐩𝐩𝐥𝐢𝐞𝐝 𝐓𝐡𝐞𝐫𝐦𝐨𝐝𝐲𝐧𝐚𝐦𝐢𝐜𝐬 (𝐄𝐒𝐀𝐓 𝟐𝟎𝟐𝟒) on using DVC to manage and track changes in molecular dynamics simulations. By applying DVC to their molecular simulations, the team could version important inputs like: 🔹Molecular structures. 🔹Force field parameters. 🔹Initial configurations. This allows for better reproducibility and transparency when running complex simulations. Computational research often involves iterating on models and data, making version control critical. But traditional tools aren't always a great fit. Kudos to Marcelle and her team for pushing the boundaries of what's possible in molecular simulations! 🧬💡