iiinova — where your digital self keeps evolving

Felix Pultar @pultar.bsky.social · 21/09/2026

Finding a promising molecule is often not the hard part in chemistry. Figuring out how to make it is. That's what our model RetroChimera goes after. Published in @nature.com today, model and weights on GitHub (MIT). Paper: nature.com/articles/s41... Code: github.com/microsoft/re... #AIforScience

nature.com

Chemist-aligned retrosynthesis by ensembling diverse inductive bias models - Nature

Nature - Chemist-aligned retrosynthesis by ensembling diverse inductive bias models

010

Reposted by Felix Pultar

Institute of Molecular Physical Science (IMPS), ETH Zurich @imps-ethzurich.bsky.social · 07/07/2026

(1/4) The new neural network potential, AMPv3-BMS25, designed by the group of Prof. Sereina Riniker for efficient ML/MM simulations, pushes the boundaries of computational chemistry and serves as a powerful complement to generative models. @ethz.ch

111

Felix Pultar @pultar.bsky.social · 01/06/2026

Published this week, our review articles on machine learning interatomic potentials in @chimiajournal.bsky.social with @rinikerlab.bsky.social : doi.org/10.2533/chim... we put special emphasis on ML/MM approaches that further reduce computational costs compared to DFT #compchem #ml

doi.org

Leveraging the Potential of Machine-Learning Interatomic Potentials for QM/MM Simulations | CHIMIA

030

Reposted by Felix Pultar

Robert Pollice @robpollice.mstdn.science.ap.brid.gy · 15/01/2026

Are you interested in any aspect of molecular chemistry? Come and joins us for the first Groningen Molecular Chemistry Symposium (GroMoChem): gromochem.web.rug.nl We have an excellent line-up of speakers, covering a broad range of topics. Additionally, if you are within 4 years of […]

mstdn.science

Original post on mstdn.science

164

Felix Pultar @pultar.bsky.social · 12/01/2026

Ever wanted to run MD simulations of entire proteins in water with DFT accuracy? Meet AMPv3-BMS25, the latest iteration of our AMP multiscale neural network potential by @rinikerlab.bsky.social Read more in the preprints: doi.org/10.26434/che... doi.org/10.26434/che...

1145