Validation of the Alchemical Transfer Method for the Estimation of Relative Binding Affinities of Molecular Series #MolecularSimulations #drugdiscovery pubs.acs.org/doi/10.1021/ac… Maciej Majewski @GallicchioEmi Gianni De Fabritiis Vol63 Issue8 #JCIM #compchem

You can find the ATMMetaForce OpenMM plugin here! github.com/Gallicchio-Lab…

"Top-down machine learning of coarse-grained protein force-fields" General-purpose neural network potentials trained on 15,000 proteins are compared to protein-specific potentials arxiv.org/abs/2306.11375

1/🧵 Happy to share my first preprint! "Top-down machine learning of coarse-grained protein force-fields" We've trained a general and protein specific coarse-grained neural network potentials (NNPs) using only protein structures and short molecular dynamic trajectories.

We're expanding our AI team specialising in Biologics. Contact me if you are looking for a job. #Sanofi #job #biologics #ML

⁦Maciej Majewski⁩ ⁦Gianni De Fabritiis⁩ Cecilia Clementi ⁦Acellera Therapeutics⁩ present machine learning coarse-grained potentials of protein thermodynamics. ⁦Nature Communications⁩ #moleculardynamics #coarsegraining #BiotechNatureComms nature.com/articles/s4146…

Happy to share that my latest paper was published in Nature Communications ! 🥳 #MolecularDynamics #MachineLearning #CoarseGraining #MD #ML #NNP #NatureComms #BiotechNatureComms

👩‍💻 TorchMD: A Deep Learning Framework for Molecular Simulations #JCTC #OpenAccess 🔓 go.acs.org/6iV #MolecularMechanics 📚🔬🖥️

We are thrilled to share our new publication pubs.acs.org/doi/full/10.10… 📚 Using only protein structures and short trajectories, we have trained coarse-grained NNPs capable of maintaining native structures and folding proteins. Thanks to @11carlesnavarro, Maciej Majewski and Gianni De Fabritiis!

Excited to share our latest review article on advancing the frontier of #DrugDiscovery through #MachineLearning! We delve into ML algorithms for predicting molecular properties of small molecules, a key step towards computable drug discovery. 🧪🖥️ 🔗 doi.org/10.1016/j.aich…

I am excited to present this work, result of a 4-year big collaborative project: arxiv.org/abs/2310.18278 #MachineLearning a transferable bottom-up protein force field, trained on force data from over all-atom MD simulations, using physical priors and graph neural networks.🧵⬇️

Great opportunity for fresh BSc graduates to do an internship at Sanofi in Barcelona! Feel free to reach out if you have any questions.

In #ACEGEN, we take advantage of the #TorchRL library of #PyTorch to do generative chemistry. It implements #REINFORCE, #REINVENT, #A2C, #PPO, #PPOD etc. A solid base for #RL in drug discovery. Code available under MIT. Acellera Therapeutics arxiv.org/abs/2405.04657

🏳️🏳️🏳️🏳️🏳️🏳️ OK, ok; my bad! ml4lms.bio submission deadline extended to May 23rd. Remember: it's **UP TO** 5 pages. Subit any below that and you're fine! Just make it sensible, topical & exciting.

ml4lms.bio will be next friday. We haveso many quality submissions -- come meet the authors! Likewise, we have a fantastic lineup, prizes, food,... Everything to set you up for the next exciting paper! Also, sign up for the social ASAP: lu.ma/rojc95k1

GPUs are *fast* at aligning protein sequences (and profiles!). 178x faster than JackHMMER! In ColabFold, 23x faster end-to-end compared to AlphaFold2 reaching the same accuracy! You get immediate speedups for all methods leveraging MSAs, from DCA, to PoET, and even AlphaFold3!

Michael Heinzinger and I are seeking talented postdocs to support for the Marie Skłodowska-Curie Fellowship! Join our international AI+biology team, collaborate on protein design, and access top labs in the US & EU. Interested? Apply by July 15! Details: machine.learning.bio/news/msca

Our development of machine-learned transferable coarse-grained models in now on Nat Chem! doi.org/10.1038/s41557… I am so proud of my group for this work! Particularly first authors Nick Charron, Klara Bonneau, Aldo S. Pasos-Trejo, Andrea Guljas.