Preprint release 😀 of "Speak to a Protein," an AI co-scientist that facilitates data gathering and analysis in an interactive collaborative session. It is quite amazing to use. Preprint: https://t.co/TqY4fJpAEV

Moving forward towards reasoning models

Learn how to set up and execute protein-ligand simulations with AceForce in our step-by-step tutorial: https://t.co/wuhubRX1zQ

AceForce 1.0 isn’t just for RBFE calculations—it’s also enabling advanced protein-ligand simulations using NNP/MM methodologies. Discover how AceForce enhances accuracy and efficiency in computational drug discovery.

AceForce 1.0 is here. Our neural network potential is designed to enhance drug discovery with quantum-level accuracy. AceForce 1.0 delivers precise predictions, reduces computational costs, and integrates seamlessly into workflows. Discover more: https://t.co/VoBLQ3vi6H

ACEMD 4.0.0 is here! Now featuring seamless integration of Neural Network Potentials (NNP) with Molecular Mechanics (MM) for advanced hybrid simulations. Key features: 🔹 Simplified NNP/MM simulations 🔹 Python API & backward compatibility Explore more:

Curious about our tools for drug discovery? Join us on Nov 6 at @ccpbiosim's Industry Talk, where we'll discuss how we use MD simulations in our QuantumBind platform. Register for free here: https://t.co/ssd7CjdvEa

Recent results from our new QuantumBind-ABFE protocol showed strong alignment with experimental outcomes in our latest RIPK2 campaign, with prediction errors of 0.6 and 1.7 kcal/mol for our two nanoMolar hits, ranking them at the top of the list.

Great news! Our new PlayMolecule drug discovery protocol identified 2 compounds with nanomolar activity (40 & 85 nM) for RIPK2 and >1000 selectivity vs RIPK1. With a 40% hit rate and a 1-week turnaround, we're pushing the limits of rapid, AI-driven discovery.

This afternoon, our CEO, @gdefabritiis , will be speaking at the @CECAMevents Flagship WS on how to enhance  the accuracy of relative binding free energies via machine learning potentials

ACEGEN: Reinforcement Learning of Generative Chemical Agents for Drug Discovery #DrugDiscovery https://t.co/cKQgurbBVD @11carlesnavarro @MacMaje @gtresadern @VincentMoens @gdefabritiis @acellera #JCIM Vol64 Issue15 #MachineLearning #DeepLearning

ACEGEN is now oficially published in @JCIM_JCTC. Check it out! ➡️

Gianni De Fabritiis is attending the L2M3 Workshop at CECAM-HQ in Lausanne! He'll showcase as well Acellera's work on applying chemical language models for chemistry. Stay tuned for insights and updates! #LLMs #Chemistry #Acellera #Innovation @CECAM_Org @gdefabritiis

We are thrilled to announce that Professor Andrew White (@andrewwhite01), an AI-driven drug discovery pioneer, has joined Acellera Therapeutics' Advisory Board. Welcome, Andrew!

#ACEFORCE coming along nicely. Scan with the Aceforce DFT model on the Sellers torsion scan benchmark and we are still improving it.

Acellera's CEO @gdefabritiis will give a lecture today on machine learning potentials at

Acellera's CEO @gdefabritiis will give a lecture today on machine learning potentials at

Trying to build nice graphics for a presentation? We are always working at improving the #PlayMolecule viewer. Try https://t.co/FhZwqIBypk.

Discover how Acellera Tx is leveraging AI-driven drug discovery to deliver efficient target-to-hit insights within weeks, achieving a hit rate of over 10% across various target families with our cutting-edge technology. 📅 Book a meeting to learn more: https://t.co/Hh6dgLWfck

🚀 ACEGEN by Acellera Therapeutics Our new toolkit for generative drug design that harnesses #ReinforcementLearning. Designed for robustness and efficiency, ACEGEN accelerates the discovery of desirable molecules. Learn more 👉 https://t.co/eHKWlSJmgD #DrugDiscovery #AI #Pharma