Lightnews — Scholar-powered news

Gianni De Fabritiis

@gdefabritiis.bsky.social

1.8K followers 110 following 23 posts

Computer Simulations, Computational Intelligence, AI. Research professor and interim CEO acellera.com. Lab: www.compscience.org Scholar: https://scholar.google.com/citations?hl=en&user=-_kX4kMAAAAJ&view_op=list_works&sortby=pubdate

scholar.google.com

Posts Media Videos Starter Packs

Gianni De Fabritiis @gdefabritiis.bsky.social · May 7

Check out AceFF 1.1

huggingface.co/Acellera/Ace...

Acellera/AceFF-1.1 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

1 3

Gianni De Fabritiis @gdefabritiis.bsky.social · May 5

Heading to Boston for the free energy workshop...
www.feworkshop.org

2025 Workshop on Free Energy Methods in Drug Design

www.feworkshop.org

Gianni De Fabritiis @gdefabritiis.bsky.social · Apr 6

First long waited summer day

Reposted by Gianni De Fabritiis

PlayMolecule @playmolecule.com · Mar 31

📂 Stay organized while exploring molecules in open.playmolecule.com! Group them by clicking the Group button in the menu bar. Toggle the visibility of all systems in a group by clicking on it. Watch the video to see how grouping simplifies your molecular exploration!

1 2

Reposted by Gianni De Fabritiis

PlayMolecule @playmolecule.com · Mar 12

🐍 Dive into molecule analysis with our Python terminal in open.playmolecule.com! Interact with loaded molecules using #Moleculekit. Execute Python code within the terminal to obtain information of your systems, apply filters, perform calculations, and more. Watch the demo!

1 3

Gianni De Fabritiis @gdefabritiis.bsky.social · Jan 29

I am really happy to announce our collaboration between Acellera Therapeutics and Psivant Therapeutics to push the frontiers of AI-driven drug discovery!
www.linkedin.com/posts/gdefab...

Gianni De Fabritiis on LinkedIn: #ai #molecularreasoning #quantumchemistry #drugdiscovery

I am really happy to announce our collaboration between Acellera Therapeutics and Psivant Therapeutics to push the frontiers of AI-driven drug discovery!…

www.linkedin.com

Gianni De Fabritiis @gdefabritiis.bsky.social · Jan 21

Interested in reasoning agents?

t.co/Ax9RtOLDCG

@andrew.diffuse.one

2 11

Gianni De Fabritiis @gdefabritiis.bsky.social · Jan 7

Aceforce 1.0 is out and downloadable from Huggingface. It covers all interesting elements and charged molecules. Tested for relative binding affinity calculations. Just version 1.0, more to come.

www.businesswire.com/news/home/20...

Acellera Therapeutics Unveils AceForce 1.0: A Novel Family of Next-Generation Neural Network Potential Accelerating Drug Discovery

Acellera Therapeutics, a pioneer in computational chemistry and AI-driven drug discovery, today announced the launch of AceForce 1.0, its groundbreaki

www.businesswire.com

3 15

Gianni De Fabritiis @gdefabritiis.bsky.social · Jan 6

Gianni De Fabritiis @gdefabritiis.bsky.social · Dec 24

Gianni De Fabritiis @gdefabritiis.bsky.social · Dec 9

BricksRL at Neurips. I am not going this year, but don't miss our spotlight paper/poster on RL with Lego for robotics.

vmoens @vmoens.bsky.social · Dec 9

I'm teaming up with Sebastian Ditter & @gdefabritiis.bsky.social to present our paper on BricksRL, a library that enables control of Lego robots using #PyTorch

Reposted by Gianni De Fabritiis

Frank Noe @franknoe.bsky.social · Dec 6

Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.

www.biorxiv.org/content/10.1...

21 150 440

Gianni De Fabritiis @gdefabritiis.bsky.social · Dec 4

ACEMD v4 is out with the integration of neural network potentials. More to come soon.

Acellera @acellera.com · Dec 4

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: www.acellera.com/blog/release...

Release of ACEMD 4.0.0: Advancing Machine Learning for Molecular Dynamics Simulations - Acellera Blog

www.acellera.com

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 26

I liked part I. Let's read part II.

arxiv.org/abs/2411.16489

O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of knowledge distillat...

arxiv.org

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 24

How did you make that? Manually?

1 1

Reposted by Gianni De Fabritiis

Mark Riedl @markriedl.bsky.social · Nov 22

Alibaba has their own version on GPT-o1. This might be the best description of “o1-type”systems so far arxiv.org/abs/2411.14405

Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Currently OpenAI o1 has sparked a surge of interest in the study of large reasoning models (LRM). Building on this momentum, Marco-o1 not only focuses on disciplines with standard answers, such as mat...

arxiv.org

8 38 270

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 20

After Martini, Espresso and Grappa methods/models in Italian drink names. Amaro was long overdue.

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

In Spring I come to ACS, you can get me a beer and we are even.

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

You are welcome!

1 2

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

The next one will be called Greg.

1 2

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

AMARO’s transferability was tested on unseen, fast-folding proteins like Trp-Cage and α3D. It effectively recovered free energy landscapes for most

This is version 1. Model fully available.

github.com/compsciencel...

GitHub - compsciencelab/amaro

Contribute to compsciencelab/amaro development by creating an account on GitHub.

github.com

1 1

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

AMARO leverages TensorNet, an O(3)-equivariant neural network, and omits hydrogen atoms to reduce complexity.

Trained on the mdCATH dataset, AMARO excels in scalability and generalization. It predicts forces with minimal error even for larger domains (>150 residues).

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics
A novel machine-learning-based force field for protein thermodynamics. It uses an all-heavy-atom approach without hydrogens to simplify simulations while maintaining key dynamics.
pubs.acs.org/doi/10.1021/...

3 17 84

Gianni De Fabritiis @gdefabritiis.bsky.social · Nov 19

Love to join in. thanks.

Reposted by Gianni De Fabritiis

Willie Neiswanger @willieneis.bsky.social · Nov 10

I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!

go.bsky.app/AcP9Lix

160 90 250