Gianni De Fabritiis
@gdefabritiis.bsky.social
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
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
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: arxiv.org/abs/2510.17826
October 22, 2025 at 4:39 PM
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: arxiv.org/abs/2510.17826
First long waited summer day
April 6, 2025 at 5:54 PM
First long waited summer day
January 21, 2025 at 6:43 PM
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/...
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/...
November 19, 2024 at 3:16 PM
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/...
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/...