ICREA research professor, associate professor, and group leader of the Computational Science Laboratory at UPF, and CEO at Acellera Therapeutics Inc. Bachelor's degree with honors in applied mathematics (1997) from the University of Bologna and a Ph.D. from the University of London (2002). I worked for the CINECA supercomputing center in Italy (1998-1999) and was a postdoctoral researcher at University College London (2003-2006). In 2006, I founded Acellera Ltd where I currently act as a CSO. In 2008 I won a tenure-track Ramon y Cajal research position and later the national I3-tenured program. In 2014 I became an ICREA Research Professor. I performed research stays as a visiting professor at Stanford University and UCLA. I published over a hundred articles in high-ranking international journals with an h-index of 54 and over 12k citations with ~2k citations per year in 2024.
Research interests
The group's research interests are rooted in the applications of computation to science, where we regard intelligence as a form of computation itself.
1) Molecular simulation and machine learning. We use computation such as physics-based simulations and modern machine learning to provide novel, innovative methodological approaches in biomedicine.
2) Computational intelligence. We investigate machine learning methods that would bring machine intelligence closer to human-level intelligence. We train intelligence agents using reinforcement learning.
Selected publications
Zariquiey FS, Galvelis R, Gallicchio E, Chodera JD, Markland TE, De Fabritiis G 2024, '- Enhancing Protein-Ligand Binding Affinity Predictions Using Neural Network Potentials', Journal of chemical information and modeling, 64 - 5 - 1481 - 1485 - .
- Pelaez RP, Simeon G, Galvelis R, Mirarchi A, Eastman P, Doerr S, Thölke P, Markland TE, De Fabritiis G 2024, 'TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations', Journal of chemical theory and computation, 20 - 10 - 4076 - 4087.
- Mirarchi A, Peláez RP, Simeon G & De Fabritiis G 2024, 'AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics', Journal of chemical theory and computation, 20 - 22 - 9871 - 9878.
- Mirarchi A, Giorgino T & De Fabritiis G 2024, "mdcath: A large-scale md dataset for data-driven computational biophysics" Scientific Data, 11 - 1299.