Computational Science Laboratory

Computation applied to science

The group research interests are rooted in application of computation to solve real world problems with a view that computation and intelligence are very much the same thing. Specifically, we develop new methods, programs and algorithms that we apply to AI, drug design, protein folding, etc.

The group and the spin-off company Acellera has collaborated with major industries worldwide like Sony, Nvidia, HTC mobile, UCB, Pfizer, Biogen, Novartis, etc.


PlayMolecule is a platform for drug discovery and structural biology applications based on physics-based simulations and deep learning. Try it at:

Unity Obstacle Tower RL challenge. We classified second at the Unity obstacle tower challenge, where an agent had to navigate a complex 3d environmet and solve tasks. Here is the agent in action: Video, and the Unity blog post

LogP SAMPL 2019 challenge. We scored second to the logP small molecule blind prediction challenge.

D3R 2018 challenge. We won two sub-challenges in the D3R 2018 drug discovery blind challenge in collaboration with Acellera related to binding affinity and pose prediction of protein-ligand complexes.

High-throughput molecular dynamics In 2015 we relased the HTMD Python environment for simulation-based molecular discovery.
Molecular dynamics engine on GPUs Since 2006 ACEMD has pioneered the use of acellerator processors for general purpose molecular simulations.
Distributed computing is currently one of the two largest distributing computing project worldwide.
Industrial Spin-Offs Acellera Ltd is a spin-off created in 2006 to accelerate the transition to simulation-based discovery in drug discovery.
Community access Everybody can access most of our tools and predictors via
Scientific Publications We have published over 80 research articles.


Research Lines

Biomedicine. We use computations, as physics-based simulations and machine learning to provide novel, innovative approaches in biomedicine.

Machine Intelligence. We develop machine learning models with the aim to attain in specific environments intelligent, useful behavior using reinforcement learning and deep learning.


HTMD - HTMD is a Python platform for computational biology, including molecular simulations, docking, Markov state models, molecule manipulation, build tools for Amber and Charmm, visualization (webGL and VMD), adaptive sampling and more. Imagine setting up an entire computational experiment in a single, simple Python script.

ACEMD - ACEMD has pioneered the use of GPUs for molecular simulations allowing for high-throughput simulations and ultimately leading to HTMD. ACEMD is still one of top molecular dynamics code, simple to use with a NAMD like syntax and compatible with input files from Charmm and Amber.

Web resources

Playmolecule - Most of our methods, predictors and machine learning approaches are publicly available via this webGL enabled site.

Computational Science Laboratory GitHub - More tools are available in our github account. Follow us there.

HTMD github repository - HTMD main repository publicly accessible in github. Contribute!

The youtube channel of Acellera - Acellera posts a lot of material here


Apply for a position

We are always looking for talented people who would like to join our laboratory. We praise on diversity of expertises, e.g. mathematics, chemistry, computer science, statistics, physics, biology, biotechnology, etc. If you are a passionate, hard working, self-motivated person with the ambition to do great science, send us an email at



These positions are closed but we might have similar ones in the future.

  • PhD position - PhD in artificial neural networks in structural bioinformatics
  • PhD position - PhD in protein-protein recognition and design
  • PhD position - PhD in intrinsically disordered proteins


Gianni De Fabritiis, GRIB, Barcelona Biomedical Research Park (PRBB),
C/ Dr. Aiguader 88, 08003, Barcelona, Spain.

Email: gianni.defabritiis at