Consultancy services for drug discovery
Run molecular dynamics simulations, conduct virtual screening campaigns or train machine learning models. We do it for you.
We are the right partner:
- Unparalleled experience in structural biology and computational chemistry.
- Strong publication record in top-tier journals.
- Proven collaborations with pharmaceutical companies [1-4].
- Pioneers in Molecular Dynamics and Machine learning applied to drug discovery [5-8].
- 9.4/10 rating in Science Exchange.
Lead optimization with Biogen, Pfizer and Janssen
Predict protein-ligand binding affinity with proven accuracy.
Our predictors (KDEEP, DeltaDelta, BindScope) have been published in peer-reviewed journals and validated in data from top pharmaceutical companies. Furthermore, KDEEP won two blind subchallenges of the D3R Grand Challenge 4 and it is now used daily in a large pharma company to perform their predictions.
Protein-ligand binding with Pfizer
Sampling the active state space of a GPCR with UCB
In collaboration with UCB, we transitioned a GPCR from inactive to active state using Molecular Dynamics.
Kinases, GPCRs and other targets undergo dramatic changes to reach their active states. We have experience exploring these structural changes with unbiased simulations, and we can do it for you.
Docking and Virtual Screening with AceDock
Our docking protocol, where we used KDEEP to re-score docked poses, won 2 blind sub-challenges of the D3R Grand Challenge 4.
With our docking software, we can cover several relevant scenarios:
- Free docking: No restrictions or prior knowledge is imposed in the docking exercise. Poses are re-scored with KDEEP.
- Scaffold-hopping: Identify compounds in your library with great pharmacophoric overlap against a known binder.
- Ensemble docking: We build an ensemble of conformations for your pocket to model protein flexibility.
- Template docking: Use a known binder to guide the docking of a similar compound or series.
- Constrained docking: Impose restrictions so certain moieties in the ligand (i.e., aromatic rings) are placed in the right spot.
Let's start a conversation.
We will write you back to your email within a business day.
- Jiménez-Luna, J., Pérez-Benito, L., Martínez-Rosell, G., Sciabola, S., Torella, R., Tresadern, G., & De Fabritiis, G. (2019). DeltaDelta neural networks for lead optimization of small molecule potency. Chemical Science, 10(47), 10911–10918. https://doi.org/10.1039/c9sc04606b
- N Ferruz, S Doerr, M A Vanase-Frawley, Y Zou, X Chen, E S Marr, R T Nelson, B L Kormos, T T Wager, X Hou, A Villalobos, S Sciabola & G De Fabritiis, Dopamine D3 receptor antagonist reveals a cryptic pocket in aminergic GPCRs, in Sci Rep. 2018; 8:897. https://www.nature.com/articles/s41598-018-19345-7
- Lovera, S., Cuzzolin, A., Kelm, S. et al. Reconstruction of apo A2A receptor activation pathways reveal ligand-competent intermediates and state-dependent cholesterol hotspots. Sci Rep 9, 14199 (2019). https://doi.org/10.1038/s41598-019-50752-6
- José Jiménez, Davide Sabbadin, Alberto Cuzzolin, Gerard Martínez-Rosell, Jacob Gora, John Manchester, José Duca, and Gianni De Fabritiis; PathwayMap: Molecular Pathway Association with Self-Normalizing Neural Networks, Journal of Chemical Information and Modeling, (2018). DOI: 10.1021/acs.jcim.8b00711
- M. J. Harvey and G. De Fabritiis, An implementation of the smooth particle-mesh Ewald (PME) method on GPU hardware, J. Chem. Theory Comput., 5, 2371–2377 (2009). https://pubs.acs.org/doi/10.1021/ct900275y
- M. Harvey, G. Giupponi and G. De Fabritiis, ACEMD: Accelerated molecular dynamics simulations in the microseconds timescale, J. Chem. Theory and Comput. 5, 1632 (2009). https://pubs.acs.org/doi/10.1021/ct9000685
- J. Jiménez, S. Doerr, G. Martinez-Rosell, A.S. Rose, G. de Fabritiis. DeepSite: Protein binding site predictor using 3D-convolutional neural networks. Structural Bioinformatics, 2017, https://doi.org/10.1093/bioinformatics/btx350
- José Jiménez Luna, Miha Skalic, Gerard Martinez-Rosell, and Gianni De Fabritiis. KDEEP: Protein-ligand absolute binding affinity prediction via 3D-convolutional neural networks. Journal of Chemical Information and Modeling. (2018) DOI: 10.1021/acs.jcim.7b00650