Science That Delivers Real Discovery Value

At Virtual Discovery, computational science drives our approach to drug discovery. Our scientific infrastructure and methodologies are designed to explore vast chemical space to discover winning molecules.

60+

Billion

Screen billions of molecules from libraries like Enamine Real, ZINC15, or your own custom libraries

"Undruggable"

Targets

Work on challenging targets like protein-protein interactions, transmembrane proteins (e.g., GPCRs), etc.

Scale &

Speed

Go beyond conventional HTS and explore vast chemical spaces for a fraction of the cost and time

We provide computational discovery services, from molecular dynamics simulations and ultra-large virtual screening to AI-driven design and quantum drug discovery. Using VirtualFlow, proprietary models, and the latest open-source tools, we efficiently explore billions of drug-like molecules to help biotechnology companies identify high-quality hits and optimize leads faster.

Interested in the methodology behind VirtualFlow?

VirtualFlow 2.0: https://www.biorxiv.org/content/10.1101/2023.04.25.537981v1
VirtualFlow 1.0: https://www.nature.com/articles/s41586-020-2117-z

Virtual Discovery Excels in CACHE Challenge #1

The CACHE Challenge evaluates the efficacy of various computational techniques for hit identification. In Challenge 1, participants applied their computational method of choice to predict which small molecule ligands bind to the LRRK2 WDR Domain, a Parkinson’s disease target.

Our team participated and finished as a top-performing team. They conducted an ultra-large virtual screen on the target using the REAL Database from Enamine. The entire workflow consisted of MD simulations, ultra-large virtual screens, fingerprint similarity searches, and conformational ensembling to identify the candidate molecules. They obtained 10 active compounds in the first round and were able to get analogs for 3 hit compounds in the second round.

https://cache-challenge.org/challenges/predict-hits-for-the-wdr-domain-of-lrrk2

KEAP1-NRF2

"To demonstrate the power of VirtualFlow, we screened more than 1 billion compounds and identified a set of structurally diverse molecules that bind to KEAP1 with submicromolar affinity. "

Gorgulla, C., Boeszoermenyi, A., Wang, ZF. et al. An open-source drug discovery platform enables ultra-large virtual screens. Nature 580, 663–668 (2020). https://doi.org/10.1038/s41586-020-2117-z

SARS-Cov-2

"In this unprecedented structure-based virtual campaign, we screened roughly 1 billion molecules against each of 40 different target sites on 17 different potential viral and host targets. In addition to targeting the active sites of viral enzymes, we also targeted critical auxiliary sites such as functionally important protein-protein interactions. "

Gorgulla C, Padmanabha Das KM, Leigh KE, Cespugli M, et al. A multi-pronged approach targeting SARS-CoV-2 proteins using ultra-large virtual screening. iScience. 2021 Feb 19;24(2):102021. doi: 10.1016/j.isci.2020.102021. Epub 2021 Jan 5. PMID: 33426509; PMCID: PMC7783459.

csNox5

"Here, we describe fully validated human NOX inhibitors, obtained from an in silico screen, targeting the active site of Cylindrospermum stagnale NOX5 (csNOX5). The hits are validated by in vitro and in cellulo enzymatic and binding assays, and their binding modes to the dehydrogenase domain of csNOX5 studied via high-resolution crystal structures. "

Reis, J., Gorgulla, C., Massari, M. et al. Targeting ROS production through inhibition of NADPH oxidases. Nat Chem Biol 19, 1540–1550 (2023). https://doi.org/10.1038/s41589-023-01457-5

Image PBD DOI: https://doi.org/10.2210/pdb5O0T/pdb

hDLG1-Tax-1 protein-protein interaction

"In order to identify potential inhibitors of the Tax-1-hDLG1 interaction, we performed an ultra-large virtual screening of small molecule libraries using crystal structures of hDLG1 PDZ-peptide complexes as an input. In particular, we screened over 10 million commercially-available compounds from the ZINC15 library using VirtualFlow platform (Gorgulla et al., 2020) and selected 212 candidate molecules with high docking scores for further experimental validation." - Maseko, 2023

Sibusiso B. Maseko, Yasmine Brammerloo, Inge Van Molle, Adrià Sogues, Charlotte Martin, Christoph Gorgulla, Estelle Plant, Julien Olivet, Jeremy Blavier, Thandokuhle Ntombela, Frank Delvigne, Haribabu Arthanari, Hiba El Hajj, Ali Bazarbachi, Carine Van Lint, Kourosh Salehi-Ashtiani, Han Remaut, Steven Ballet, Alexander N. Volkov, Jean-Claude Twizere, Identification of small molecule antivirals against HTLV-1 by targeting the hDLG1-Tax-1 protein-protein interaction, Antiviral Research, Volume 217, 2023, 105675, ISSN 0166-3542, https://doi.org/10.1016/j.antiviral.2023.105675.

Cream and Brown Photographic Beauty Site Launch Website_edited_edited_edited.jpg

μ-opioid receptor

"Here, this multi-objective optimal affinity approach is presented, together with a virtual drug discovery pipeline for its practical implementation. When applied to finding pH-specific drug candidates, it combines protonation state-dependent structure and ligand preparation with high-throughput virtual screening. We employ this pipeline to characterize a set of MOR agonists identifying a morphine-like opioid derivative with higher predicted binding affinities to the MOR at low pH compared to neutral pH."

- Secker, 2023

Secker, C., Fackeldey, K., Weber, M. et al. Novel multi-objective affinity approach allows to identify pH-specific μ-opioid receptor agonists. J Cheminform 15, 85 (2023). https://doi.org/10.1186/s13321-023-00746-4

Quantum-Enhanced Discovery of KRAS Inhibitors

The team developed a hybrid quantum–classical generative model to design small molecules capable of inhibiting KRAS. They combined a dataset of known inhibitors with ultra-large virtual screening of the Enamine REAL database, generating over 1 million training compounds using methods like VirtualFlow 2.0, STONED, and Chemistry42. The workflow produced 15 candidate molecules, of which 2 showed strong potential for development as KRAS inhibitors. This work highlights how quantum-enhanced algorithms can generate experimentally validated hits, complementing classical computational approaches in drug discovery.

Ghazi Vakili, M., Gorgulla, C., Snider, J. et al. Quantum-computing-enhanced algorithm unveils potential KRAS inhibitors. Nat Biotechnol 43, 1954–1959 (2025). https://doi.org/10.1038/s41587-024-02526-3

Image by Thomas Splettstoesser (www.scistyle.com)

Science That Delivers Real Discovery Value

Virtual Discovery Excels in CACHE Challenge #1

csNox5

Quantum-Enhanced Discovery of KRAS Inhibitors

Join Our Newsletter