Technology & Software
Change the way you search
It is easy to get lost in the vast amount of bioinformatics information available to us today. A targeted and novel approach is crucial for true discoveries. To more efficiently identify new drug candidates or enzymes, we need to change how we search and go beyond traditional algorithms and types of data.
By coupling our patented CatalophoreTM technology to state-of-the-art conventional bioinformatics approaches as well as artificial intelligence, we mine structural and sequence databases using three-dimensional (3D) search templates called “catalophores” (i.e., carrier of the catalytic function) defined by point clouds of physico-chemical features.
Novel enzymes identified by this technique do not necessarily share a common structure or sequence basis with their employed counterparts. Therefore, they potentially feature altered protein properties, such as thermostability, robustness, substrate spectrum, selectivity, and specificity.
Our platform can improve your performance within wet-chemical lab efforts by minimizing in-vitro screening for enzymes. An in-silico approach makes it possible to reduce time to market significantly.
The space within
Beyond the surface
While Catalophore is used to explore cavities, our Halo technology explores the surface of a protein. For productive protein-protein interaction to occur, specific phyico-chemical conditions need to be given. A Halo can be seen as external point cloud depicting the surface environment in an extremely detailed way. A large number of different surface properties can be calculated.
Catalophore Cavity
When inner values count
With the CatalophoreTM point-cloud technology, we take a closer look at the “empty space” in a protein. Active sites and cavities have a unique physico-chemical interior that is essential for a specific reaction to proceed. Starting at a given structure of a protein, our CatalophoreTM technology focuses on the properties and architecture of the active site. This method enables the discovery of unexpected new candidates independent of the overall structure of a protein.
Beyond the surface
In a natural analogy to CatalophoreTM cavities, a CatalophoreTM Halo explores the surface of a protein. For productive protein-protein interaction to occur, specific physico-chemical conditions must be present. A Halo can be seen as an external point cloud that represents the surface environment in extreme detail. The generation of Halo structures allows us to detect similarities and differences between proteins without the need for sequential or structural information.
Applications in Biotech and Pharma
Biotech
Industrial biocatalysis and biotechnology
Find enzymes that can carry out novel reaction (e.g. altered substrate scope, selectivity) or overcome insufficient properties and severe limitation in biocatalysis (e.g. increased pH or thermal stability) by fining unforeseen enzymes with our Catalophore technology. Circumvent protection by IP rights or patents (gain or regain your FTO) by employing alternative enzymes in your process. Or simply get a new starting point for your traditional engineering pipeline if you reached the end and your biocatalyst still does not do the job.
Pharma
Drug discovery and repurposing in pharma and medicine
Use our technology as a new tool for the in-silico prediction of unexpected side-effects before clinical trials start. Or employ it to screen for repurposing opportunities of existing, novel or abandoned drugs.
Our technology in a nutshell
3D POINT CLOUDS
The physico-chemical properties inside a cavity or above a surface are represented by using point clouds (so-called catalophores). Each property’s value is calculated separately at each point in 3D space. A vast number of properties are available, providing new insights into the nature of the selected area.
HOW WE SEE THE WORLD
Our 3D point clouds cover several physico-chemical properties (e.g., electrostatics, hydrophobicity, accessibility, hydrogen-binding potential, elasticity…) that are matched to find similarities to binding sites without requiring sequential or structural similarity.
DATA MINING & DATABASE
We mine and homogenize publicly available data sources, such as PDB, PISA, UniProt, ProFam etc.
Our proprietary database includes:
– 98% of the experimental structures from RCSB PDB
– 100% of the biological assemblies from ePDB PISA
– AlphaFold Protein Structure Database
– High-throughput distributed automatic comparative modeling
– Tailored in-silico mutant libraries
– Synthetic proteins including non-canonical amino acids
MATCHING
Our customized iterative-closest-point (ICP)-based algorithms for matching multidimensional point clouds compute the similarity of cavities including the physico-chemical properties as artificial dimensions enriching the Cartesian shape similarity.
BIG-DATA AND MACHINE LEARNING
We feed matching and other information into our deep-learning models to improve accuracy and speed. The more we match, the better we know.
The non-cartesian view of the cavity world allows us to recognize similarities in deep dimensional space a human observer would hardly find.
One match is quick, it usually takes 3 seconds. We match millions a day. That’s why we run supercomputers.
POWERED BY SUPERCOMPUTING
High-performance supercomputing is our daily business. Our clusters can use up to 6500 CPUs to run your experiments. For special needs or during peak times, we deploy experiments on cloud-computing services like Amazon Web Service (AWS) and Google Cloud.
ADDITIONAL TOOLS INTEGRATED INTO THE PLATFORM
– Homology modeling
– In-silico protein engineering
– Docking
– In-silico protein modification
– Molecular dynamics simulations
