We partner with pharmaceutical companies and biotechs to provide a range of protein engineering and drug discovery services, based on the technology we develop.
Our state-of-the-art AI/ML algorithms, coupled with in-silico pipelines and workflows, enables us to rapidly develop new therapeutic lead molecules.
Wet-lab based approaches to drug discovery can be slow and expensive, requiring many rounds of optimisation to yield results.
Our approach is different: we find high-quality candidates in silico, then work with you to validate them in the lab. Our technology allows us to find these candidates in days, rather than months or years as for traditional wet-lab approaches.
Our fully in-silico drug development technology identifies and optimises lead candidates fast. Traditional lab-based approaches to drug development can be time consuming and costly with multiple rounds of optimisation. By only validating high-quality leads in laboratory experiments, we save you save time and money.
Our technology is built on high performance and secure cloud-based computing that can scale easily. We can discover and design binders for multiple targets in parallel. The benefit is that we can assist you to widen your discovery programs by taking on multiple targets simultaneously.
AI/ML approaches in drug discovery are moving at a high pace. We keep abreast with the current state of the art and develop and integrate the latest and greatest technologies into one platform. By using our technology, you can rest assured that the best techniques are being applied to your problem, and you can focus your efforts on other priorities.
We have developed several state-of-the-art AI/ML algorithms in order to enable rapid drug development for our partners. We provide solutions for several steps in the drug development pipeline including: target characterisation, hit identification, lead characterization and lead optimisation.
Predict the structure of proteins, antibodies and nanobodies from their sequence information; predict the effect of mutations on a structure; model libraries of antibody structures.
Predict the paratope residues of an antibody; predict the epitope of an antibody for a given target; predict PPI sites of proteins; characterise surface properties.
Perform structure-based virtual screening of antibody libraries to identify hits; design de novo protein scaffolds based on a given target structure.
Improve the binding affinity of a biologic for a protein target; simultaneously improve the binding affinity of a biologic for several homologous proteins.
Perform sequence and structure based humanisation of antibody candidates when parental antibodies come from non-human sources.
Assess and optimise the key characteristics of therapeutic candidates for solubility, stability and sequence liabilities.
Eve is our cloud-based software platform for biologics design, discovery and optimization. It integrates our machine learning models, workflows and pipelines with visualisation and project management functionality.
Eve was built to operate at speed and scale. Following best practices for software development, optimised compute infrastructure, data management and security, Eve enables the rapid development of biologics-based therapeutics.
3D Structure from sequence.
Antibody/antigen binding hotspots.
Find or generate antibody leads.
Optimise binding affinity.
Mitigate developability issues.
Assess and optimise "humanness".
The rapid advancement of AI technology and in-silico modelling of biologics are opening up new ways to design and discover biologics.
It is now entirely possible to design completely new de novo biologics on the computer or to have massive virtual screening campaigns to discover lead molecules much faster than what is possible in the lab.
At SilicoGenesis, the process of design, discovery and optimization of biologics starts in silico. Once lead molecules are identified, these molecules are then tested in the lab to verify their efficacy and properties.
SilicoGenesis was founded by Lionel Bisschoff and Fred Senekal in 2021. Initially based in Johannesburg, South Africa, we have now expanded to Leuven, Belgium.
We are an interdisciplinary team of experts in biochemistry, machine learning, software engineering and cloud development turning our vision into a reality.
Founder
Lionel has over 25 years of experience as an entrepreneur, consultant and director in the technology space. Lionel has assisted startups and designed, directed and delivered multi-million corporate programmes across a broad range of industries.
Founder
Fred has worked in the fields of AI, machine learning and pattern recognition for 20 years. He founded various companies and authored various papers. He holds an M.Eng. with specialisation in Bioinformatics.
Chief Biochemist
Dean is a structural biologist with experience in molecular biology, computational biology and drug discovery. He has a PhD in Biochemistry and Cell Biology and a background in biotechnology.
Machine Learning Engineer
Mechiel is a ML engineer with a Master’s degree in Bioengineering from Trinity College Dublin as well as a Master’s degree in Biomedical Engineering from Ghent University. He has experience in product development in the biotech industry.
Data Scientist
Claudio is a data engineer & data scientist with experience in machine learning and statistical techniques. He has a Master’s degree in Advanced Data Analytics.
AWS Software Architect
Ronald is a software architect and developer. He has been working in software development for over 17 years across various industries and technologies.
Scientific Advisor
Ian is a protein biochemist with an interest in protein and antibody engineering. Ian has previously acted as the CSO of Absolute Antibody and mAbsolve (which he co-founded) and is the founder of mAbvice consulting services.
Let us help you fasttrack your drug discovery and optimisation pipelines. Contact us for a brief chat and find out how we can collaborate. E-mail communication is preferred.
Copyright © 2021-2023 SilicoGenesis. All Rights Reserved.
Leuven, Belgium and Johannesburg, South Africa.