Engineering the future of drug discovery
We use machine learning to optimise and develop the current drug discovery process. Our world-first computational technique means we can discover new antibodies, faster and better.
Antiverse is recognized as one of the top biotech startups in the UK with our antibody discovery service already in use by big pharma.
Co-founded in 2017 by engineers Murat Tunaboylu and Ben Holland, our team is dedicated to engineering the future of drug development to change the course of people's lives. We are passionate about what we do and the impact our discoveries will have on patients across the globe. Based in Cardiff, our expert team spans structural biology, machine learning and medicine - and together, we are always striving for that next breakthrough in drug discovery.
10x Diversity with AI-Augmented Drug Discovery
Existing antibody discovery methods are well-developed and often effective at discovering binders. But when you need to find the best possible candidate, or when finding a suitable candidate is hard with current methods, your options are limited and often costly.
Antiverse works alongside your expert lab scientists, using next-generation sequencing (NGS) to extract even more data from existing workloads. Our AI-Augmented Drug Discovery platform and trained models analyse the statistics gained from thousands of experiments. These are compared against known data to propose the best selection of candidates according to your criteria.
When you have too many antibody-antigen binding options to choose from, we can provide targeted options so you can focus on testing safely in the knowledge that you have the cream of the crop in front of you.
When you struggle to find sufficient binders, we can recover potential binders that are so often missed by conventional methods.
When you have some binders that bind but are deficient in other aspects, we can generate new variants to expand your options.
How We Do It
To benefit from AI-Augmented Drug Discovery, the input required is surprisingly minimal and risk-free. All that is needed are the panning outputs and the resulting campaign performance metrics. By deep-sequencing the panning outputs, we can glean invaluable information about the underlying process, allowing us to select sequences that would otherwise be missed, whilst screening out sequence anomalies that don't require a second longer of your time.
Through looking at hundreds of thousands of sequences from the different panning rounds, we can assess the abundance and enrichment of each sequence, in combination with analysis of the sequence itself and how similar sequences behave, to give each sequence a score related to its binding.
Because simple clustering using sequence similarity alone misses important aspects, we use structural-based clustering as well as clustering in a transformed sequence space that represents and respects the variation of natural human antibody repertoires.
Combining the binding scores and our dual-clustering methods, we can select the tradeoff between diversity and confidence that best suits the customer.
Everything we do here at Antiverse challenges the status quo. We work in an industry where there are more antibodies than there are stars in the universe, so that makes our work fiercely exciting and fun. We like to think differently and are fortunate to have a brilliant team based in Cardiff. It’s our mission to make a difference to people’s lives that drives us.
A decade’s worth of experience in the biopharma sector, previously lead on programmes at GSK.
Implements machine learning solutions, working on the infrastructure and systems required to build, optimise and deploy the models.
Developer of novel computer vision algorithms for automatic analysis of medical images with a focus on domain shift and representation learning.
The programme is designed for startups with well defined business models and technical capability, in addition to access to computation power, the programme provides the frameworks and expertise to accelerate the responsible and ethical development and application of AI across industry.
We’ve been selected as one of Hello Tomorrow’s Top 500 deeptech startups from over 4,500 applications from 119 countries!
It is our pleasure to share that Antiverse has closed its Seed Round with well-known, highly regarded investors from software and biotech industries. The capital and the new connections acquired at this round will give Antiverse the chance to bring its machine learning model to the next level.
If you are interested in learning more about our drug discovery service, please get in touch with us using the form below.