The Apheris product is used by some of the largest global life sciences organizations to collaborate on sensitive, proprietary data across teams, borders, and organizations.
Our customers unlock the value of complementary data and collaboratively train machine learning models on their distributed datasets to improve accuracy and generalizability to meet the precision required for industrial settings.
Meet our Founders
Robin Röhm
Co-Founder & CEO
Robin studied medicine, philosophy and mathematics and was trained in global banking at UBS. In one of his previous start-ups, he lost multiple customers as data couldn’t be centralized due to regulatory constraints. He is driving the vision, strategy, and culture of Apheris.
Michael Höh
Co-Founder & CTO
Michael has a PhD in physics and computer science. He was trained at BCG where he built digital solutions and AI applications for industrial clients. As CTO he leads our platform architecture and design, our engineering target picture, technical customer commitments and legal and contractual scoping.
Events we're joining
Our VP of Product, Ellie Dobson, will speak about fine-tuning OpenFold3 on proprietary pharma data - bridging the gab between today's algorithmic capabilities and complex industrial demands
Robin Röhm, and Markus Bujotzek will present a privacy-preserving federated clustering framework protecting each partner's IP. Our method combines clustering algorithms evaluated on drug discovery data with a secure translation into a federated setting, implemented using the NVIDIA FLARE framework.
Excited to join the AI in Chemistry Symposium to learn about the latest industry breakthroughs and connect with leading experts in structural drug discovery and ADMET modeling.
To explore molecular data diversity for drug development in federated settings, we benchmarked clustering methods (Fed-kMeans, Fed-PCA+Fed-kMeans, Fed-LSH) on eight datasets, evaluating results with quantitative, qualitative, and domain-specific metrics.
Our CEO, Robin Röhm, will present how the AISB Network addresses the scarcity of public protein-ligand structure data through secure, collaborative AI model training. We’ll present the experimental setup, federated learning infrastructure, IP protection, and collaborative training results of our first initative.
Our culture is based upon our core values
Impact
We are driven by impact and strive for the impossible
Collaboration
Through collaboration, we create a whole that is far greater than the sum of its parts
Responsibility
We are responsible together and commit to ownership
Humility
We have the humility and hunger to learn