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.
Meet our Scientific Advisory Board
Our Scientific Advisory Board brings together leaders from academia, biotech, and pharma who have shaped the fields of drug discovery and computational science. With decades of combined experience in AI, molecular modeling, and building world-class research organizations, they guide our scientific strategy and help drive innovation across our work.
Woody Sherman
Founder & Chief Innovation Officer at Psivant Therapeutics
Woody leads Psivant's efforts to integrate computational methods with wet lab experiments to design therapeutics for protein targets previously considered to be undruggable with oral small molecules. His specializations including protein structure prediction, quantum mechanics, molecular dynamics, de novo design, machine learning, and cheminformatics. He is the original architect of the QUAISAR platform and has over 100 peer-reviewed scientific publications. Previously, he held senior scientific roles at Silicon Therapeutics, Roivant Sciences, and Schrödinger and holds a PhD in Physical Chemistry from MIT.
Richard Bickerton
Co-Founder, Exscientia
Richard co-founded Exscientia, where he helped build the company’s AI-first discovery platform, later acquired by Recursion. His background spans cheminformatics, large-scale ML systems, and data science. He brings experience in technology, biotech, and company building.
Mohammed AlQuraishi
Assistant Professor, Columbia University
His lab sits in the Department of Systems Biology at Columbia University. They develop AI models for protein structure and function prediction, as well as protein-ligand interaction. Mohammed holds degrees in biology, computer science, and mathematics, and a PhD in genetics from Stanford University. Mohammed's lab built OpenFold, the leading open-source protein structure prediction model, and is spearheading the creation of OpenFold 3, the leading open co-folding model.
Pamela Carroll
Former COO, Isomorphic Labs
Pam has held executive leadership roles in pharma and biotech, including in business development at Roivant, Johnson and Johnson; and scientific leadership positions in oncology at Roche and Merck. She is widely recognized for pioneering the integration of emerging technology platforms to accelerate the discovery and development of novel medicines.
Darren Green
Former Head of Cheminformatics, GSK and Honorary Professor of Chemistry, University College London
Darren brings more than three decades of experience in the application of advanced computational methods to drug discovery across multiple therapeutic areas. He has been a pioneer in applying federated learning to advance drug discovery ML models, e.g., as part of the MELLODDY project.
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