The Apheris Resource Library

Apheris will bring privacy-preserving, AI infrastructure and collaboration on proprietary data to the OpenFold Consortium

The AI Structural Biology (AISB) Network, powered by Apheris GmbH, has expanded its Federated OpenFold3 Initiative with the addition of Astex Pharmaceuticals, Bristol Myers Squibb, and Takeda. The new partners join founding members AbbVie and Johnson & Johnson to fine-tune OpenFold3 on proprietary structural datasets.

Ginkgo Bioworks today announced a series of new initiatives from its Datapoints offering to accelerate the application of artificial intelligence in biologics drug discovery. These include a strategic partnership with Apheris to launch the Antibody Developability Consortium and, separately, the AbDev AI Competition.

In this proof-of-concept work, we aim to apply and adopt Federated Learning (FL) in a real-world hospital setting. We assessed FL for MS lesion segmentation using the self-configuring nnU-Net model, leveraging 512 MRI cases from three sites without sharing raw patient data.

In collaboration with AWS, we implemented FRA-LoRA (Full Rank Aggregation of Low-Rank Adapters) in a federated setting to fine-tune ESM-2 across multiple sites, all without sharing raw data. LoRA reduced trainable parameters to <2% of the original model, cutting communication overhead while preserving accuracy.

In the ever-evolving landscape of drug discovery, understanding how a drug behaves in the body is crucial. In this blog, Dr Angelo Pugliese explores the pivotal role ADMETox plays in this process.

Fine-tuning large language models requires high computational and memory resources, and is therefore associated with significant costs. When training on federated datasets, an increased communication effort is also needed. For this reason, parameter-efficient methods (PEFT) are becoming increasingly important.

We discuss the real-world application of federated learning (FL) in the healthcare and life sciences industry, noting a tipping point in its adoption beyond academia.

In a new initiative by the AI Structural Biology (AISB) Consortium and powered by Apheris, OpenFold3, a protein structure prediction algorithm developed by the lab of Mohammed AlQuraishi, will be fine-tuned using proprietary data from AbbVie and Johnson & Johnson.

AbbVie, J&J to add proprietary data to AIprotein model in bid to accelerate drugdiscovery. OpenFold3 will access the companies’ data using federation technology from Apheris

Thousands of 3D protein structures locked up in big-pharma vaults will be usedto create a new AI tool that won’t be open to academics.

Apheris achieves SOC 2 Type I attestation, reaffirming its commitment to data security and privacy, and the comprehensive measures we have implemented to protect sensitive information and ensure the highest level of security.

"As AI adoption gathers momentum, it is essential we get in front of this generational technology and regulate it in a way that works for everyone – before it is too late."

Certification highlights our mission and focus on best practices for federated machine learning and analytics, enabling organizations to securely build and operationalize machine learning and data applications across boundaries.

Seed extension round led by Octopus Ventures to drive growth of platform enabling organizations to unlock terabytes of valuable data risk-free

Berlin 09.03.2025 - Apheris has successfully completed SOC 2 Type II attestation, confirming that our controls for data protection, security, and privacy adhere to recognized industry standards.

The Apheris Platform enables multiple organisations to extract value from each other’s decentralised data sets and overcome regulatory, technical, and commercial challenges.

This release introduces the magic of chaining Derived Datasets, levels up model management in the Governance Portal, and fine-tunes the Apheris Model Registry. Let’s crack open the details.

Computational governance could be the key to AI safety.
The stakes are becoming increasingly high for companies developing AI in highly-regulated industries. In sectors such as healthcare and finance, compliance is not just a legal obligation, but a crucial aspect of building trust and integrity.

Apheris Co-founder and CEO, Robin Röhm, discusses how data is the lifeblood of AI. Those who produce, own, or control access are critical stakeholders. However, they face a paradox: They must protect their organization’s sensitive data, but in doing so, they act as a blocker to realizing the potential of that data for ML and AI.

Ellie Dobson, VP Product at Apheris, discusses how the rapid adoption of ML has led to data becoming one of the most valuable assets in business. However, for use cases where compliance with regulation and data privacy is of paramount importance, unlocking the full potential of data raises unique challenges.

In this article, Robin Röhm, CEO Apheris, comments on the relationship between data and AI: “... AI is nothing without the data that is used to feed its machine learning algorithms...There is a monopoly of power that comes with AI and data accessibility,” he said

As AI reshapes many industries, the balance between innovation, security, and compliance has become paramount, especially in regulated sectors.

While governments around the world are laying out plans to regulate AI, many businesses are woefully underprepared for the complexity of what lies ahead. With regulation about to roll through jurisdictions across the world, it is time to stop talking about what it might look like – and start acting.

Plans to create a data platform in partnership with the private sector could revolutionize NHS treatment, but concerns over data privacy and security are festering

With the EU AI Act imminently being finalised and countries like the UK and the US recently publishing their national AI development strategies, the topic of regulation is being hotly debated.

ChatGPT has thrown artificial intelligence into the mainstream, and now it’s Rishi Sunak’s job to design rules which don’t prevent its growth, but keep us safe, writes Robin Röhm.

AI safety is not a future problem to solve, it’s a real problem right now. In this blog I'll explain the challenges we face as a society in developing and using AI, and propose some operating principles to help us leverage AI for social good.

AI regulation looks like the next continental differing of opinion — here's why the UK's approach could affect the rest of the Europe.

AI development is happening at breakneck speed, underpinned by massive investments from Big Tech companies such as Microsoft, Google and Amazon...But AI regulation need not be an obstruction to innovation.

Explore some of the common challenges organizations face when implementing federated learning and key considerations that can help them overcome those challenges and reap the rewards of working with federated data.

Robin Röhn, CEO and co-founder and Berlin-based Apheris weighs in on what the US-EU artificial intelligence collaboration agreement means going forward, including what's sure to be a growing call for increased regulation.

Organizations are sitting on terabytes of data that only they can access. While it is highly valuable when used to inform key decisions for an individual company, the true power of data lies in collaboration between organizations.

Advising the German Federal Office for Information Security on the Security of AI-Systems, Apheris provides an overview on attack vectors and threats of AI systems where external data is used or trained models are exposed to third parties. Recommendations are derived on how to systematically safeguard and test AI-systems.

Microsoft’s recent purchase of a £1.5bn stake – equivalent to 4% – in the London Stock Exchange Group (LSEG) was the latest deal to unite Big Tech with a business running one of the world’s most significant financial markets.

Apheris is a platform for creating collaborative data ecosystems. The platform enables multiple organisations to extract value from each other's decentralised data sets, without changing the data’s location or sharing it.

The announcement this week by culture secretary Michelle Donelan that the UK plans to replace GDPR with its own “business and consumer-friendly British data protection system” is bad news. It will only increase complexity for companies in Britain and the EU hoping to collaborate by sharing data across geographical boundaries...

New culture secretary decries ‘red tape,’ but detractors warn complexity could arise.
The U.K. government plans to scrap the General Data Protection Regulation (GDPR), the EU’s data privacy regime it adopted before leaving the union.

The UK currently holds a data adequacy agreement with the EU, enabling cross-border data flows. Any moves that threaten to disrupt that trade must be considered carefully and without ideology.

The advancement of molecular profiling techniques fuels biomedical research with a deluge of data. To facilitate data sharing, the Global Alliance for Genomics and Health established the Beacon system, a search engine designed to help researchers find datasets of interest.

We present a multi-language, cross-platform, open-source library for asymmetric private set intersection (PSI) and PSI-Cardinality (PSI-C). Our protocol combines traditional DDH-based PSI and PSI-C protocols with compression based on Bloom filters that helps reduce communication in the asymmetric setting.

We introduce PyVertical, a framework supporting vertical federated learning using split neural networks. The proposed framework allows a data scientist to train neural networks on data features vertically partitioned across multiple owners while keeping raw data on an owner's device.

Our focus on sustainability extends beyond the impact we have on our customers, and our environmentally conscious mindset is at the core of Apheris’ work culture.