Apheris released OpenBind-0, an open co-folding model that ships with 717 ligand-bound structures from fragment-to-hit campaigns on three real discovery targets.
Public source
Publisher name
Public post
The main finding from OpenBind's new release is that more public data did not fix performance on hard targets. The release, OpenBind-0, is an open co-folding model that…
Company
Apheris
Life sciences data networks for AI
- Industry
- Biotechnology Research
- Location
- Berlin, DE
- Company size
- 51–200 employees
About Apheris
Apheris delivers enterprise-grade AI applications for drug discovery, designed for pharma companies to run and customize securely within their own IT environments. By keeping all data local, organizations maintain full sovereignty over IP-sensitive assets. These local deployments also serve as the foundation for Apheris-hosted federated data networks, where pharma companies collaboratively train and benchmark models on proprietary datasets to unlock more robust and generalizable models for drug discovery.
See moreLatest activity
Latest activity from Apheris
12 signals
Presence & Recognition
Apheris presented at NVIDIA FLARE Day on federated training to improve protein-ligand co-folding models.
People
Apheris is hiring a Senior ML Research Engineer to build co-folding and binding-affinity models for molecular and structural biology.
People
Apheris welcomed Pedro Casal Ribeiro as Agentic AI Engineer.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
RECEPTOR.AI
RECEPTOR.AI is finalizing an upcoming whitepaper featuring internal benchmark results demonstrating the capabilities of ForceFold, a co-folding architecture conditioned by physics-based methods.
Research & Knowledge
Ardigen
Ardigen published research from the University of Bonn and collaborating German institutes using RFdiffusion, ProteinMPNN, and structure-prediction models to design thousands of compact protein minibinders against cancer-associated surface targets including PD-L1, CD276, and VTCN1.
Research & Knowledge
OpenADMET
OpenADMET published a Practical Cheminformatics post examining how agent workflows can reduce friction when evaluating computational methods and foundation models using real-world ADMET datasets from the OpenADMET ExpansionRx Blind Challenge and Biogen.
Research & Knowledge
deepmirror
deepmirror saw a perspective on benchmark to clinical impact from A Nature Reviews Drug Discovery.
Research & Knowledge
Insilico Medicine