AI methods often rely on limited public datasets, restricting industrial impact. Federated learning enables secure collaboration across private pharma data, but data access remains a major challenge.
GEN published a thoughtful coverage of last month's Bio-IT World plenary keynote where JT from Apheris presented a session on federated learning and fine-tuning for drug discovery.
ADMET liabilities drive 40–45% of clinical attrition, and models break on novel chemistry which is precisely where chemists need them most. Pre-competitive federated networks address this through complementary data collaboration. A walk through the evidence behind the Apheris ADMET Network.
We rebuilt the SandboxAQ affinity head inside ApherisFold and fine-tuned it on 49 JAK2 macrocycles. Architectural changes alone lifted Spearman ranking from 0.418 to 0.60; fine-tuning then pushed validation Pearson from 0.23 to 0.76, mostly by correcting how the model handled inactives.
NEWSLETTER
A quaterly briefing on operationalizing and customizing co-folding, ADMET and antibody developability models. Written by Robin Röhm, co-founder and CEO at Apheris.
