Industry-Scale Orchestrated Federated Learning for Drug Discovery

\'Ad\'am Arany; Adam Zalewski; Adrien Darbier; Alexandre Picosson; Andr\'as Formanek; Ansgar Schuffenhauer; Antoine Simon; Arnaud Gohier; Arne Dieckmann; Ashley Nicollet

REVIEW

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2210.08871 v2 pith:DGIJ43YU submitted 2022-10-17 cs.LG stat.ML

Industry-Scale Orchestrated Federated Learning for Drug Discovery

Martijn Oldenhof , Gergely \'Acs , Bal\'azs Pej\'o , Ansgar Schuffenhauer , Nicholas Holway , No\'e Sturm , Arne Dieckmann , Oliver Fortmeier

show 39 more authors

Eric Boniface Cl\'ement Mayer Arnaud Gohier Peter Schmidtke Ritsuya Niwayama Dieter Kopecky Lewis Mervin Prakash Chandra Rathi Lukas Friedrich Andr\'as Formanek Peter Antal Jordon Rahaman Adam Zalewski Wouter Heyndrickx Ezron Oluoch Manuel St\"o{\ss}el Michal Van\v{c}o David Endico Fabien Gelus Tha\"is de Boisfoss\'e Adrien Darbier Ashley Nicollet Matthieu Blotti\`ere Maria Telenczuk Van Tien Nguyen Thibaud Martinez Camille Boillet Kelvin Moutet Alexandre Picosson Aur\'elien Gasser Inal Djafar Antoine Simon \'Ad\'am Arany Jaak Simm Yves Moreau Ola Engkvist Hugo Ceulemans Camille Marini Mathieu Galtier

This is my paper

classification cs.LG stat.ML

keywords platformfederateddiscoverydrugmelloddypartnerscompaniesdifferent

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n{\deg}831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper.

Industry-Scale Orchestrated Federated Learning for Drug Discovery

discussion (0)