MELLODDY: Cross-pharma Federated Learning at Unprecedented Scale Unlocks Benefits in QSAR without Compromising Proprietary Information
MELLODDY：前所未有的跨制药公司联邦学习规模释放了QSAR的优势，且不泄露专有信息
期刊:Journal of Chemical Information and Modeling
影响因子:5.3
doi:10.1021/acs.jcim.3c00799
Heyndrickx, Wouter; Mervin, Lewis; Morawietz, Tobias; Sturm, Noé; Friedrich, Lukas; Zalewski, Adam; Pentina, Anastasia; Humbeck, Lina; Oldenhof, Martijn; Niwayama, Ritsuya; Schmidtke, Peter; Fechner, Nikolas; Simm, Jaak; Arany, Adam; Drizard, Nicolas; Jabal, Rama; Afanasyeva, Arina; Loeb, Regis; Verma, Shlok; Harnqvist, Simon; Holmes, Matthew; Pejo, Balazs; Telenczuk, Maria; Holway, Nicholas; Dieckmann, Arne; Rieke, Nicola; Zumsande, Friederike; Clevert, Djork-Arné; Krug, Michael; Luscombe, Christopher; Green, Darren; Ertl, Peter; Antal, Peter; Marcus, David; Do Huu, Nicolas; Fuji, Hideyoshi; Pickett, Stephen; Acs, Gergely; Boniface, Eric; Beck, Bernd; Sun, Yax; Gohier, Arnaud; Rippmann, Friedrich; Engkvist, Ola; Göller, Andreas H; Moreau, Yves; Galtier, Mathieu N; Schuffenhauer, Ansgar; Ceulemans, Hugo
