Cold-start problems in data-driven prediction of drug-drug interaction effects

HIGHLIGHTS

• who: Pieter Dewulf and colleagues from the KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Coupure Links , have published the Article: Cold-Start Problems in Data-Driven Prediction of Drug-Drug Interaction Effects, in the Journal: Pharmaceuticals 2021, 14, 429. of /2021/
• what: The authors propose suitable validation schemes for the different subtasks that emerge. The authors develop a new model that obtains AUC-ROC = 0.843 for the hardest cold-start task up to AUC-ROC = 0.957 for the easiest one on the benchmark dataset of Zitnik et_al Finally the authors . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.