DrugOrchestra: Jointly predicting drug response, targets, and side effects via deep multi-task learning

 DrugOrchestra: Jointly predicting drug response, targets, and side effects via deep multi-task learning 

Yuepeng Jiang1 , Stefano Rensi2 , Sheng Wang 2*, Russ B. Altman 2,3* 1Department of Electrical and Computer Engineering, University of California, San Diego, USA 2Department of Bioengineering, Stanford University, Stanford, CA, USA 3Department of Genetics, Stanford University, Stanford, CA, USA *Correspondence to swang91@stanford.edu russ.altman@stanford.edu

multi-task deep learning

Training multiple tasks simultaneously could be challenging using multi-task learning since they need

to be assigned proper importance weights. Extensively tuning hyperparameters for the weights of

each task is time consuming. Therefore, we used a schema that can automatically adjust the weight of

each task. In this paper, we compared two weight adjusting strategies introduced by Liu et al. [23] and

Liu et al. [48] and observed that the dynamic weight adjustment strategy from Liu et al. [23] is

empirically better. The dynamic weight adjustment (DWA) strategy first calculates the relative

descending rate ω from two previous epochs. 

https://www.biorxiv.org/content/10.1101/2020.11.17.385757v1.full.pdf

https://github.com/jiangdada1221/DrugOrchestra