An optimal set of inhibitors for Reverse Engineering via Kinase Regularization.
Rata, S.; Gruver, J. S.; Trikoz, N.; Lukyanov, A.; Vultaggio, J.; Ceribelli, M.; Thomas, C.; Gujral, T. S.; Kirschner, M. W.; Peshkin, L.
Show abstract
We present a comprehensive resource of 257 kinase inhibitor profiles against 365 human protein kinases using gold-standard kinase activity assays. We show the utility of this dataset with an improved version of Kinome Regularization (KiR) to deconvolve protein kinases involved in a cellular phenotype. We assayed protein kinase inhibitors against more than 70% of the human protein kinome and chose an optimal subset of 58 inhibitors to assay at ten doses across four orders of magnitude. We demonstrate the effectiveness of KiR to identify key kinases by using a quantitative cell migration assay and updated machine learning methods. This approach can be widely applied to biological problems for which a quantitative phenotype can be measured and which can be perturbed with our set of kinase inhibitors.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Computational drug repurposing against SARS-CoV-2 reveals plasma membrane cholesterol depletion as key factor of antiviral drug activity 94%
- Predicting drug polypharmacology from cell morphology readouts using variational autoencoder latent space arithmetic 94%
- RIDDEN: Data-driven inference of receptor activity from transcriptomic data 94%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.