A two-VAE generative model, fine-tuned with reinforcement learning and a drug-sensitivity critic, produces molecules with high predicted efficacy against specific cancer transcriptomic profiles, but only in silico.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.BM 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PaccMann$^{RL}$: Designing anticancer drugs from transcriptomic data via reinforcement learning
A two-VAE generative model, fine-tuned with reinforcement learning and a drug-sensitivity critic, produces molecules with high predicted efficacy against specific cancer transcriptomic profiles, but only in silico.