DE NOVO DRUG DESIGN WITH DEEP GENERATIVE MODELS : AN EMPIRICAL STUDY - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

DE NOVO DRUG DESIGN WITH DEEP GENERATIVE MODELS : AN EMPIRICAL STUDY

Résumé

We present an empirical study about the usage of RNN generative models for stochastic optimization in the context of de novo drug design. We study different kinds of architectures and we find models that can generate molecules with higher values than ones seen in the training set. Our results suggest that we can improve traditional stochastic optimizers, that rely on random perturbations or random sampling by using generative models trained on unlabeled data, to perform knowledge-driven optimization.
Fichier principal
Vignette du fichier
de-novo-drug (1).pdf (260.29 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01773760 , version 1 (23-04-2018)

Identifiants

  • HAL Id : hal-01773760 , version 1

Citer

Mehdi Cherti, Balázs Kégl, Akin Osman Kazakçi. DE NOVO DRUG DESIGN WITH DEEP GENERATIVE MODELS : AN EMPIRICAL STUDY. International Conference on Learning Representations, Apr 2017, Toulon, France. ⟨hal-01773760⟩
338 Consultations
404 Téléchargements

Partager

Gmail Facebook X LinkedIn More