-
Molecular generative model based on conditional variational autoencoder for de novo molecular design
We propose a molecular generative model based on the conditional variati...
06/15/2018 ∙ by Jaechang Lim, et al. ∙
0
∙
share
read it
-
Deep Evolutionary Learning for Molecular Design
In this paper, we propose a deep evolutionary learning (DEL) process tha...
12/28/2020 ∙ by Yifeng Li, et al. ∙
0
∙
share
read it
-
Multi-Objective De Novo Drug Design with Conditional Graph Generative Model
Recently, deep generative models have revealed itself as a promising way...
01/18/2018 ∙ by Yibo Li, et al. ∙
0
∙
share
read it
-
TzK: Flow-Based Conditional Generative Model
We formulate a new class of conditional generative models based on proba...
02/05/2019 ∙ by Micha Livne, et al. ∙
6
∙
share
read it
-
Molecular De Novo Design through Deep Reinforcement Learning
This work introduces a method to tune a sequence-based generative model ...
04/25/2017 ∙ by Marcus Olivecrona, et al. ∙
0
∙
share
read it
-
GuacaMol: Benchmarking Models for De Novo Molecular Design
De novo design seeks to generate molecules with required property profil...
11/22/2018 ∙ by Nathan Brown, et al. ∙
0
∙
share
read it
-
Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
Recent advances in artificial intelligence have propelled the developmen...
09/29/2020 ∙ by Navid Shervani-Tabar, et al. ∙
0
∙
share
read it
Improving Molecular Design by Stochastic Iterative Target Augmentation
02/11/2020 ∙ by Kevin Yang, et al. ∙
13
∙
share
Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training approach for iteratively creating additional molecular targets. We first pre-train the generative model together with a simple property predictor. The property predictor is then used as a likelihood model for filtering candidate structures from the generative model. Additional targets are iteratively produced and used in the course of stochastic EM iterations to maximize the log-likelihood that the candidate structures are accepted. A simple rejection (re-weighting) sampler suffices to draw posterior samples since the generative model is already reasonable after pre-training. We demonstrate significant gains over strong baselines for both unconditional and conditional molecular design. In particular, our approach outperforms the previous state-of-the-art in conditional molecular design by over 10 absolute gain.
READ FULL TEXT
Comments
There are no comments yet.