paper-with-me

홈 › Papers

MolecularRNN: Generating realistic molecular graphs with optimized properties

2019-05-31 · Mariya Popova, Mykhailo Shvets, Junier Oliva, Olexandr Isayev

Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estimates the reward for the property of interest. We show a significant distribution shift to the desired range for lipophilicity, drug-likeness, and melting point outperforming state-of-the-art works. With the use of rejection sampling based on valency constraints, our model yields 100% validity. Moreover, we show that invalid molecules provide a rich signal to the model through the use of structure penalty in our reinforcement learning pipeline.

📄 PDF Abstract BibTeX arXiv:1905.13372

Code (2)

shubhamgupta5893/GraphRNN pytorch
shubhamguptaiitd/GraphRNN pytorch

Tasks

Drug DiscoveryMolecular Graph GenerationReinforcement Learning

Similar Papers 제목 키워드 기반

MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

2021-03-18 · ICLR 2021 1 · Yutong Xie, Chence Shi, Hao Zhou, Yuwei Yang 외

Searching for novel molecules with desired chemical properties is crucial in drug discovery. Existing work focuses on developing neural models to generate either molecular sequences or chemical graphs. However, it remain…

Drug DiscoveryGraph Neural NetworkMolecular Graph Generation

Junction Tree Variational Autoencoder for Molecular Graph Generation

2018-02-12 · ICML 2018 7 · Wengong Jin, Regina Barzilay, Tommi Jaakkola

We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direc…

Drug DiscoveryGraph GenerationMolecular Graph Generation

MoFlow: An Invertible Flow Model for Generating Molecular Graphs

2020-06-17 · Chengxi Zang, Fei Wang

Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process. Such graph generative models usually consist of two …

Drug DiscoveryGraph GenerationMolecular Graph Generationvalid

Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models

2026-06-02 · Alessio Barboni, Massimiliano Lupo Pasini, Bishal Lakha, Edoardo Serra arxiv

Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond. However, current graph generative models remain limited b…

Graph Generation

Deep Learning for Molecular Graphs with Tiered Graph Autoencoders and Graph Prediction

2019-10-24 · Daniel T. Chang

Tiered graph autoencoders provide the architecture and mechanisms for learning tiered latent representations and latent spaces for molecular graphs that explicitly represent and utilize groups (e.g., functional groups). …

General ClassificationGraph ClassificationPrediction