Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015-09-30T00:00:00.000000Z)

TL;DR

A convolutional neural network that operates directly on graphs that allows end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape is introduced.

Abstract

We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.

Authors

Alán Aspuru-Guzik

14 papers

Ryan P. Adams

6 papers

D. Duvenaud

7 papers

TL;DR

Abstract

Authors

References31 items

Toxicity Prediction using Deep Learning

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Massively Multitask Networks for Drug Discovery

Adam: A Method for Stochastic Optimization

Neural Turing Machines

Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures

Multi-task Neural Networks for QSAR Predictions

A Convolutional Neural Network for Modelling Sentences

Spectral Networks and Locally Connected Networks on Graphs

Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules

Regularization of Neural Networks using DropConnect

Theano: new features and speed improvements

Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid

Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions

The Harvard Clean Energy Project. Large-scale computational screening and design of molecular motifs for organic photovoltaics on the World Community Grid

Thousands of chemical starting points for antimalarial lead identification

Extended-Connectivity Fingerprints

Neural Network for Graphs: A Contextual Constructive Approach

Python for Scientific Computing

Circular fingerprints: flexible molecular descriptors with applications from physical chemistry to ADME.

ESOL: Estimating Aqueous Solubility Directly from Molecular Structure

Convolutional networks for images, speech, and time series

Long Short-Term Memory

SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules

The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service.

Deep Learning as an Opportunity in Virtual Screening

National center for advancing translational sciences. http://tripod. nih.gov/tox21/challenge

The Graph Neural Network Model

RDKit: Open-source cheminformatics

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names