Convolutional Networks on Graphs for Learning Molecular Fingerprints
arXiv (Cornell University)Published 30 September 2015Open access
David Duvenaud, Dougal Maclaurin, Jorge Aguilera‐Iparraguirre, Rafael Gómez‐Bombarelli, Timothy Hirzel, Alán Aspuru‐Guzik
Citations906
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
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.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular BiologyMaterials Science
Neural ComputationLong Short-Term Memory
98,079 Citations1997Sepp Hochreiter, Jürgen Schmidhuber
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
UvA-DARE (University of Amsterdam)Adam: A Method for Stochastic Optimization
84,783 Citations2014Diederik P. Kingma, Jimmy Ba
arXiv (Cornell University)Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
15,635 Citations2024Sergey Ioffe
IEEE Transactions on Neural NetworksThe Graph Neural Network Model
9,326 Citations2008Franco Scarselli, M. Gori +3 more
A new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains, and implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space.
arXiv (Cornell University)Spectral Networks and Locally Connected Networks on Graphs
2,726 Citations2013Joan Bruna, Wojciech Zaremba +2 more
This paper considers possible generalizations of CNNs to signals defined on more general domains without the action of a translation group, and proposes two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian.
International review of cytologyRegularization of Neural Networks using DropConnect
1,916 Citations2013Li Wan, Matthew D. Zeiler +3 more
This work introduces DropConnect, a generalization of Dropout, for regularizing large fully-connected layers within neural networks, and derives a bound on the generalization performance of both Dropout and DropConnect.
Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
1,198 Citations2011Richard Socher, Jeffrey Pennington +3 more
A novel machine learning framework based on recursive autoencoders for sentence-level prediction of sentiment label distributions that outperform other state-of-the-art approaches on commonly used datasets, without using any pre-defined sentiment lexica or polarity shifting rules.
Journal of Chemical Information and Computer SciencesESOL: Estimating Aqueous Solubility Directly from Molecular Structure
1,075 Citations2004John Delaney
This paper describes a simple method for estimating the aqueous solubility (ESOL--Estimated SOLubility) of a compound directly from its structure, and was competitive with the well-established "General Solubility Equation" for medicinal/agrochemical sized molecules.
NatureThousands of chemical starting points for antimalarial lead identification
1,013 Citations2010Francisco‐Javier Gamo, Laura M. Sanz +12 more
Chemical structures and associated data suggest several novel mechanisms of antimalarial action, such as inhibition of protein kinases and host–pathogen interaction related targets.
Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection
810 Citations2011Richard Socher, Eric Huang +3 more
This work introduces a method for paraphrase detection based on recursive autoencoders (RAE) and unsupervised RAEs based on a novel unfolding objective and learns feature vectors for phrases in syntactic trees to measure word- and phrase-wise similarity between two sentences.
The Journal of Physical Chemistry LettersThe Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid
692 Citations2011Johannes Hachmann, Roberto Olivares‐Amaya +7 more
This Perspective introduces the Harvard Clean Energy Project (CEP), a theory-driven search for the next generation of organic solar cell materials, and gives a broad overview of its setup and infrastructure, present first results, and outline upcoming developments.
IEEE Transactions on Neural NetworksNeural Network for Graphs: A Contextual Constructive Approach
613 Citations2009Alessio Micheli
The new model allows the extension of the input domain for supervised neural networks to a general class of graphs including both acyclic/cyclic, directed/undirected labeled graphs and can realize adaptive contextual transductions, learning the mapping from graphs for both classification and regression tasks.
Journal of Chemical Information and ModelingDeep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules
572 Citations2013Alessandro Lusci, Gianluca Pollastri +1 more
A brief overview of deep learning methods is presented and in particular how recursive neural network approaches can be applied to the problem of predicting molecular properties, by considering an ensemble of recursive neural networks associated with all possible vertex-centered acyclic orientations of the molecular graph.
arXiv (Cornell University)A Convolutional Neural Network for Modelling Sentences
482 Citations2014Nal Kalchbrenner, Edward Grefenstette +1 more
arXiv (Cornell University)Massively Multitask Networks for Drug Discovery
401 Citations2015Bharath Ramsundar, Steven Kearnes +4 more
The results underscore the need for greater data sharing and further algorithmic innovation to accelerate the drug discovery process and investigate several aspects of the multitask framework.
arXiv (Cornell University)Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
254 Citations2014John R. Hershey, Jonathan Le Roux +1 more
This work starts with a model-based approach and an associated inference algorithm, and folds the inference iterations as layers in a deep network, and shows how this framework allows to interpret conventional networks as mean-field inference in Markov random fields, and to obtain new architectures by instead using belief propagation as the inference algorithm.
arXiv (Cornell University)Multi-task Neural Networks for QSAR Predictions
150 Citations2014George E. Dahl, Navdeep Jaitly +1 more
This work used an artificial neural network to learn a function that predicts activities of compounds for multiple assays at the same time and compared its methods to alternative methods reported to perform well on these tasks and found that the neural net methods provided superior performance.
arXiv (Cornell University)Toxicity Prediction using Deep Learning
92 Citations2015Thomas Unterthiner, Andreas Mayr +2 more
The Deep Learning approach won both of the panel-challenges (nuclear receptors and stress response) as well as the overall Grand Challenge, and thereby sets a new standard in tox prediction.