Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules

By Alessandro Lusci, Gianluca Pollastri, Pierre Baldi. 2013

506 citations recorded by the source corpus.

Shallow machine learning methods have been applied to chemoinformatics problems with some success. As more data becomes available and more complex problems are tackled, deep machine learning methods may also become useful. Here we present a brief overview of deep learning methods and show in particular how recursive neural network approaches can be applied to the problem of predicting molecular properties. However molecules are typically described by undirected cyclic graphs, while recursive approaches typically use directed acyclic graphs. Thus we develop methods to address this discrepancy, essentially by considering an ensemble of recursive neural networks associated with all possible vertex-centered acyclic orientations of the molecular graph. One advantage of this approach is that it relies only minimally on the identification of suitable molecular descriptors, since suitable representations are learnt automatically from the data. Several variants of this approach are applied to the problem of predicting aqueous solubility and tested on four benchmark datasets. Experimental results show that the performance of the deep learning methods matches or exceeds the performance of other state-of-the-art methods according to several evaluation metrics and expose the fundamental limitations arising from training sets that are too small or too noisy. A web-based predictor AquaSol is available online through the ChemDB portal (cdb.ics.uci.edu) together with additional material.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Spectroscopy, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Spectroscopy

In Computational Chemistry & Drug Discovery

Citations in the corpus

Gated Graph Sequence Neural Networks (2015, background): “Lusci et al. (2013) converts an arbitrary undirected graph to a number of different DAGs with different orientations and then propagates node representations inwards towards each root, training an ensemble of models.”
Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015, background): “Neural graph fingerprints The most closely related work is [15], who build a neural network having graph-valued inputs.”
Neural Message Passing for Quantum Chemistry (2017, methodology): “While neural networks have been applied in a variety of situations (Merkwirth & Lengauer, 2005; Micheli, 2009; Lusci et al., 2013; Duvenaud et al., 2015), they have yet to become widely adopted.”
Deep learning in neural networks: An overview (2014, background): “cture prediction (Baldi et al., 1999). DAG-RNNs (Baldi and Pollastri, 2003; Wu and Baldi, 2008) generalize BRNNs to multiple dimensions. They learned to predict properties of small organic molecules (Lusci et al., 2013) as well as protein contact maps (Tegge et al., 2009), also in conjunction with a”
Molecular graph convolutions: moving beyond fingerprints (2016, methodology): “In another vein, Lusci et al. (2013) convert undirected molecular graphs to a directed recursive neural net and take an ensemble over multiple conversions.”
Hierarchical Graph Representation Learning with Differentiable Pooling (2018, methodology): “GNNs have been applied to a wide variety of tasks, including node classification [16, 21], link prediction [31], graph classification [7, 11, 39], and chemoinformatics [14, 19, 27, 28, 32].”
Opportunities and obstacles for deep learning in biology and medicine (2017, background): “[309] applied recursive neural networks for directed acyclic graphs to undirected molecular graphs by creating an ensemble of directed graphs in which one atom is selected as the root node.”
Massively Multitask Networks for Drug Discovery (2015, background): “Other related work uses deep recursive neural networks to predict aqueous solubility by extracting features from the connectivity graphs of small molecules (Lusci et al., 2013).”
Development and evaluation of a deep learning model for protein–ligand binding affinity prediction (2017, methodology): “Several promising examples of deep learning methods have also been shown for computer-aided drug de-sign (CADD) (Lusci et al. , 2013; Dahl et al. , 2014; Ma et al. , 2015; Xu et al. , 2015; Duvenaud et al. , 2015; Kearnes et al. , 2016; Jastrz¸ebski et al. , 2016; Segler et al. , 2017; Olivecrona et”
Modeling, Inference and Optimization With Composable Differentiable Procedures (2016, background): “[60], who build a neural network having graph-valued inputs.”
Detecting Cardiovascular Disease from Mammograms with Deep Learning (2017, unknown): “have been used to successfully tackle a variety of problems in engineering, ranging from computer vision [24]–[27] to speech recognition [28], as well as in the natural sciences, in areas ranging from high energy physics [29], [30], to chemistry [31]–[33], and to biology [34]–[36].”