• Corpus ID: 38235267

Deep Learning as an Opportunity in Virtual Screening

@inproceedings{Unterthiner2015DeepLA,
  title={Deep Learning as an Opportunity in Virtual Screening},
  author={Thomas Unterthiner and Andreas Mayr and J{\"o}rg Kurt Wegner},
  year={2015}
}
Deep learning excels in vision and speech applications where it pushed the stateof-the-art to a new level. However its impact on other fields remains to be shown. The Merck Kaggle challenge on chemical compound activity was won by Hinton’s group with deep networks. This indicates the high potential of deep learning in drug design and attracted the attention of big pharma. However, the unrealistically small scale of the Kaggle dataset does not allow to assess the value of deep learning in drug… 

Figures and Tables from this paper

Low Data Drug Discovery with One-Shot Learning

This work demonstrates how one-shot learning can be used to significantly lower the amounts of data required to make meaningful predictions in drug discovery applications and introduces a new architecture, the iterative refinement long short-term memory, that significantly improves learning of meaningful distance metrics over small-molecules.

Exploring a Siamese Neural Network Architecture for One-Shot Drug Discovery

The results achieved demonstrate that using a Siamese Deep Neural Network for one-shot classification leads to overall improved performance when compared to other state-of-the-art models.

DeepCPI: A Deep Learning-based Framework for Large-scale in silico Drug Screening

DeepTox: Toxicity Prediction using Deep Learning

DeepTox had the highest performance of all computational methods winning the grand challenge, the nuclear receptor panel, the stress response panel, and six single assays (teams ``Bioinf@JKU'').

Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing.

Deep learning and virtual drug screening

The broad basics and integration of both virtual screening (VS) and ML are explained and artificial neural networks (ANNs) are discussed and their usage for VS is discussed.

Ranking ligands in structure-based virtual screening using siamese neural networks

This work proposes a deep learning energy-based model using siamese neural networks to rank ligands and shows that the model can learn to identify important biochemical interactions between ligand and receptors and calculates their compatibility.

Revealing cytotoxic substructures in molecules using deep learning

In drug development, late stage toxicity issues of a compound are the main cause of failure in clinical trials. In silico methods are therefore of high importance to guide the early design process to

Multi-Target Deep Neural Networks for Toxicity Prediction / Author Thomas Unterthiner, MSc

This work compares the multi-task approach to a single-task learning approach and analyzes it further in terms of its learned representation and other properties, showing that multi- task learning significantly improves results in this application.

Boosting Docking-Based Virtual Screening with Deep Learning

The proposed deep neural network, DeepVS, uses the output of a docking program and learns how to extract relevant features from basic data such as atom and residues types obtained from protein-ligand complexes, and is the best AUC reported so far for virtual screening using the 40 receptors from the DUD.
...

References

SHOWING 1-10 OF 32 REFERENCES

Prediction of Biological Activity for High-Throughput Screening Using Binary Kernel Discrimination

Binary kernel discrimination is shown to perform robustly with varying quantities of training data and also in the presence of noisy data, highlighting the importance of the judicious use of general pattern recognition techniques for compound selection.

Predicting new molecular targets for known drugs

Compared 3,665 US Food and Drug Administration (FDA)-approved and investigational drugs against hundreds of targets, defining each target by its ligands, chemical similarities between drugs and ligand sets predicted thousands of unanticipated associations.

Deep Learning of Representations: Looking Forward

This paper proposes to examine some of the challenges of scaling deep learning algorithms to much larger models and datasets, reducing optimization difficulties due to ill-conditioning or local minima, designing more efficient and powerful inference and sampling procedures, and learning to disentangle the factors of variation underlying the observed data.

Ligand-Target Prediction Using Winnow and Naive Bayesian Algorithms and the Implications of Overall Performance Statistics

Two algorithms for ligand-target prediction, namely, the Laplacian-modified Bayesian classifier and the Winnow algorithm are compared, which led to very similar measures for overall accuracy for both classifiers, whereas there were significant differences for individual activity classes.

ChEMBL: a large-scale bioactivity database for drug discovery

ChEMBL is an Open Data database containing binding, functional and ADMET information for a large number of drug-like bioactive compounds to maximize their quality and utility across a wide range of chemical biology and drug-discovery research problems.

Deep Learning in High-Energy Physics: Improving the Search for Exotic Particles

It is shown that deep learning methods need no manually constructed inputs and yet improve the AUC (Area Under the ROC Curve) classification metric by as much as 8% over the best current approaches, which is a large relative improvement and demonstrates thatDeep learning approaches can improve the power of collider searches for exotic particles.

Docking and scoring in virtual screening for drug discovery: methods and applications

Key concepts and specific features of small-molecule–protein docking methods are reviewed, selected applications are highlighted and recent advances that aim to address the acknowledged limitations of established approaches are discussed.

Classification of kinase inhibitors using a Bayesian model.

The use of Bayesian statistics to model both general (multifamily) and specific (single-target) kinase inhibitors is investigated. The approach demonstrates an alternative to current computational

Representation Learning: A Review and New Perspectives

Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.

Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification

Although SVM outperformed the ANN classifiers with regard to overall prediction accuracy, both methods were shown to complement each other, as the sets of true positives, false positives, true negatives, and false negatives produced by the two classifiers were not identical.