Deep Learning in Drug Discovery

Gawehn, Erik; Hiss, Jan A.; Schneider, Gisbert

doi:10.1002/minf.201501008

Cited by 597 publications

(416 citation statements)

References 211 publications

Supporting

Mentioning

398

Contrasting

Unclassified

Order By: Relevance

“…To date there have been relatively few studies that have made comparisons of deep learning to the wide array of classical machine learning methods or have discussed this methods application in pharmaceutical research 41, 110, 111 or even used the models for actual predictions for ongoing projects. This study therefore fills a void related to drug discovery applications of these methods.…”

Section: Discussionmentioning

confidence: 99%

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Korotcov¹,

Tkachenko²,

et al. 2017

View full text Add to dashboard Cite

Machine learning methods have been applied to many datasets in pharmaceutical research for several decades. The relative ease and availability of fingerprint type molecular descriptors paired with Bayesian methods resulted in the widespread use of this approach for a diverse array of endpoints relevant to drug discovery. Deep learning is the latest machine learning algorithm attracting attention for many of pharmaceutical applications from docking to virtual screening. Deep learning is based on an artificial neural network with multiple hidden layers and has found considerable traction for many artificial intelligence applications. We have previously suggested the need for a comparison of different machine learning methods with deep learning across an array of varying datasets that is applicable to pharmaceutical research. Endpoints relevant to pharmaceutical research include absorption, distribution, metabolism, excretion and toxicity (ADME/Tox) properties, as well as activity against pathogens and drug discovery datasets. In this study, we have used datasets for solubility, probe-likeness, hERG, KCNQ1, bubonic plague, Chagas, tuberculosis and malaria to compare different machine learning methods using FCFP6 fingerprints. These datasets represent whole cell screens, individual proteins, physicochemical properties as well as a dataset with a complex endpoint. Our aim was to assess whether deep learning offered any improvement in testing when assessed using an array of metrics including AUC, F1 score, Cohen’s kappa, Matthews correlation coefficient and others. Based on ranked normalized scores for the metrics or datasets Deep Neural Networks (DNN) ranked higher than SVM, which in turn was ranked higher than all the other machine learning methods. Visualizing these properties for training and test sets using radar type plots indicates when models are inferior or perhaps over trained. These results also suggest the need for assessing deep learning further using multiple metrics with much larger scale comparisons, prospective testing as well as assessment of different fingerprints and DNN architectures beyond those used.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Korotcov¹,

Tkachenko²,

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Current complex machine learning models, for example following 'deep learning' principles [41,42], that are trained on comprehensive datasets are still difficult to interpret, and result in performances that are as of yet insignificant compared with existing methodologies. In particular, large ligand-target networks have been reported to suffer from a strong target selection bias [43], which may force models to learn historic target preferences rather than identifying informative ligand-target patterns [44].…”

Section: Introductionmentioning

confidence: 99%

Active Learning for Computational Chemogenomics

et al. 2017

Self Cite

View full text Add to dashboard Cite

Aim: Computational chemogenomics models the compound–protein interaction space, typically for drug discovery, where existing methods predominantly either incorporate increasing numbers of bioactivity samples or focus on specific subfamilies of proteins and ligands. As an alternative to modeling entire large datasets at once, active learning adaptively incorporates a minimum of informative examples for modeling, yielding compact but high quality models. Results/methodology: We assessed active learning for protein/target family-wide chemogenomic modeling by replicate experiment. Results demonstrate that small yet highly predictive models can be extracted from only 10–25% of large bioactivity datasets, irrespective of molecule descriptors used. Conclusion: Chemogenomic active learning identifies small subsets of ligand–target interactions in a large screening database that lead to knowledge discovery and highly predictive models.

show abstract

“…It has recently proved to be useful for several applications, for instance, image recognition, [18][19][20][21] speech recognition, 22 and drug discovery. 23 The technique, especially, provides an efficient and effective means of handling large-scale datasets as well as discovering intrinsic feature representation of the datasets.…”

Section: Research Motivationmentioning

confidence: 99%

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

Moon

Kwak

et al. 2017

J. Appl. Remote Sens

View full text Add to dashboard Cite

, "Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles," J. Appl. Remote Sens. 11(4), 042621 (2017), doi: 10.1117/1.JRS.11.042621. Abstract. Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

show abstract

Deep Learning in Drug Discovery

Cited by 597 publications

References 211 publications

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Active Learning for Computational Chemogenomics

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

Contact Info

Product

Resources

About