Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data

Koutsoukas, Alexios; Monaghan, Keith J.; Li, Xiaoli; Huan, Jun

doi:10.1186/s13321-017-0226-y

Cited by 244 publications

(179 citation statements)

References 58 publications

(48 reference statements)

Supporting

Mentioning

177

Contrasting

Unclassified

Order By: Relevance

“…Deep learning approaches have also been proposed in QSAR methods, such as Koutsoukas et al [51]. They can predict ligands for a given protein, or given bio-activity for molecules.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity

Playe

Stoven

2020

J Cheminform

View full text Add to dashboard Cite

Chemogenomics, also called proteochemometrics, covers a range of computational methods that can be used to predict protein-ligand interactions at large scales in the protein and chemical spaces. They differ from more classical ligand-based methods (also called QSAR) that predict ligands for a given protein receptor. In the context of drug discovery process, chemogenomics allows to tackle the question of predicting off-target proteins for drug candidates, one of the main causes of undesirable side-effects and failure within drugs development processes. The present study compares shallow and deep machine-learning approaches for chemogenomics, and explores data augmentation techniques for deep learning algorithms in chemogenomics. Shallow machine-learning algorithms rely on expertbased chemical and protein descriptors, while recent developments in deep learning algorithms enable to learn abstract numerical representations of molecular graphs and protein sequences, in order to optimise the performance of the prediction task. We first propose a formulation of chemogenomics with deep learning, called the chemogenomic neural network (CN), as a feed-forward neural network taking as input the combination of molecule and protein representations learnt by molecular graph and protein sequence encoders. We show that, on large datasets, the deep learning CN model outperforms state-of-the-art shallow methods, and competes with deep methods with expert-based descriptors. However, on small datasets, shallow methods present better prediction performance than deep learning methods. Then, we evaluate data augmentation techniques, namely multi-view and transfer learning, to improve the prediction performance of the chemogenomic neural network. We conclude that a promising research direction is to integrate heterogeneous sources of data such as auxiliary tasks for which large datasets are available, or independently, multiple molecule and protein attribute views.

show abstract

“…Deep learning approaches have also been proposed in QSAR methods, such as Koutsoukas et al [51]. They can predict ligands for a given protein, or given bio-activity for molecules.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity

Playe

Stoven

2020

J Cheminform

View full text Add to dashboard Cite

show abstract

“…Most recently, one group has suggested some datasets for molecular machine learning and used these for comparison with selected machine learning methods 41 . A second group has assessed several machine learning methods with 7 ChEMBL datasets but only focused on a single metric to assess performance 42 . Very frequently deep learning is applied to a single dataset in isolation and not compared to many of the available alternative methods.…”

Section: Introductionmentioning

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

“…Whereas existing computational tools to model in vitro compound activity mostly rely on established algorithms (e.g., Random Forest or Support Vector Machines), the utilization of deep learning in drug discovery is gaining momentum, a trend that is only expected to increase in the coming years [21]. Deep learning techniques have been already applied in numerous drug discovery tasks, including toxicity modelling [22,23], bioactivity prediction [24][25][26][27][28][29][30], and de novo drug design [31][32][33][34], among others. Most of these studies have utilized feedforward neural networks consisting of multiple fully-connected layers trained on one of the many compound descriptors developed over the last >30 years in the chemoinformatics field [27,35].…”

Section: Introductionmentioning

confidence: 99%

KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images

Cortés-Ciriano

Bender

2019

J Cheminform

View full text Add to dashboard Cite

The application of convolutional neural networks (ConvNets) to harness high-content screening images or 2D compound representations is gaining increasing attention in drug discovery. However, existing applications often require large data sets for training, or sophisticated pretraining schemes. Here, we show using 33 IC 50 data sets from ChEMBL 23 that the in vitro activity of compounds on cancer cell lines and protein targets can be accurately predicted on a continuous scale from their Kekulé structure representations alone by extending existing architectures (AlexNet, DenseNet-201, ResNet152 and VGG-19), which were pretrained on unrelated image data sets. We show that the predictive power of the generated models, which just require standard 2D compound representations as input, is comparable to that of Random Forest (RF) models and fully-connected Deep Neural Networks trained on circular (Morgan) fingerprints. Notably, including additional fully-connected layers further increases the predictive power of the ConvNets by up to 10%. Analysis of the predictions generated by RF models and ConvNets shows that by simply averaging the output of the RF models and ConvNets we obtain significantly lower errors in prediction for multiple data sets, although the effect size is small, than those obtained with either model alone, indicating that the features extracted by the convolutional layers of the ConvNets provide complementary predictive signal to Morgan fingerprints. Lastly, we show that multi-task ConvNets trained on compound images permit to model COX isoform selectivity on a continuous scale with errors in prediction comparable to the uncertainty of the data. Overall, in this work we present a set of ConvNet architectures for the prediction of compound activity from their Kekulé structure representations with state-of-the-art performance, that require no generation of compound descriptors or use of sophisticated image processing techniques. The code needed to reproduce the results presented in this study and all the data sets are provided at https://github.com/isidroc/kekulescope .

show abstract

Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data

Cited by 244 publications

References 58 publications

Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity

Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity

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

KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images

Contact Info

Product

Resources

About