Advancing drug discovery via GPU-based deep learning

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

doi:10.1080/17460441.2018.1465407

Cited by 67 publications

(39 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, numerous reviews have been published comprising good introductions into the field [ 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 ]. Here, we want to focus on recent developments of artificial intelligence in the field of property or activity prediction, de novo design and retrosynthetic approaches.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence in Drug Design

Heßler¹,

Baringhaus²

2018

Molecules

285

160

View full text Add to dashboard Cite

Artificial Intelligence (AI) plays a pivotal role in drug discovery. In particular artificial neural networks such as deep neural networks or recurrent networks drive this area. Numerous applications in property or activity predictions like physicochemical and ADMET properties have recently appeared and underpin the strength of this technology in quantitative structure-property relationships (QSPR) or quantitative structure-activity relationships (QSAR). Artificial intelligence in de novo design drives the generation of meaningful new biologically active molecules towards desired properties. Several examples establish the strength of artificial intelligence in this field. Combination with synthesis planning and ease of synthesis is feasible and more and more automated drug discovery by computers is expected in the near future.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence in Drug Design

Heßler¹,

Baringhaus²

2018

Molecules

285

160

View full text Add to dashboard Cite

show abstract

“…ML models are statistical methods that present the capacity to learn from data without the explicit programming for this task, and then, make a prediction for new compounds (Mak and Pichika, 2019). The increase of storage capacity and the size of the datasets available, coupled to advances in computer hardware such as graphical processing units (GPUs) (Gawehn et al, 2018), provided means to move theoretical studies in ML to practical applications in drug discovery (Vamathevan et al, 2019).…”

Section: Machine Learning (Ml) and Deep Learning (Dl) Modelsmentioning

confidence: 99%

In silico Strategies to Support Fragment-to-Lead Optimization in Drug Discovery

et al. 2020

View full text Add to dashboard Cite

“…Concerning time complexity, GPU-based deep-learning approaches show a significant reduction in time complexity compared to the case when running on a traditional CPU. Gawehn et al [64] discussed and introduced several strategies for employing GPU to accelerate drug discovery systems. For further verification of the effectiveness of the proposed DeepH-DTA, the computational complexity needs to be addressed.…”

Section: E Computational Complexitymentioning

confidence: 99%

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

et al. 2020

View full text Add to dashboard Cite

The rapid spread of novel coronavirus pneumonia (COVID-19) has led to a dramatically increased mortality rate worldwide. Despite many efforts, the rapid development of an effective vaccine for this novel virus will take considerable time and relies on the identification of drug-target (DT) interactions utilizing commercially available medication to identify potential inhibitors. Motivated by this, we propose a new framework, called DeepH-DTA, for predicting DT binding affinities for heterogeneous drugs. We propose a heterogeneous graph attention (HGAT) model to learn topological information of compound molecules and bidirectional ConvLSTM layers for modeling spatio-sequential information in simplified molecular-input line-entry system (SMILES) sequences of drug data. For protein sequences, we propose a squeezed-excited dense convolutional network for learning hidden representations within amino acid sequences; while utilizing advanced embedding techniques for encoding both kinds of input sequences. The performance of DeepH-DTA is evaluated through extensive experiments against cutting-edge approaches utilising two public datasets (Davis, and KIBA) which comprise eclectic samples of the kinase protein family and the pertinent inhibitors. DeepH-DTA attains the highest Concordance Index (CI) of 0.924 and 0.927 and also achieved a mean square error (MSE) of 0.195 and 0.111 on the Davis and KIBA datasets respectively. Moreover, a study using FDA-approved drugs from the Drug Bank database is performed using DeepH-DTA to predict the affinity scores of drugs against SARS-CoV-2 amino acid sequences, and the results show that that the model can predict some of the SARS-Cov-2 inhibitors that have been recently approved in many clinical studies.

show abstract

Advancing drug discovery via GPU-based deep learning

Cited by 67 publications

References 20 publications

Artificial Intelligence in Drug Design

Artificial Intelligence in Drug Design

In silico Strategies to Support Fragment-to-Lead Optimization in Drug Discovery

DeepH-DTA: Deep Learning for Predicting Drug-Target Interactions: A Case Study of COVID-19 Drug Repurposing

Contact Info

Product

Resources

About