Applications of machine learning in drug discovery and development

Vamathevan, Jessica; Clark, Dominic; Czodrowski, Paul; Dunham, Ian; Ferràn, Edgardo A.; Lee, George; Li, Bin; Madabhushi, Anant; Shah, Parantu K.; Spitzer, Michaela; Zhao, Shanrong

doi:10.1038/s41573-019-0024-5

Cited by 1,863 publications

(1,211 citation statements)

References 113 publications

Supporting

Mentioning

1,055

Contrasting

Unclassified

Order By: Relevance

“…ML models are aimed at guiding data-driven decision making, and these models have shown their potential to reduce failure rates and accelerate several phases of drug discovery and development. 16 The IDG-DREAM Drug Kinase Binding Prediction Challenge sought to benchmark state-of-the-art ML algorithms in the task of exploring the druggable kinome space by combining predictive modelling with experimental target activity profiling. In particular, the Challenge participants applied supervised ML models in the task of guiding biochemical mapping efforts by systematic prioritization of the most potent compound-target activities for further experimental evaluation.…”

Section: Discussionmentioning

confidence: 99%

Crowdsourced mapping extends the target space of kinase inhibitors

Cichońska

Ravikumar

Allaway

et al. 2020

Preprint

View full text Add to dashboard Cite

Despite decades of intensive search for compounds that modulate the activity of particular proteins, there are currently small-molecule probes available only for a small proportion of the human proteome. Effective approaches are therefore required to map the massive space of unexplored compound-target interactions for novel and potent activities. Here, we carried out a crowdsourced benchmarking of the accuracy of machine learning (ML) algorithms at predicting kinase inhibitor potencies across multiple kinase families. A total of 268 ML predictions were scored in unpublished bioactivity data sets. Top-performing algorithms used kernel learning, gradient boosting and deep learning, with predictive accuracy exceeding that of target activity assays. Subsequent experiments carried out based on the the top-performing model predictions demonstrated that these models and their ensemble can improve the accuracy of experimental mapping efforts, especially for so far under-studied kinases. The open-source ML algorithms together with the novel dose-response data for 905 bioactivities between 95 compounds and 295 kinases provide a unique resource for extending the druggable kinome.AI approaches, that can leverage the information extracted from similar kinases and compounds to predict the activity of so far unexplored interactions.The Challenge was implemented in a screening-based, pre-competitive drug discovery project in collaboration with the NIH-supported Illuminating the Druggable Genome (IDG) program ( https://commonfund.nih.gov/idg ), with the common aim to establish kinome-wide target profiles of small-molecule agents, and thereby to extend the druggability of the human kinome space by providing activity information on under-studied proteins. The specific questions this Challenge sought to address were: (i) What are the best computational modelling approaches for predicting quantitative compound-target activity profiles?; (ii) What are the optimal molecular and chemical descriptors for maximal prediction accuracy?; and (iii) What are the most predictive bioactivity assays and publicly available datasets? The Challenge attracted 212 active participants, and a total of 268 predictions were scored, covering a wide range of ML approaches, including deep and kernel learning and gradient boosting decision trees. Here, we describe the benchmarking results from the Challenge, and the use of top-performing models for identifying novel kinase inhibitor activities.

show abstract

Section: Discussionmentioning

confidence: 99%

Crowdsourced mapping extends the target space of kinase inhibitors

Cichońska

Ravikumar

Allaway

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…A potential solution is to predict candidate pharmacogenes according to the chemical structure of a new drug by the artificial intelligence and machine learning algorithm [21,22] . Then related molecular biological studies can be conducted to validate these candidate pharmacogenes rapidly.…”

Section: Discussionmentioning

confidence: 99%

Genetic Profiles in Pharmacogenes Indicate Personalized Drug Therapy for COVID-19

Wang

Cui

Ouyang

et al. 2020

Preprint

View full text Add to dashboard Cite

Background:The coronavirus disease 2019 has become a global pandemic currently. Many drugs showed potential for COVID-19 therapy. However, genetic factors which can lead to different drug efficiency and toxicity among populations are still undisclosed in COVID-19 therapy. Methods:We selected 67 potential drugs for COVID-19 therapy (DCTs) from clinical guideline and clinical trials databases. 313 pharmaco-genes related to these therapeutic drugs were included. Variation information in 125,748 exomes were collected for racial differences analyses. The expression level of pharmaco-genes in single cell resolution was evaluated from single-cell RNA sequencing (scRNA-seq) data of 17 healthy adults.Results: Pharmacogenes, including CYP3A4, ABCB1, SLCO1B1, ALB, CYP3A5, were involved in the process of more than multi DCTs. 224 potential drug-drug interactions (DDIs) of DCTs were predicted, while 112 of them have been reported.Racial discrepancy of common nonsynonymous mutations was found in pharmacogenes including: VDR, ITPA, G6PD, CYP3A4 and ABCB1 which related to DCTs including ribavirin, α -interferon, chloroquine and lopinavir. Moreover, ACE2, the target of 2019-nCoV, was only found in parts of lung cells, which makes drugs like chloroquine that prevent virus binding to ACE2 more specific than other targeted drugs such as camostat mesylate.

show abstract

“…They have shattered performance benchmarks in many challenging medical applications, including mitosis detection 3,4 , the quantification of tumor immune infiltration 5 , cancer subtypes classification 6,7 and grading 8,9 . Ultimately, they enhance the practices of pathologists, improving the prediction of patient survival outcomes and response to treatment 10,11 and presenting exciting opportunities in clinical and biomedical fields 12,13 .…”

mentioning

confidence: 99%

Transcriptomic learning for digital pathology

Schmauch¹,

Romagnoni²,

Pronier³

et al. 2019

Preprint

View full text Add to dashboard Cite

^,⋕ : These authors contributed equally.Deep learning methods for digital pathology analysis have proved an effective way to address multiple clinical questions, from diagnosis to prognosis and the prediction of treatment outcomes. They have also recently been used to predict gene mutations from pathology images, but no comprehensive evaluation of their potential for extracting molecular features from histology slides, has yet been performed. We propose a novel approach based on the integration of multiple data modes, and show that our deep learning model HE2RNA can be trained to predict systematically RNA-Seq profiles from whole-slide images alone, without the need for expert annotation. The model facilitates the virtual spatialization of gene expression, as validated by double-staining in an independent dataset. The results can therefore be interpreted in detail and this model opens up new opportunities for virtual staining. Finally, the transcriptomic representation learned by the model could be could be used to improve performances for other clinical tasks, particularly for small datasets. For example we studied the problem of predicting microsatellite instability from Hematoxylin & Eosin (H&E)-stained images. Greater prediction ability was achieved in such a realistic framework.

show abstract

Applications of machine learning in drug discovery and development

Cited by 1,863 publications

References 113 publications

Crowdsourced mapping extends the target space of kinase inhibitors

Crowdsourced mapping extends the target space of kinase inhibitors

Genetic Profiles in Pharmacogenes Indicate Personalized Drug Therapy for COVID-19

Transcriptomic learning for digital pathology

Contact Info

Product

Resources

About