ChEMBL: towards direct deposition of bioassay data

Méndez, David; Gaulton, Anna; Bento, A. Patrícia; Chambers, Jon; Veij, Marleen De; Félix, Eloy; Magariños, María Paula; Mosquera, Juan F; Mutowo, Prudence; Nowotka, Michał; Gordillo-Marañón, María; Hunter, Fiona; Junco, Laura; Mugumbate, Grace; Lopez, Milagros Rodriguez; Atkinson, Francis; Bosc, Nicolas; Radoux, Chris J.; Segura‐Cabrera, Aldo; Hersey, Anne; Leach, Andrew R.

doi:10.1093/nar/gky1075

Cited by 1,684 publications

(1,600 citation statements)

References 25 publications

Supporting

Mentioning

1,439

Contrasting

Unclassified

Order By: Relevance

“…Interactions were binarized by their pK d values into positive class (pK d > 7) and negative class (pK d ≤ 7). • Average AUC: average area under ten receiver operating characteristic (ROC) curves generated using ten interaction threshold values from the pK d interval [6,8] to binarize pK d 's into true class labels.…”

Section: Scoring Of the Model Predictionsmentioning

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 A total of 268 ML predictions were scored in unpublished bioactivity data sets.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: Scoring Of the Model Predictionsmentioning

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

“…ChEMBL is a large, open-access drug-discovery database, currently storing >15 million bioactivity measurements for ß1.8 million distinct compounds (Mendez et al, 2019). ChEMBL is a large, open-access drug-discovery database, currently storing >15 million bioactivity measurements for ß1.8 million distinct compounds (Mendez et al, 2019).…”

Section: Harnessing Public Bioactivity Data To Model the In Vitro Cytmentioning

confidence: 99%

“…Here, we describe how to generate and validate a set of predictive models of compound cytotoxicity, using as a case study IC 50 data from ChEMBL 21 for the cell line DU-145. ChEMBL is a large, open-access drug-discovery database, currently storing >15 million bioactivity measurements for ß1.8 million distinct compounds (Mendez et al, 2019). The R programming language, which has proved a versatile framework for medicinal chemistry applications (Kuhn, 2008;Mente & Kuhn, 2012), will be used to generate the models.…”

Section: Harnessing Public Bioactivity Data To Model the In Vitro Cytmentioning

confidence: 99%

“…camb (Murrell et al, 2015): required for the manipulation of chemical structures and the calculation of molecular descriptors (PaDEL and circular Morgan fingerprints); available at https://github.com/cambDI/ camb caret (Kuhn, 2008) and camb are required for the training and validation of predictive models, as well as for the application of these models to external molecules (i.e., prospective predictions); available at http://topepo.github.io/caret/index.html conformal (Cortés-Ciriano, 2015;Cortés-Ciriano et al, 2015): required to generate confidence intervals for individual predictions using the conformal prediction framework (Norinder et al, 2014); available at https://github.com/isidroc/conformal Appropriate scripts required to run the protocol, available at https://github.com/isidroc/Current_Protocols_Cytotoxicity Files Cytotoxicity data set extracted from ChEMBL 21 (the script to extract the data is provided in Supplementary File 4 and is available at https://github.com/isidroc/ Current_Protocols_Cytotoxicity/blob/master/download_IC50_data.sql) Data set extraction 1. Download the bioactivity data and compound structures from ChEMBL database (Mendez et al, 2019) by running the mysql query provided in Supplementary File 4.…”

Section: Necessary Resources Hardwarementioning

confidence: 99%

See 1 more Smart Citation

Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account

Drakakis

Cortés-Ciriano

Alexander-Dann

et al. 2019

CP Chemical Biology

View full text Add to dashboard Cite

The modes of action (MoAs) of drugs frequently are unknown, because many are small molecules initially identified from phenotypic screens, giving rise to the need to elucidate their MoAs. In addition, the high attrition rate for candidate drugs in preclinical studies due to intolerable toxicity has motivated the development of computational approaches to predict drug candidate (cyto)toxicity as early as possible in the drug-discovery process. Here, we provide detailed instructions for capitalizing on bioactivity predictions to elucidate the MoAs of small molecules and infer their underlying phenotypic effects. We illustrate how these predictions can be used to infer the underlying antidepressive effects of marketed drugs. We also provide the necessary functionalities to model cytotoxicity data using single and ensemble machine-learning algorithms. Finally, we give detailed instructions on how to calculate confidence intervals for individual predictions using the conformal prediction framework. C 2019 by John Wiley & Sons, Inc.Keywords: ChEMBL r cytotoxicity r in silico bioactivity prediction r mechanism of action r polypharmacology r toxicology modeling

show abstract

“…Data was retrieved from ChEMBL23 [56] via a PostgreSQL interface (pgAdmin3) by querying for compounds along with their bioactivity information (activity type, activity standard value, standard unit etc. ), structural information (canonical smiles, standard InChI, and InChIKeys), target information (including protein classification), assay information and document information.…”

Section: Data Retrievalmentioning

confidence: 99%

Moving Targets: Monitoring Target Trends in Drug Discovery by Mapping Targets, GO Terms, and Diseases

Zdrazil

Richter

Brown

et al. 2019

Preprint

View full text Add to dashboard Cite

Drug Discovery is a lengthy and costly process and has faced a period of declining productivity within the last two decades. As a consequence, integrative data-driven approaches are nowadays on the rise in pharmaceutical research, making use of an inter-connected (network) view on diseases. In addition, evidence-based decisions are alleviated by studying the time evolution of innovation trends in drug discovery.In this paper a new approach leveraging data mining and data integration for inspecting target innovation trends protein family-wise is presented. The study highlights protein families which are receiving emerging interest in the drug discovery community (mainly kinases and G protein coupled receptors) and those with areas of interest in target space that have just emerged in the scientific literature (mainly kinases and transporters) highlighting novel opportunities for drug intervention.In order to delineate the evolution of target-driven research interest from a biological perspective, trends in biological process annotations from Gene Ontology (GO) and disease 2 annotations from DisGeNet for major target families are captured. The analysis reveals an increasing interest in targets related to immune system processes, and a recurrent trend for targets involved in circulatory system processes. At the level of disease annotations, targets associated to e.g., cancer-related pathologies as well as to intellectual disability and schizophrenia are increasingly investigated nowadays.Can this knowledge be used to study the "movement of targets" in a network view and unravel new links between diseases and biological processes? We tackled this question by creating dynamic network representations considering data from different time periods. The dynamic network for immune system process-associated targets suggest that e.g. breast cancer as well as schizophrenia are linked to the same targets (cannabinoid receptor CB2 and VEGFR2) thus suggesting similar treatment options which could be confirmed by literature search. The methodology has the potential to identify other drug repurposing candidates and enables researchers to capture trends in research attention in target space at an early stage.In this study we have investigated target innovation in drug discovery over a period of 22 years by extracting time trends of research interest (as published in the scientific literature and stored in the ChEMBL database) in certain protein classes inspecting different measures (numbers of pharmacological measurements, targets, papers, and drugs). Focusing on the most relevant protein classes in drug discovery (G protein-coupled receptors, kinases, ion channels, nuclear receptors, proteases, and transporters), we further linked single targets to Gene Ontology (GO) biological process annotations and inspected steep increasing or decreasing trends of GO annotations within target families over time. We also tracked trends in disease annotations from DisGeNET by filtering out diseases linked to targets with emerging trends in resea...

show abstract

ChEMBL: towards direct deposition of bioassay data

Cited by 1,684 publications

References 25 publications

Crowdsourced mapping extends the target space of kinase inhibitors

Crowdsourced mapping extends the target space of kinase inhibitors

Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account

Moving Targets: Monitoring Target Trends in Drug Discovery by Mapping Targets, GO Terms, and Diseases

Contact Info

Product

Resources

About