ChEMBL: a large-scale bioactivity database for drug discovery
By Anna Gaulton, L. Bellis, A. P. Bento, Jon Chambers, M. Davies, Anne Hersey, Yvonne Light, S. McGlinchey, D. Michalovich, B. Al-Lazikani and 1 more. 2011
4,143 citations recorded by the source corpus.
ChEMBL is an Open Data database containing binding, functional and ADMET information for a large number of drug-like bioactive compounds. These data are manually abstracted from the primary published literature on a regular basis, then further curated and standardized to maximize their quality and utility across a wide range of chemical biology and drug-discovery research problems. Currently, the database contains 5.4 million bioactivity measurements for more than 1 million compounds and 5200 protein targets. Access is available through a web-based interface, data downloads and web services at: https://www.ebi.ac.uk/chembldb.
Subfields: Computational Theory and Mathematics, Molecular Biology, Pharmacology, Evaluation & Benchmarks, Computational Chemistry & Drug Discovery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
- Stephen H. Bryant
- Evan E. Bolton
- Sunghwan Kim
- Charles Siegel
- Abhinav Vishnu
- Garrett B. Goh
- Nathan Oken Hodas
- Noel M. O'Boyle
In Molecular Biology
- Marinka Zitnik
- Jure Leskovec
- Lars Juhl Jensen
- Peer Bork
- Stephen H. Bryant
- Vijay S. Pande
- C. von Mering
- Noel M. O'Boyle
In Pharmacology
- Stephen H. Bryant
- Sunghwan Kim
- Evan E. Bolton
- Noel M. O'Boyle
- Marinka Zitnik
- Jure Leskovec
- C. D. Giovanni
- Antonio Lavecchia
In Evaluation & Benchmarks
- Vijay S. Pande
- Steven M. Kearnes
- Giulio Rastelli
- Luca Pinzi
- David Ryan Koes
- Jocelyn Sunseri
- Charles Siegel
- Abhinav Vishnu
In Computational Chemistry & Drug Discovery
- Noel M. O'Boyle
- Jure Leskovec
- Vijay S. Pande
- David Ryan Koes
- Giulio Rastelli
- Luca Pinzi
- Jocelyn Sunseri
- Steven M. Kearnes
Citations in the corpus
- Strategies for Pre-training Graph Neural Networks (2019, methodology): “For graph-level multi-task supervised pre-training, we use a preprocessed ChEMBL dataset (Mayr et al., 2018; Gaulton et al., 2011 Dataset splitting.”
- Opportunities and obstacles for deep learning in biology and medicine (2017, background): “Another approach to de novo design is to train character-based RNNs on large collections of molecules, for example, ChEMBL [325], to first obtain a generic .”
- Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction (2017, methodology): “paration steps. „en, we document the training and transfer learning protocols, as well as the evaluation metrics used in this work. 3.1 Dataset for Pre-Training ChemNet was •rst trained on the ChEMBL [11] database, which is a manually curated database of bioactive molecules with drug-like properties”
- Molecular de-novo design through deep reinforcement learning (2017, methodology): “Through learning an augmented episodic likelihood which is a composite of prior likelihood [17] and a user defined scoring function, the method aims to fine-tune an RNN pre-trained on the ChEMBL database [20] towards generating desirable compounds.”
- PubChem's BioAssay Database (2011, methodology): “PubChem collaborates with the European Bioinformatics Institute (EBI) and mirrors the full ChEMBL database (12).”
- The ChEMBL bioactivity database: an update (2013, methodology): “Details of the data extraction process, curation and data model have been published previously (10); therefore, the current article focuses on recent enhancements to ChEMBL.”
- DrugBank 4.0: shedding new light on drug metabolism (2013, background): “Additional experimental drugs were added from a variety of literature sources and online databases, such as ChEMBL (11).”
- The use of a graph database is a complementary approach to a classical similarity search for identifying commercially available fragment merges (2022, methodology): “Thresholds were set by analysing the number of consecutive non-ring bonds in ChEMBL29 [51] drug molecules (after applying the Lipinski and rotatable bond lters) and calculating the 95th percentile (Supplementary Figure S3).”
- Machine learning approaches and databases for prediction of drug–target interaction: a survey paper (2020, methodology): “The data stored in the ChEMBL database [237–239] were manually extracted from published literatures.”
- Ambiguity of non-systematic chemical identifiers within and between small-molecule databases (2015, methodology): “The databases vary greatly in size and in the average number of non-systematic identifiers per compound, ranging from 1.3 for ChemSpider-V and ChEMBL to 35.4 for TTD.”
- Discovery and resupply of pharmacologically active plant-derived natural products: A review (2015, background): “mainly found in bioactivity databases, such as CHEMBL (Gaulton et al., 2012) or PubChem (Li et al.”