ZINC 15 – Ligand Discovery for Everyone
By Teague Sterling, John J. Irwin. 2015
3,066 citations recorded by the source corpus.
Many questions about the biological activity and availability of small molecules remain inaccessible to investigators who could most benefit from their answers. To narrow the gap between chemoinformatics and biology, we have developed a suite of ligand annotation, purchasability, target, and biology association tools, incorporated into ZINC and meant for investigators who are not computer specialists. The new version contains over 120 million purchasable “drug-like” compounds – effectively all organic molecules that are for sale – a quarter of which are available for immediate delivery. ZINC connects purchasable compounds to high-value ones such as metabolites, drugs, natural products, and annotated compounds from the literature. Compounds may be accessed by the genes for which they are annotated as well as the major and minor target classes to which those genes belong. It offers new analysis tools that are easy for nonspecialists yet with few limitations for experts. ZINC retains its original 3D roots – all molecules are available in biologically relevant, ready-to-dock formats. ZINC is freely available at http://zinc15.docking.org.
Subfields: Computational Theory and Mathematics, Molecular Biology, Pharmacology, 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
- Tommi S. Jaakkola
- Regina Barzilay
- Jure Leskovec
- Wengong Jin
- Tianfan Fu
- Kyle Swanson
- Jimeng Sun
- Marinka Zitnik
In Molecular Biology
- Tommi S. Jaakkola
- Jure Leskovec
- Regina Barzilay
- Wengong Jin
- Marinka Zitnik
- Kyle Swanson
- Vijay S. Pande
- Qi Liu
In Pharmacology
- Kyle Swanson
- Brian K. Shoichet
- Qi Liu
- Tianfan Fu
- Maximilian Nickel
- Douwe Kiela
- Jimeng Sun
- John J. Irwin
In Computational Chemistry & Drug Discovery
- Kyle Swanson
- Tommi S. Jaakkola
- Regina Barzilay
- Vijay S. Pande
- Wengong Jin
- Brian K. Shoichet
- Connor W. Coley
- Qi Liu
Citations in the corpus
- Strategies for Pre-training Graph Neural Networks (2019, methodology): “For the chemistry domain, we use 2 million unlabeled molecules sampled from the ZINC15 database (Sterling & Irwin, 2015) for node-level self-supervised pre-training.”
- Learning Multimodal Graph-to-Graph Translation for Molecular Optimization (2018, methodology): “6 ), and we extracted 120K and 53K translation pairs respectively from the ZINC dataset (Sterling & Irwin, 2015; Jin et al., 2018) for training.”
- WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “This means that molecular properties need to be predicted over very diverse sets of molecules, such as those found in combinatorially large chemical databases like ZINC (Sterling and Irwin, 2015) or DNA-encoded libraries (Lyu et al., 2019; McCloskey et al., 2020).”
- All SMILES Variational Autoencoder (2019, methodology): “We evaluate the All SMILES VAE on standard 250,000 and 310,000 element subsets [16, 28] of the ZINC database of small organic molecules [25, 61].”
- NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions (2018, methodology): “More specifically, we collected all the binding affinity data between drug-like compounds and proteins that satisfied Ki 1:0nm from the ZINC15 database (Sterling and Irwin, 2015).”
- Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models (2018, methodology): “Size Purpose ZINC [30, 31] 980M Commercially available compounds for virtual screening ChEMBL [32] 2M A manually curated database of bioactive drug-like molecules SureChEMBL [33] 17M Named compounds from chemical patents eMolecules 18M Purchasable molecules SuperNatural [34] 330k Natural product…”
- PDBe: improved findability of macromolecular structure data in the PDB (2019, background): “Where possible, we have added cross-references to the database entries for the same compound in other resources, including ChEMBL (21), ChEBI (22), ZINC (23) and DrugBank (24).”
- Mapping the Landscape of Artificial Intelligence Applications against COVID-19 (2020, methodology): “…Ton et al. (2020) develop a Deep Docking (DD) platform that trains a neural network to predict docking scores, which they use to identify a set of 3 million candidate 3C-like protease inhibitors from a set of over 1 billion compounds extracted from the ZINC database (Sterling & Irwin, 2015).”