Reoptimization of MDL Keys for Use in Drug Discovery

By J. L. Durant, B. A. Leland, D. Henry, J. Nourse. 2002

1,688 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Molecular Biology, Pharmacology

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

1. Evan E. Bolton
2. Stephen H. Bryant
3. Sunghwan Kim
4. Kyle Swanson
5. Wenbo Yu
6. Paul A. Thiessen
7. Alexander D. MacKerell
8. George Karypis

In Molecular Biology

1. Stephen H. Bryant
2. Evan E. Bolton
3. Kyle Swanson
4. Wenbo Yu
5. Paul A. Thiessen
6. Yanli Wang
7. Sunghwan Kim
8. Alexander D. MacKerell

In Pharmacology

1. Evan E. Bolton
2. Alexander D. MacKerell
3. Wenbo Yu
4. Stephen H. Bryant
5. Heng Ji
6. Sandeepkumar Kothiwale
7. Jens Meiler
8. E. W. Lowe

Citations in the corpus

• Ligand biological activity predicted by cleaning positive and negative chemical correlations (2019, background): “However, regardless of how one defines chemical motifs— common strategies include using pharmacological intuitions (15– 17), enumerating all linear or circular fragments below a certain size around every atom (17, 18), or unsupervised learning (19)— a molecule has many motifs, but only a few are…”
• ChemProt: a disease chemical biology database (2010, background): “The 166 MACCS keys, encode the presence or absence of predefined substructural or functional groups (29).”
• Comparison of descriptor spaces for chemical compound retrieval and classification (2006, background): “Maccs Keys (MK) Molecular Design Limited (MDL) created the key based fingerprints (Maccs Keys) [4] based on pattern matching of a chemical compound structure to a pre-defined set of structural fragments that have been identified by domain experts [19].”
• Virtual and biomolecular screening converge on a selective agonist for GPR30 (2006, methodology): “Smi2fp_ascii (Daylight Chemical Information Systems) and MACCSKeys320 Generator (Mesa Analytics and Computing) software was used to compute Daylight and MD”
• Message passing neural networks for molecular property prediction (2019, background): “Improvements in property prediction accuracy using these models has primary come through the development of better molecular descriptors [44, 8, 15, 33, 31, 32].”
• Computational Methods in Drug Discovery (2014, methodology): “Commonly used fingerprints include the ISIS (Integrated Scientific Information System) keys with 166 bits and the MDL (Molecular Design Limited) MACCS (Molecular ACCess System) keys (Durant et al., 2002) with 960 bits.”