Atom pairs as molecular features in structure-activity studies: definition and applications
By R. Carhart, Dennis H. Smith, R. Venkataraghavan. 1985
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Mukund Deshpande
- George Karypis
- Michihiro Kuramochi
- Nikil Wale
- Esben Jannik Bjerrum
- Garrett B. Goh
- Petr Skoda
- Adrià Cereto-Massagué
Citations in the corpus
- Molecular graph convolutions: moving beyond fingerprints (2016, background): “…molecular graph into subtrees or fixed-length paths (GraphSim Toolkit, OpenEye Sci-entific Software, Inc., Santa Fe, NM, USA), as well as atom pair (AP) descriptors that encode atom types and graph distances (number of intervening bonds) for all pairs of atoms in a molecule (Carhart et al., 1985).”
- Open-source platform to benchmark fingerprints for ligand-based virtual screening (2013, background): “In atom pair (AP) fingerprints [44], pairs of atoms together with the number of bonds separating them are encoded.”
- Frequent substructure-based approaches for classifying chemical compounds (2003, background): “This includes various atom-centered, bond-centered, ring-centered fragments [3], fragments based on atom-pairs [17], topological torsions [66], and fragments that are derived by performing a rule-based compound segmentation [10], [11], [54].”
- SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules (2017, methodology): “[23, 21] The approach seems close to using a mixture of topological torsions[24] with one, two and three atoms and atom-pair[25] fingerprints.”
- Neural Networks for the Prediction of Organic Chemistry Reactions (2016, unknown): “29 This last example is particularly interesting as Go is a complex board game with a search space of 10 170 , which is on the order of chemical space for medium sized molecules.”
- Molecular fingerprint similarity search in virtual screening. (2015, background): “• RDKit [31] RDKit is also a free and open-source cheminformatics toolkit that provides access to several fingerprints: 166-bit MACCS, “Topological” (Daylight-like), “Atom pairs” (based on the atomic environments and shortest path separations of every atom pair in the molecule [42]),“Morgan” (ECFP a”