The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service.

By H. Morgan. 1965

Subfields: 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 Chemistry & Drug Discovery

Citations in the corpus

Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015, methodology): “Circular fingerprints [6] are a refinement of the Morgan algorithm [17], designed to encode which substructures are present in a molecule in a way that is invariant to atom-relabeling.”
Open Babel: An open chemical toolbox (2011, methodology): “Although the algorithm is similar to the original Morgan canonical code [21], various improvements are implemented to improve performance.”
Molecular fingerprint similarity search in virtual screening. (2015, methodology): “◦ ECFP: The de facto standard circular fingerprints are the Extended-Connectivity Fingerprints (ECFPs), based on the Morgan algorithm [26], which were specifically designed for their use in structure-activity modeling [27].”
Modern Hopfield Networks for Few- and Zero-Shot Reaction Prediction (2021, methodology): “Different ﬁngerprint-types have been tried out, e.g. folded Morgan ﬁngerprints with chirality (Morgan, 1965) and the hyperparameter selection procedure (see Table 4) selected Morgan ﬁngerprint size of 2 folded to 4096 features.”
The rise of deep learning in drug discovery. (2018, methodology): “The basic idea is similar to the UGRNN method, which employs NNs to automatically generate a molecular description vector and vector values are learned by training NNs. Inspired by the Morgan circular ﬁngerprint method [48], Duvenaud et al .”
Can graph neural networks count substructures? (2020, methodology): “In the literature of molecular chemistry, substructure counts have been used to generate molecular fingerprints [43, 48] and compute similarities between molecules [1, 53].”
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs (2021, methodology): “We benchmark two types of models: a simple MLP over the Morgan fingerprint (Morgan, 1965) and more advanced GNN models.”
Computer‐aided synthesis design: 40 years on (2012, methodology): “An effective solution to this problem employs the Morgan canonical naming algorithm 70 (or one of its derivatives 71 ) to generate a sequence of characters that can be rapidly compared to others.”
Extensions of marginalized graph kernels (2004, background): “Indeed, this particular scheme is well-known in chemoinformatics under the name of Morgan index ( Morgan, 1965 ), and is considered a good and fast solution to detect graph isomorphism and determine canonical representations of molecules.”