Atomic ring invariant and Modified CANON extended connectivity algorithm for symmetry perception in molecular graphs and rigorous canonicalization of SMILES

Krotko, Dmytro G.

doi:10.1186/s13321-020-00453-4

Cited by 6 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many popular canonicalization procedures in chemistry are variants of the classical Morgan algorithm [ 21 ], which however uses the bond type of edges as an initial atom invariant and therefore is not domain-independent. Furthermore, non-equivalent atoms can still be assigned identical extended connectivity values, in particular in highly symmetrical molecules [ 23 , 36 ], a problem that is particularly relevant to inorganic cluster chemistry. In contrast, TUCAN only relies on the atomic number as a chemistry-specific invariant.…”

Section: Resultsmentioning

confidence: 99%

TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson

Brammer

Blanke²,

Kellner

et al. 2022

J Cheminform

View full text Add to dashboard Cite

TUCAN is a canonical serialization format that is independent of domain-specific concepts of structure and bonding. The atomic number is the only chemical feature that is used to derive the TUCAN format. Other than that, the format is solely based on the molecular topology. Validation is reported on a manually curated test set of molecules as well as a library of non-chemical graphs. The serialization procedure generates a canonical “tuple-style” output which is bidirectional, allowing the TUCAN string to serve as both identifier and descriptor. Use of the Python NetworkX graph library facilitated a compact and easily extensible implementation. Graphical Abstract

show abstract

Section: Resultsmentioning

confidence: 99%

TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson

Brammer

Blanke²,

Kellner

et al. 2022

J Cheminform

View full text Add to dashboard Cite

show abstract

“…The generation of a unique SMILES representation requires the specification of a canonical atom ordering [ 20 , 21 ]. Over the past decades, various algorithms have been developed to achieve such a canonicalization [ 20 , 21 , 29 – 32 ]. While the matrix canonicity criterion of enu already leads to a canonical ordering of the atoms, this order is not necessarily suitable to create elegant (i.e., easily readable) SMILES strings.…”

Section: Methodsmentioning

confidence: 99%

Development of an open-source software for isomer enumeration

et al. 2023

View full text Add to dashboard Cite

This article documents enu, a freely-downloadable, open-source and stand-alone program written in C++ for the enumeration of the constitutional isomers and stereoisomers of a molecular formula. The program relies on graph theory to enumerate all the constitutional isomers of a given formula on the basis of their canonical adjacency matrix. The stereoisomers of a given constitutional isomer are enumerated as well, on the basis of the automorphism group of this matrix. The isomer list is then reported in the form of canonical SMILES strings within files in XML format. The specification of the molecule family of interest is very flexible and the code is optimized for computational efficiency. The algorithms and implementations underlying enu are described, and simple illustrative applications are presented. The enu code is freely available on GitHub at https://github.com/csms-ethz/CombiFF.

show abstract

“…The conversion of the 3D molecular structure of Arglecin into its 2D representation and subsequent SMILES code can be described mathematically using the concept of graph theory [32]. The 3D molecular structure of Arglecin can be represented as a graph, wherein atoms are represented by nodes and chemical bonds between atoms are represented by edges.…”

Section: Sample Smiles String Representationmentioning

confidence: 99%

Hybrid Genetic Algorithm and CMA-ES Optimization for RNN-Based Chemical Compound Classification

Guo,

Hou,

2024

Mathematics

View full text Add to dashboard Cite

The compound classification strategies addressed in this study encounter challenges related to either low efficiency or accuracy. Precise classification of chemical compounds from SMILES symbols holds significant importance in domains such as drug discovery, materials science, and environmental toxicology. In this paper, we introduce a novel hybrid optimization framework named GA-CMA-ES which integrates Genetic Algorithms (GA) and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to train Recurrent Neural Networks (RNNs) for compound classification. Leveraging the global exploration capabilities og GAs and local exploration abilities of the CMA-ES, the proposed method achieves notable performance, attaining an 83% classification accuracy on a benchmark dataset, surpassing the baseline method. Furthermore, the hybrid approach exhibits enhanced convergence speed, computational efficiency, and robustness across diverse datasets and levels of complexity.

show abstract

Atomic ring invariant and Modified CANON extended connectivity algorithm for symmetry perception in molecular graphs and rigorous canonicalization of SMILES

Cited by 6 publications

References 26 publications

TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson

TUCAN: A molecular identifier and descriptor applicable to the whole periodic table from hydrogen to oganesson

Development of an open-source software for isomer enumeration

Hybrid Genetic Algorithm and CMA-ES Optimization for RNN-Based Chemical Compound Classification

Contact Info

Product

Resources

About