SMILES. 2. Algorithm for generation of unique SMILES notation

By David Weininger, A. Weininger, J. Weininger. 1989

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

Interpreting linear support vector machine models with heat map molecule coloring (2011, background): “The algorithm starts with the initial atom identifier (in our case Daylight invariants [17]) of the center atom and grows a circular substructure around this atom.”
Molecular de-novo design through deep reinforcement learning (2017, background): “Algorithms that always represent a certain molecule with the same SMILES are referred to as canonicalization algorithms [26].”
The Chemistry Development Kit (CDK): An Open-Source Java Library for Chemo-and Bioinformatics (2003, methodology): “The CDK features a generator for canonical SMILES, written to comply with the rules published by the Daylight Inc. founders.”
MoFlow: An Invertible Flow Model for Generating Molecular Graphs (2020, background): “Prior works leverage different deep generative frameworks for generating molecular SMILES codes [33] or molecular graphs, including variational autoencoder (VAE)-based models [4, 5, 12, 16, 19, 20, 31], generative adversarial networks (GAN)-based models [6, 34], and autoregressive (AR)-based models ”
Small molecules of different origins have distinct distributions of structural complexity that correlate with protein-binding profiles (2010, methodology): “Weininger DA, Weininger A, Weininger JL (1989) SMILES 2: Algorithm for generation of unique SMILES notation.”
Translation between Molecules and Natural Language (2022, methodology): “A popular input for these algorithms has been SMILES strings (Weininger, 1988; Weininger et al., 1989), which are a computer-readable linearization of molecule graphs.”
Self-Supervised Graph Transformer on Large-Scale Molecular Data (2020, methodology): “Following these works, [21, 62] take the SMILES representation [59] as input and use RNN-based models to produce molecular representations.”
Randomized SMILES strings improve the quality of molecular generative models (2019, methodology): “This is specially the case with canonical SMILES: Morgan numbering greatly reduces the possible paths, as it tends to prioritize starting in sidechains rather than in the rings of the molecule [28].”
InChI, the IUPAC International Chemical Identifier (2015, methodology): “The resultant colors produce a so called equitable partition, in a way which is conceptually almost same as the intermediate result of the SMILES-2 algorithm [17].”