Molecular generation by Fast Assembly of (Deep)SMILES fragments

Abstract Background In recent years, in silico molecular design is regaining interest. To generate on a computer molecules with optimized properties, scoring functions can be coupled with a molecular generator to design novel molecules with a desired property profile. Results In this article, a simp...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Francois Berenger, Koji Tsuda
Formato: article
Lenguaje:EN
Publicado: BMC 2021
Materias:
Acceso en línea:https://doaj.org/article/5439dd3838a54210ab3db8f99d806114
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5439dd3838a54210ab3db8f99d806114
record_format dspace
spelling oai:doaj.org-article:5439dd3838a54210ab3db8f99d8061142021-11-21T12:33:31ZMolecular generation by Fast Assembly of (Deep)SMILES fragments10.1186/s13321-021-00566-41758-2946https://doaj.org/article/5439dd3838a54210ab3db8f99d8061142021-11-01T00:00:00Zhttps://doi.org/10.1186/s13321-021-00566-4https://doaj.org/toc/1758-2946Abstract Background In recent years, in silico molecular design is regaining interest. To generate on a computer molecules with optimized properties, scoring functions can be coupled with a molecular generator to design novel molecules with a desired property profile. Results In this article, a simple method is described to generate only valid molecules at high frequency ( $$>300,000$$ > 300 , 000 molecule/s using a single CPU core), given a molecular training set. The proposed method generates diverse SMILES (or DeepSMILES) encoded molecules while also showing some propensity at training set distribution matching. When working with DeepSMILES, the method reaches peak performance ( $$>340,000$$ > 340 , 000 molecule/s) because it relies almost exclusively on string operations. The “Fast Assembly of SMILES Fragments” software is released as open-source at https://github.com/UnixJunkie/FASMIFRA . Experiments regarding speed, training set distribution matching, molecular diversity and benchmark against several other methods are also shown.Francois BerengerKoji TsudaBMCarticleMolecular generationMolecular fragmentsSMILESDeepSMILESInformation technologyT58.5-58.64ChemistryQD1-999ENJournal of Cheminformatics, Vol 13, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Molecular generation
Molecular fragments
SMILES
DeepSMILES
Information technology
T58.5-58.64
Chemistry
QD1-999
spellingShingle Molecular generation
Molecular fragments
SMILES
DeepSMILES
Information technology
T58.5-58.64
Chemistry
QD1-999
Francois Berenger
Koji Tsuda
Molecular generation by Fast Assembly of (Deep)SMILES fragments
description Abstract Background In recent years, in silico molecular design is regaining interest. To generate on a computer molecules with optimized properties, scoring functions can be coupled with a molecular generator to design novel molecules with a desired property profile. Results In this article, a simple method is described to generate only valid molecules at high frequency ( $$>300,000$$ > 300 , 000 molecule/s using a single CPU core), given a molecular training set. The proposed method generates diverse SMILES (or DeepSMILES) encoded molecules while also showing some propensity at training set distribution matching. When working with DeepSMILES, the method reaches peak performance ( $$>340,000$$ > 340 , 000 molecule/s) because it relies almost exclusively on string operations. The “Fast Assembly of SMILES Fragments” software is released as open-source at https://github.com/UnixJunkie/FASMIFRA . Experiments regarding speed, training set distribution matching, molecular diversity and benchmark against several other methods are also shown.
format article
author Francois Berenger
Koji Tsuda
author_facet Francois Berenger
Koji Tsuda
author_sort Francois Berenger
title Molecular generation by Fast Assembly of (Deep)SMILES fragments
title_short Molecular generation by Fast Assembly of (Deep)SMILES fragments
title_full Molecular generation by Fast Assembly of (Deep)SMILES fragments
title_fullStr Molecular generation by Fast Assembly of (Deep)SMILES fragments
title_full_unstemmed Molecular generation by Fast Assembly of (Deep)SMILES fragments
title_sort molecular generation by fast assembly of (deep)smiles fragments
publisher BMC
publishDate 2021
url https://doaj.org/article/5439dd3838a54210ab3db8f99d806114
work_keys_str_mv AT francoisberenger moleculargenerationbyfastassemblyofdeepsmilesfragments
AT kojitsuda moleculargenerationbyfastassemblyofdeepsmilesfragments
_version_ 1718418942599364608