De Novo Molecular Design by Combining Deep Autoencoder Recurrent Neural Networks with Generative Topographic Mapping

Journal of Chemical Information and Modeling
Boris SattarovAlexandre Varnek

Abstract

Here we show that Generative Topographic Mapping (GTM) can be used to explore the latent space of the SMILES-based autoencoders and generate focused molecular libraries of interest. We have built a sequence-to-sequence neural network with Bidirectional Long Short-Term Memory layers and trained it on the SMILES strings from ChEMBL23. Very high reconstruction rates of the test set molecules were achieved (>98%), which are comparable to the ones reported in related publications. Using GTM, we have visualized the autoencoder latent space on the two-dimensional topographic map. Targeted map zones can be used for generating novel molecular structures by sampling associated latent space points and decoding them to SMILES. The sampling method based on a genetic algorithm was introduced to optimize compound properties "on the fly". The generated focused molecular libraries were shown to contain original and a priori feasible compounds which, pending actual synthesis and testing, showed encouraging behavior in independent structure-based affinity estimation procedures (pharmacophore matching, docking).

References

Aug 1, 1996·Current Opinion in Biotechnology·H J Böhm
Oct 23, 1997·Neural Computation·S Hochreiter, J Schmidhuber
Jul 15, 2000·Journal of Computer-aided Molecular Design·G SchneiderP Schneider
Apr 30, 2004·Journal of Computational Chemistry·Junmei WangDavid A Case
Jun 5, 2004·Journal of Molecular Graphics & Modelling·Carla J ChurchwellJean-Loup Faulon
Aug 2, 2005·Nature Reviews. Drug Discovery·Gisbert Schneider, Uli Fechner
Nov 18, 2005·Journal of Computer-aided Molecular Design·A VarnekV P Solov'ev
Jul 25, 2006·Journal of Chemical Information and Modeling·Dharmesh M ManiyarAndreas Sewing
Oct 13, 2006·Journal of Computer-aided Molecular Design·Nathan BrownJohann Gasteiger
Jul 19, 2008·Nature Reviews. Drug Discovery·Yusuf Tanrikulu, Gisbert Schneider
Jun 24, 2010·European Journal of Medicinal Chemistry·A A ToropovE Benfenati
Oct 12, 2010·Journal of Medicinal Chemistry·Peter RipphausenJürgen Bajorath
Feb 26, 2011·Drug Discovery Today·Peter RipphausenJürgen Bajorath
Jun 24, 2011·Journal of Chemical Information and Modeling·John R OwenFabian López-Vallejo
Oct 11, 2011·Bioorganic & Medicinal Chemistry Letters·Pavel V KarpovNikolay S Zefirov
Feb 24, 2012·PLoS Computational Biology·Markus HartenfellerGisbert Schneider
Dec 12, 2012·Journal of Chemical Information and Modeling·Laurent Hoffer, Dragos Horvath
Mar 30, 2013·Journal of Chemical Information and Modeling·Laurent HofferDragos Horvath
Jun 22, 2013·IEEE Transactions on Pattern Analysis and Machine Intelligence·Yoshua BengioPascal Vincent
Nov 26, 2014·Journal of Chemical Information and Modeling·Héléna A GasparAlexandre Varnek
May 23, 2015·Molecules : a Journal of Synthetic Chemistry and Natural Product Chemistry·Laurent HofferDragos Horvath
May 29, 2015·Nature·Yann LeCunGeoffrey Hinton
Oct 13, 2015·Journal of Chemical Information and Modeling·Héléna A GasparAlexandre Varnek
Nov 14, 2015·Journal of Computer-aided Molecular Design·Pavel SidorovDragos Horvath
Jan 29, 2016·Journal of Chemical Information and Modeling·Tomoyuki MiyaoKimito Funatsu
Jun 14, 2016·Expert Opinion on Drug Discovery·Igor I BaskinIgor V Tetko
Jul 14, 2016·Journal of Chemical Information and Modeling·Kyrylo KlimenkoAlexandre Varnek
Jan 12, 2010·Molecular Informatics·Tomoyuki MiyaoKimito Funatsu
Jan 17, 2011·Molecular Informatics·Alexandre Varnek, Igor I Baskin
Jun 1, 2015·Molecular Informatics·H A GasparA Varnek
Aug 6, 2016·Molecular Informatics·Erik GawehnGisbert Schneider
Mar 4, 2017·Journal of Chemical Information and Modeling·William YuanAlbert C Koong
Apr 20, 2017·Molecular Informatics·Dragos HorvathAlexandre Varnek
Jul 9, 2017·Journal of Computer-aided Molecular Design·Igor I BaskinAlexandre Varnek
Nov 1, 2017·Journal of Cheminformatics·Marcus OlivecronaHongming Chen
Nov 3, 2017·Molecular Informatics·Anvita GuptaGisbert Schneider
Dec 14, 2017·Molecular Informatics·Thomas BlaschkeHongming Chen
Feb 3, 2018·ACS Central Science·Marwin H S SeglerMark P Waller
Mar 14, 2018·ACS Central Science·Rafael Gómez-BombarelliAlán Aspuru-Guzik
May 16, 2018·Journal of Chemical Information and Modeling·Evgeny PutinAlex Zhavoronkov
Jul 25, 2018·Molecular Informatics·Marta GlavatskikhAlexandre Varnek
Jul 28, 2018·Science Advances·Mariya PopovaAlexander Tropsha
Sep 3, 2018·Journal of Computer-aided Molecular Design·Michael ZheninDragos Horvath

❮ Previous
Next ❯

Citations

Dec 6, 2019·Nature Reviews. Drug Discovery·Petra SchneiderGisbert Schneider
Apr 30, 2020·Molecular Informatics·Arkadii LinAlexandre Varnek
Mar 20, 2020·Chemical Science·Ryan-Rhys Griffiths, José Miguel Hernández-Lobato
Apr 2, 2020·Expert Opinion on Drug Discovery·Igor I Baskin
Aug 6, 2020·Molecules : a Journal of Synthetic Chemistry and Natural Product Chemistry·Soumitra SamantaDouglas B Kell
Nov 5, 2019·Molecular Informatics·Philippe GantzerCarlos Nieto-Draghi
Aug 14, 2019·Journal of Computer-aided Molecular Design·Arkadii LinAlexandre Varnek
Nov 26, 2020·Molecular Informatics·Takahiro InoueKimito Funatsu
Feb 6, 2021·Journal of Molecular Modeling·Yuemin Bian, Xiang-Qun Xie
Feb 6, 2021·Scientific Reports·William BortAlexandre Varnek
Dec 24, 2020·Physical Chemistry Chemical Physics : PCCP·Katherine J SchultzRyan S Renslow
Mar 13, 2021·Nature Biomedical Engineering·Payel DasAleksandra Mojsilovic
Jul 6, 2020·Current Topics in Medicinal Chemistry·Ravina KhandelwalSanjeev Kumar Singh
Dec 1, 2019·Drug Discovery Today. Technologies·Dragos HorvathAlexandre Varnek
Dec 24, 2020·Expert Opinion on Drug Discovery·Julio Caballero
Jun 18, 2021·Frontiers in Immunology·José T Moreira-FilhoCarolina H Andrade
Jul 3, 2021·Chemical Society Reviews·Eugene N MuratovAlexander Tropsha
Jul 10, 2021·Journal of Chemical Information and Modeling·Biao MaYasushi Okuno
Oct 30, 2020·Journal of Chemical Information and Modeling·Thomas BlaschkeAtanas Patronov
Jul 21, 2020·Journal of Chemical Information and Modeling·Kaifu GaoGuo-Wei Wei
Dec 2, 2020·Journal of Chemical Information and Modeling·Vishal B SiramshettyAlexey V Zakharov
Dec 11, 2019·Journal of Chemical Information and Modeling·Seung Hwan HongWoo Youn Kim
Jan 7, 2020·Journal of Chemical Information and Modeling·Francesca GrisoniGisbert Schneider
Aug 28, 2020·Journal of Chemical Information and Modeling·Alberga DomenicoNicolotti Orazio
Apr 9, 2020·The Journal of Physical Chemistry. a·Nicolae C Iovanac, Brett M Savoie
Aug 31, 2021·RSC Medicinal Chemistry·Lauren L Grant, Clarissa S Sit
Oct 27, 2021·Journal of Chemical Information and Modeling·Tiago SousaMiguel Rocha
Nov 5, 2021·Briefings in Bioinformatics·Jianyuan DengFusheng Wang
Nov 16, 2021·Journal of Cheminformatics·Francois Berenger, Koji Tsuda
Nov 19, 2021·Journal of Chemical Information and Modeling·Sowmya Ramaswamy KrishnanArijit Roy
Dec 18, 2021·Expert Opinion on Drug Discovery·Martin Vogt
Jan 6, 2022·The Journal of Physical Chemistry. a·Nicolae C IovanacBrett M Savoie

❮ Previous
Next ❯

Related Concepts

Trending Feeds

COVID-19

Coronaviruses encompass a large family of viruses that cause the common cold as well as more serious diseases, such as the ongoing outbreak of coronavirus disease 2019 (COVID-19; formally known as 2019-nCoV). Coronaviruses can spread from animals to humans; symptoms include fever, cough, shortness of breath, and breathing difficulties; in more severe cases, infection can lead to death. This feed covers recent research on COVID-19.

Blastomycosis

Blastomycosis fungal infections spread through inhaling Blastomyces dermatitidis spores. Discover the latest research on blastomycosis fungal infections here.

Nuclear Pore Complex in ALS/FTD

Alterations in nucleocytoplasmic transport, controlled by the nuclear pore complex, may be involved in the pathomechanism underlying multiple neurodegenerative diseases including Amyotrophic Lateral Sclerosis and Frontotemporal Dementia. Here is the latest research on the nuclear pore complex in ALS and FTD.

Applications of Molecular Barcoding

The concept of molecular barcoding is that each original DNA or RNA molecule is attached to a unique sequence barcode. Sequence reads having different barcodes represent different original molecules, while sequence reads having the same barcode are results of PCR duplication from one original molecule. Discover the latest research on molecular barcoding here.

Chronic Fatigue Syndrome

Chronic fatigue syndrome is a disease characterized by unexplained disabling fatigue; the pathology of which is incompletely understood. Discover the latest research on chronic fatigue syndrome here.

Evolution of Pluripotency

Pluripotency refers to the ability of a cell to develop into three primary germ cell layers of the embryo. This feed focuses on the mechanisms that underlie the evolution of pluripotency. Here is the latest research.

Position Effect Variegation

Position Effect Variagation occurs when a gene is inactivated due to its positioning near heterochromatic regions within a chromosome. Discover the latest research on Position Effect Variagation here.

STING Receptor Agonists

Stimulator of IFN genes (STING) are a group of transmembrane proteins that are involved in the induction of type I interferon that is important in the innate immune response. The stimulation of STING has been an active area of research in the treatment of cancer and infectious diseases. Here is the latest research on STING receptor agonists.

Microbicide

Microbicides are products that can be applied to vaginal or rectal mucosal surfaces with the goal of preventing, or at least significantly reducing, the transmission of sexually transmitted infections. Here is the latest research on microbicides.

© 2022 Meta ULC. All rights reserved