No Cover Image

Journal article 349 views

Direct deduction of chemical class from NMR spectra

Stefan Kuhn, Carlos Cobas, Agustin Barba, Simon Colreavy-Donnelly, Fabio Caraffini Orcid Logo, Ricardo Moreira Borges

Journal of Magnetic Resonance, Volume: 348, Start page: 107381

Swansea University Author: Fabio Caraffini Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.1016/j.jmr.2023.107381

Abstract

This paper presents a proof-of-concept method for classifying chemical compounds directly from NMR data without performing structure elucidation. This can help to reduce the time in finding good structure candidates, as in most cases matching must be done by a human engineer, or at the very least a...

Full description

Published in: Journal of Magnetic Resonance
ISSN: 1090-7807
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62394
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-01-23T10:51:26Z
last_indexed 2023-02-17T04:16:34Z
id cronfa62394
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-02-16T09:39:54.7354216</datestamp><bib-version>v2</bib-version><id>62394</id><entry>2023-01-23</entry><title>Direct deduction of chemical class from NMR spectra</title><swanseaauthors><author><sid>d0b8d4e63d512d4d67a02a23dd20dfdb</sid><ORCID>0000-0001-9199-7368</ORCID><firstname>Fabio</firstname><surname>Caraffini</surname><name>Fabio Caraffini</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-01-23</date><deptcode>SCS</deptcode><abstract>This paper presents a proof-of-concept method for classifying chemical compounds directly from NMR data without performing structure elucidation. This can help to reduce the time in finding good structure candidates, as in most cases matching must be done by a human engineer, or at the very least a process for matching must be meaningfully interpreted by one. The method identified as suitable for classification is a convolutional neural network (CNN). Other methods, including clustering and image registration, have not been found to be suitable for the task in a comparative analysis. The result shows that deep learning can offer solutions to spectral interpretation problems.</abstract><type>Journal Article</type><journal>Journal of Magnetic Resonance</journal><volume>348</volume><journalNumber/><paginationStart>107381</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1090-7807</issnPrint><issnElectronic/><keywords>NMR; Chemical classification; Image processing; Convolutional neural network; Deep learning</keywords><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-03-01</publishedDate><doi>10.1016/j.jmr.2023.107381</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>S.K acknowledges funding by De Montfort University for computational facilities (VC2020 new staff L SL 2020). C.C and A.B thank Xunta de Galicia for funding the Mestrelab Research Center (CIM), subsidized by the Galician Innovation Agency, through the business aid program for the creation and integration of new business research centers 001_IN853D_2022.</funders><projectreference/><lastEdited>2023-02-16T09:39:54.7354216</lastEdited><Created>2023-01-23T09:32:40.6669145</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Stefan</firstname><surname>Kuhn</surname><order>1</order></author><author><firstname>Carlos</firstname><surname>Cobas</surname><order>2</order></author><author><firstname>Agustin</firstname><surname>Barba</surname><order>3</order></author><author><firstname>Simon</firstname><surname>Colreavy-Donnelly</surname><order>4</order></author><author><firstname>Fabio</firstname><surname>Caraffini</surname><orcid>0000-0001-9199-7368</orcid><order>5</order></author><author><firstname>Ricardo Moreira</firstname><surname>Borges</surname><order>6</order></author></authors><documents><document><filename>Under embargo</filename><originalFilename>Under embargo</originalFilename><uploaded>2023-01-23T10:51:22.9606342</uploaded><type>Output</type><contentLength>560230</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2024-01-21T00:00:00.0000000</embargoDate><documentNotes>&#xA9;2023 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2023-02-16T09:39:54.7354216 v2 62394 2023-01-23 Direct deduction of chemical class from NMR spectra d0b8d4e63d512d4d67a02a23dd20dfdb 0000-0001-9199-7368 Fabio Caraffini Fabio Caraffini true false 2023-01-23 SCS This paper presents a proof-of-concept method for classifying chemical compounds directly from NMR data without performing structure elucidation. This can help to reduce the time in finding good structure candidates, as in most cases matching must be done by a human engineer, or at the very least a process for matching must be meaningfully interpreted by one. The method identified as suitable for classification is a convolutional neural network (CNN). Other methods, including clustering and image registration, have not been found to be suitable for the task in a comparative analysis. The result shows that deep learning can offer solutions to spectral interpretation problems. Journal Article Journal of Magnetic Resonance 348 107381 Elsevier BV 1090-7807 NMR; Chemical classification; Image processing; Convolutional neural network; Deep learning 1 3 2023 2023-03-01 10.1016/j.jmr.2023.107381 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University S.K acknowledges funding by De Montfort University for computational facilities (VC2020 new staff L SL 2020). C.C and A.B thank Xunta de Galicia for funding the Mestrelab Research Center (CIM), subsidized by the Galician Innovation Agency, through the business aid program for the creation and integration of new business research centers 001_IN853D_2022. 2023-02-16T09:39:54.7354216 2023-01-23T09:32:40.6669145 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Stefan Kuhn 1 Carlos Cobas 2 Agustin Barba 3 Simon Colreavy-Donnelly 4 Fabio Caraffini 0000-0001-9199-7368 5 Ricardo Moreira Borges 6 Under embargo Under embargo 2023-01-23T10:51:22.9606342 Output 560230 application/pdf Accepted Manuscript true 2024-01-21T00:00:00.0000000 ©2023 All rights reserved. All article content, except where otherwise noted, is licensed under a Creative Commons Attribution Non-Commercial No Derivatives License (CC-BY-NC-ND) true eng https://creativecommons.org/licenses/by-nc-nd/4.0/
title Direct deduction of chemical class from NMR spectra
spellingShingle Direct deduction of chemical class from NMR spectra
Fabio Caraffini
title_short Direct deduction of chemical class from NMR spectra
title_full Direct deduction of chemical class from NMR spectra
title_fullStr Direct deduction of chemical class from NMR spectra
title_full_unstemmed Direct deduction of chemical class from NMR spectra
title_sort Direct deduction of chemical class from NMR spectra
author_id_str_mv d0b8d4e63d512d4d67a02a23dd20dfdb
author_id_fullname_str_mv d0b8d4e63d512d4d67a02a23dd20dfdb_***_Fabio Caraffini
author Fabio Caraffini
author2 Stefan Kuhn
Carlos Cobas
Agustin Barba
Simon Colreavy-Donnelly
Fabio Caraffini
Ricardo Moreira Borges
format Journal article
container_title Journal of Magnetic Resonance
container_volume 348
container_start_page 107381
publishDate 2023
institution Swansea University
issn 1090-7807
doi_str_mv 10.1016/j.jmr.2023.107381
publisher Elsevier BV
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description This paper presents a proof-of-concept method for classifying chemical compounds directly from NMR data without performing structure elucidation. This can help to reduce the time in finding good structure candidates, as in most cases matching must be done by a human engineer, or at the very least a process for matching must be meaningfully interpreted by one. The method identified as suitable for classification is a convolutional neural network (CNN). Other methods, including clustering and image registration, have not been found to be suitable for the task in a comparative analysis. The result shows that deep learning can offer solutions to spectral interpretation problems.
published_date 2023-03-01T04:21:58Z
_version_ 1763754449461837824
score 11.012678

Similar Items