Scalable Variational Quantum Circuits for Autoencoder-based Drug Discovery

The de novo design of drug molecules is recognized as a time-consuming and costly process, and computational approaches have been applied in each stage of the drug discovery pipeline. Variational autoencoder is one of the computer-aided design methods which explores the chemical space based on an ex...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings - Design, Automation, and Test in Europe Conference and Exhibition s. 340 - 345
Hlavní autoři: Li, Junde, Ghosh, Swaroop
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: EDAA 14.03.2022
Témata:
ISSN:1558-1101
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The de novo design of drug molecules is recognized as a time-consuming and costly process, and computational approaches have been applied in each stage of the drug discovery pipeline. Variational autoencoder is one of the computer-aided design methods which explores the chemical space based on an existing molecular dataset. Quantum machine learning has emerged as an atypical learning method that may speed up some classical learning tasks because of its strong expressive power. However, near-term quantum computers suffer from limited num-ber of qubits which hinders the representation learning in high dimensional spaces. We present a scalable quantum generative autoencoder (SQ-VAE) for simultaneously reconstructing and sampling drug molecules, and a corresponding vanilla variant (SQ-AE) for better reconstruction. The architectural strategies in hybrid quantum classical networks such as, adjustable quantum layer depth, heterogeneous learning rates, and patched quantum circuits are proposed to learn high dimensional dataset such as, ligand-targeted drugs. Extensive experimental results are reported for different dimensions including 8x8 and 32x32 after choosing suitable architectural strategies. The performance of quantum generative autoencoder is compared with the corre-sponding classical counterpart throughout all experiments. The results show that quantum computing advantages can be achieved for normalized low-dimension molecules, and that high-dimension molecules generated from quantum generative autoencoders have better drug properties within the same learning period.
AbstractList The de novo design of drug molecules is recognized as a time-consuming and costly process, and computational approaches have been applied in each stage of the drug discovery pipeline. Variational autoencoder is one of the computer-aided design methods which explores the chemical space based on an existing molecular dataset. Quantum machine learning has emerged as an atypical learning method that may speed up some classical learning tasks because of its strong expressive power. However, near-term quantum computers suffer from limited num-ber of qubits which hinders the representation learning in high dimensional spaces. We present a scalable quantum generative autoencoder (SQ-VAE) for simultaneously reconstructing and sampling drug molecules, and a corresponding vanilla variant (SQ-AE) for better reconstruction. The architectural strategies in hybrid quantum classical networks such as, adjustable quantum layer depth, heterogeneous learning rates, and patched quantum circuits are proposed to learn high dimensional dataset such as, ligand-targeted drugs. Extensive experimental results are reported for different dimensions including 8x8 and 32x32 after choosing suitable architectural strategies. The performance of quantum generative autoencoder is compared with the corre-sponding classical counterpart throughout all experiments. The results show that quantum computing advantages can be achieved for normalized low-dimension molecules, and that high-dimension molecules generated from quantum generative autoencoders have better drug properties within the same learning period.
Author Li, Junde
Ghosh, Swaroop
Author_xml – sequence: 1
  givenname: Junde
  surname: Li
  fullname: Li, Junde
  email: jul1512@psu.edu
  organization: The Pennsylvania State University,Department of Computer Science and Engineering
– sequence: 2
  givenname: Swaroop
  surname: Ghosh
  fullname: Ghosh, Swaroop
  email: szg212@psu.edu
  organization: The Pennsylvania State University,Department of Computer Science and Engineering
BookMark eNotj91KwzAYQKMouE6fwAvzAq35kjRNLku3-cNAxOntSNMvEukaSVthb6_grs7d4ZyMXAxxQELugBVcGDD3q3q3LiWALDjjvDBVJUslz0gmjAbDlVDqnCygLHUOwOCKZOP4xRgrBTcL8vzmbG_bHumHTcFOIQ62p6-zHab5QJuQ3BymkfqYaD1PEQcXO0x5a0fs6CrNn3QVRhd_MB2vyaW3_Yg3Jy7J-2a9ax7z7cvDU1Nv88CZmHL3V8ekrzqDHjqorAemla-0M8hFpxVrjW8dawUH40qOSnvNLDiHmkupxJLc_nsDIu6_UzjYdNyfvsUvDfRPuw
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.23919/DATE54114.2022.9774564
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISBN 3981926366
9783981926361
EISSN 1558-1101
EndPage 345
ExternalDocumentID 9774564
Genre orig-research
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
FEDTE
IEGSK
IPLJI
KZ1
LMP
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i203t-c56404f7d9ef1d17af1086f78c9e23d860b9fbc0b3219c52e68f80a1cce824463
IEDL.DBID RIE
ISICitedReferencesCount 11
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000819484300067&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:36:23 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-c56404f7d9ef1d17af1086f78c9e23d860b9fbc0b3219c52e68f80a1cce824463
PageCount 6
ParticipantIDs ieee_primary_9774564
PublicationCentury 2000
PublicationDate 2022-March-14
PublicationDateYYYYMMDD 2022-03-14
PublicationDate_xml – month: 03
  year: 2022
  text: 2022-March-14
  day: 14
PublicationDecade 2020
PublicationTitle Proceedings - Design, Automation, and Test in Europe Conference and Exhibition
PublicationTitleAbbrev DATE
PublicationYear 2022
Publisher EDAA
Publisher_xml – name: EDAA
SSID ssj0005329
ssib048702904
ssib051591249
Score 2.3022194
Snippet The de novo design of drug molecules is recognized as a time-consuming and costly process, and computational approaches have been applied in each stage of the...
SourceID ieee
SourceType Publisher
StartPage 340
SubjectTerms Drug Discovery
Drugs
Image synthesis
Learning systems
Pipelines
Quantum Machine Learning
Qubit
Representation learning
Space exploration
Variational Autoen-coder
Title Scalable Variational Quantum Circuits for Autoencoder-based Drug Discovery
URI https://ieeexplore.ieee.org/document/9774564
WOSCitedRecordID wos000819484300067&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELXaigGWQgviWx4Yces4jj_GqqVCDFURBXWr4i-UgRalCRL_HjtNC0gsbFGGyLoX5-457-4BcON4IqmKHBI0ZYgqbZCU3CFmrRIp17FKcWU2wScTMZ_LaQPc7nphrLWV-Mz2wmX1L9-sdBmOyvqhVkkYbYIm52zTq7V9d3zdjYn8phYhTUcVtdjKPWIiN_ouEstI9keD2V1CPRvwHJGQXv3oXx4rVYoZt_-3uENw_N2rB6e7LHQEGnbZAe2tWQOs924HHPyYPNgFD08em9A1BV88Wa4PBOFj6eNcvsFhlusyK9bQV7RwUBarMO3S2ByFnGfgKC9f4Shb6yD__DwGz-O72fAe1bYKKCM4LpD2q8TUcSOti0zEUxfclhwXWloSG8Gwkk5prGL_NdMJsUw4gdNIayt8McDiE9Barpb2FEAtsbE6uF95BAzhgmmHExwgVzTV6RnohkAt3jeTMxZ1jM7_vn0B9gMWQeEV0UvQKvLSXoE9_VFk6_y6gvsLfoGpxg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT8JAEJ0gmqgXFDR-uwePFrfbbbt7JIBBRYIRDTfS7ofpQTClNfHfu1sKaOLFW9NDs5nX7czbvpkHcKVDn9PY1Q6jUeDQWEiH81A7gVIxi0LhxREuzCbCwYCNx3xYgetVL4xSqhCfqaa9LP7ly5nI7VHZja1V_IBuwKZPKcGLbq3l22Mqb0z4mlzYRO0W5GIp-PAIXyi8iMddftNpjbo-NXzAsERCmuXDf7msFEnmtva_5e3BwbpbDw1XeWgfKmpah9rSrgGVu7cOuz9mDzbg_tmgY_um0Kuhy-WRIHrKTaTzd9ROUpEn2RyZmha18mxm511KlTo260nUSfM31EnmwgpAvw7g5bY7avec0ljBSQj2MkeYVWKqQ8mVdqUbRtr6LemQCa6IJ1mAY65jgWPPfM-ET1TANMORK4RiphwIvEOoTmdTdQRIcCyVsP5XBgFJQhYIjX1sQY9pJKJjaNhATT4WszMmZYxO_r59Cdu90WN_0r8bPJzCjsXF6r1cegbVLM3VOWyJzyyZpxcF9N-Dra0N
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+-+Design%2C+Automation%2C+and+Test+in+Europe+Conference+and+Exhibition&rft.atitle=Scalable+Variational+Quantum+Circuits+for+Autoencoder-based+Drug+Discovery&rft.au=Li%2C+Junde&rft.au=Ghosh%2C+Swaroop&rft.date=2022-03-14&rft.pub=EDAA&rft.eissn=1558-1101&rft.spage=340&rft.epage=345&rft_id=info:doi/10.23919%2FDATE54114.2022.9774564&rft.externalDocID=9774564