Universal Informatics · Research reading room

Quantum annealing versus classical machine learning applied to a simplified computational biology problem

npj Quantum Information

Original publication · Original publication

Attributed extracts from the research record

“Transcription factors regulate gene expression, but how these proteins recognize and specifically bind to their DNA targets is still debated. Machine learning models are effective means to reveal interaction mechanisms. Here we studied the ability of a quantum machine learning approach to classify and rank binding affinities.”
“Despite technological limitations, we find a slight advantage in classification performance and nearly equal ranking performance using the quantum annealer for these fairly small training data sets.”
“Thus, we propose that quantum annealing might be an effective method to implement machine learning for certain computational biology problems.

Evidence and provenance

Chapter Trust Factor uses a minimum of three distinct qualifying studies. Publication records retain their own evidence and assessment.

Study design and assessment
design
assessment
Not recorded
trust Factor
score
Not recorded
scope
Paper
status
unassessed
randomized Controlled Trial
Not recorded
blinding
not-confirmed
peer Reviewed
false
basis
Publication-specific design or publication status remains unconfirmed.
sources

https://www.nature.com/articles/s41534-018-0060-8

review Scope
Existing publication-specific assessments and bibliographic indexing; no blanket full-text appraisal.
assessed At
2026-10-27
jadad
status
unassessed
score
Not recorded
evidence
Not recorded
Topics and recorded topic scores
  1. key
    general:sound-xxviii
    title
    Quantum computing methods for bioinformatics and gene-expression modelling
    collection
    general
    trust Score
    Not recorded
Citation snapshot and identifiers
id
src-32ff0961cd36
doi
10.1038/s41534-018-0060-8
pmid
Not recorded
citation Snapshot
Not recorded
citations By Collection
general
50
Complete approved library record
id
src-32ff0961cd36
publication Key
Not recorded
aliases
None recorded
title
Quantum annealing versus classical machine learning applied to a simplified computational biology problem
journal
npj Quantum Information
publisher Family
nature
publisher Family Label
Nature Portfolio
neurotransmitters
None recorded
year
Not recorded
authors
design
kind
Source record
identity Conflict
Not recorded
doi
10.1038/s41534-018-0060-8
urls

https://www.nature.com/articles/s41534-018-0060-8 · https://doi.org/10.1038/s41534-018-0060-8

collections

general

categories

Gene expression · Genetics & genomics · Methods & context

targets
None recorded
priority
0
quotes

“Transcription factors regulate gene expression, but how these proteins recognize and specifically bind to their DNA targets is still debated. Machine learning models are effective means to reveal interaction mechanisms. Here we studied the ability of a quantum machine learning approach to classify and rank binding affinities.” · “Despite technological limitations, we find a slight advantage in classification performance and nearly equal ranking performance using the quantum annealer for these fairly small training data sets.” · “Thus, we propose that quantum annealing might be an effective method to implement machine learning for certain computational biology problems.

summary
limitation
citation Count
50
paper Trust Assessment
score
Not recorded
scope
Paper
status
unassessed
randomized Controlled Trial
Not recorded
blinding
not-confirmed
peer Reviewed
false
basis
Publication-specific design or publication status remains unconfirmed.
sources

https://www.nature.com/articles/s41534-018-0060-8

review Scope
Existing publication-specific assessments and bibliographic indexing; no blanket full-text appraisal.
assessed At
2026-10-27
citations By Collection
general
50
topics
  1. key
    general:sound-xxviii
    title
    Quantum computing methods for bioinformatics and gene-expression modelling
    collection
    general
    trust Score
    Not recorded
journal Key
npjquantuminformation
journal Label
npj Quantum Information
chapter Entries
  1. id
    general-sound-xxviii-src-32ff0961cd36
    record Id
    src-32ff0961cd36
    title
    Quantum annealing versus classical machine learning applied to a simplified computational biology problem
    journal
    npj Quantum Information
    year
    Not recorded
    authors
    design
    urls

    https://www.nature.com/articles/s41534-018-0060-8 · https://doi.org/10.1038/s41534-018-0060-8

    quotes
      1. text
        “Transcription factors regulate gene expression, but how these proteins recognize and specifically bind to their DNA targets is still debated. Machine learning models are effective means to reveal interaction mechanisms. Here we studied the ability of a quantum machine learning approach to classify and rank binding affinities.”
        emphasis
        false
      1. text
        “Despite technological limitations, we find a slight advantage in classification performance and nearly equal ranking performance using the quantum annealer for these fairly small training data sets.”
        emphasis
        false
      1. text
        “Thus, we propose that quantum annealing might be an effective method to implement machine learning for certain computational biology problems.
        emphasis
        false
    citation Count
    50
    source Pages

    115

    targets
    None recorded
    categories

    Gene expression · Genetics & genomics · Methods & context

    doi
    10.1038/s41534-018-0060-8
    pmid
    Not recorded
    paper Trust Assessment
    score
    Not recorded
    scope
    Paper
    status
    unassessed
    randomized Controlled Trial
    Not recorded
    blinding
    not-confirmed
    peer Reviewed
    false
    basis
    Publication-specific design or publication status remains unconfirmed.
    sources

    https://www.nature.com/articles/s41534-018-0060-8

    review Scope
    Existing publication-specific assessments and bibliographic indexing; no blanket full-text appraisal.
    assessed At
    2026-10-27
    collection
    general
    chapter Number
    7
    topic Id
    sound-xxviii
    topic Title
    Quantum computing methods for bioinformatics and gene-expression modelling
    trust Score
    Not recorded
jadad
status
unassessed
score
Not recorded
condition Evidence
None recorded
conditions
None recorded
topic Trust Scores
None recorded
full Text
status
reuse-review
retrieval Available
false
url
https://pmc-oa-opendata.s3.amazonaws.com/PMC5891835.1/PMC5891835.1.xml?md5=db0b292b8f60c94f7e259dd68312e22f
pmcid
PMC5891835
rights
license
TDM
use
Private text mining
public Fulltext Redistribution
false
provider Upload
false
model Training
false
basis
https://pmc.ncbi.nlm.nih.gov/tools/pmcaws/
article Rights

This file is available for text mining. It may also be used consistent with the principles of fair use under the copyright law.

sha256
1fe7e128719897eadb80aca7b8342655bd0076f4d925e4ecdc9df66ad3ee0999
checked At
2026-10-24

Open this publication in the interactive library