PET PET
  • My Account
  • Subscribe
Become a Friend Donate
  • About Us
    • People
    • Press Office
    • Our History
  • Get Involved
    • Become a Friend of PET
    • Volunteer
    • Campaigns
    • Writing Scheme
    • Partnership and Sponsorship
    • Advertise with Us
  • Donate
    • Become a Friend of PET
  • BioNews
    • News
    • Comment
    • Reviews
    • Elsewhere
    • Topics
    • Glossary
    • Newsletters
  • Events
    • Upcoming Events
    • Previous Events
  • Engagement
    • Policy and Projects
      • Resources
    • Education
  • Jobs & Opportunities
  • Contact Us
  • About Us
    • People
    • Press Office
    • Our History
  • Get Involved
    • Become a Friend of PET
    • Volunteer
    • Campaigns
    • Writing Scheme
    • Partnership and Sponsorship
    • Advertise with Us
  • Donate
    • Become a Friend of PET
  • BioNews
    • News
    • Comment
    • Reviews
    • Elsewhere
    • Topics
    • Glossary
    • Newsletters
  • Events
    • Upcoming Events
    • Previous Events
  • Engagement
    • Policy and Projects
      • Resources
    • Education
  • Jobs & Opportunities
  • Contact Us
  • My Account
  • Subscribe
  • Privacy Statement
  • Advertising Policy
  • Thanks and Acknowledgements
PETBioNewsNewsMachine learning technique detects epigenetic drivers of cancers

BioNews

Machine learning technique detects epigenetic drivers of cancers

Published 14 May 2021 posted in News and appears in BioNews 1095

Author

Eleanor Mackle

Image by Christoph Bock/Max Planck Institute for Informatics via Wikimedia Commons. Depicts a DNA molecule that is methylated on both strands on the centre cytosine.
CC BY-SA 3.0
Image by Christoph Bock/Max Planck Institute for Informatics via Wikimedia Commons. Depicts a DNA molecule that is methylated on both strands on the centre cytosine.

Machine learning has been used to predict whether certain epigenetic changes are likely to lead to cancer...

Machine learning has been used to predict whether certain epigenetic changes are likely to lead to cancer.

Researchers already know that epigenetic changes – which modify the activation of genes, but not the DNA sequence itself – are key factors in cancer. However, these changes occur randomly and so it is difficult to differentiate the 'driver' changes that result in cancer, from the 'passenger' mutations that do not. 

'If we can profile a large number of tumours with techniques like this, we can map the epigenetic changes that are contributing to tumour growth in certain cancers,' said Dr Dan Landau, associate professor of medicine at Weill Cornell Medicine, New York, who was the senior author of the study. 

This study published in Cancer Discovery focused on a chemical process called DNA methylation, which is an epigenetic change that can result in certain genes being 'silenced'. The researchers created an algorithm called MethSig to predict which mutation would ultimately lead to tumour growth.

The algorithm the authors developed uses statistical methods, and unlike previous work, it accounts for biological features that are known to affect the random rate of DNA methylation changes. They applied their model to both blood and solid tumours, and found that it was able to infer the small fraction of methylation changes that were 'driver' events, from thousands of 'passenger' ones that occur after the initial change. 

To confirm the cancer drivers they found, the scientists then used CRISPR/Cas9 genome editing to eliminate the affected gene in chronic lymphocytic leukaemia cells. They found that when the affected gene was absent and the cells were left untreated, there was enhanced cell growth, which is a key marker of cancer. Overall, they were able to conclude that the MethSig algorithm achieved higher sensitivity and specificity than other methods, and was consistent across patients and tumour types.  

The study's first author, Dr Heng Pan, at the Institute of Computational Biomedicine at Weill Cornell Medicine said, 'MethSig produced estimated risks for each patient, and we found that patients with higher estimated risks were more likely to have had worse outcomes'. 

Further work is needed to enhance the performance of the technique, and reduce false positives. Professor Landau explained the goal of their work, saying, 'ultimately we envision being able to map the entire landscape of cancer-driving DNA methylation changes, for different tumour types and in the contexts of different treatments'.  

Sources and References

  • 10/05/2021
    Cancer Discovery
    Discovery of candidate DNA methylation cancer driver genes
  • 10/05/2021
    Weill Cornell Medicine
    New mapping technique reveals epigenetic drivers of cancers
  • 11/05/2021
    Health Europa
    Identifying epigenetic drivers of cancer with machine learning
  • 10/05/2021
    Florida News Times
    New mapping technology reveals epigenetic drivers of cancer

Related Articles

Image by Peter Artymiuk via the Wellcome Collection. Depicts the shadow of a DNA double helix, on a background that shows the fluorescent banding of the output from a DNA sequencing machine.
CC BY 4.0
Image by Peter Artymiuk via the Wellcome Collection. Depicts the shadow of a DNA double helix, on a background that shows the fluorescent banding of the sequencing output from an automated DNA sequencing machine.
News
7 May 2021 • 2 minutes read

PARP inhibitor is most effective in ovarian cancer patients with DNA repair mutations

by Emma Bunting

New research suggests mutations in multiple DNA repair genes can determine how well ovarian cancer patients will respond to the PARP inhibitor, rucaparib...

Image by Christoph Bock/Max Planck Institute for Informatics via Wikimedia Commons. Depicts a DNA molecule that is methylated on both strands on the centre cytosine.
CC BY-SA 3.0
Image by Christoph Bock/Max Planck Institute for Informatics via Wikimedia Commons. Depicts a DNA molecule that is methylated on both strands on the centre cytosine.
News
15 May 2020 • 2 minutes read

First epigenetic study in 3D human cancer cells

by Dr Charlott Repschläger

Researchers have, for the first time, characterised the epigenetic profile of tumour organoids and made their results available in public databases...

Image by Christoph Bock/Max Planck Institute for Informatics via Wikimedia Commons. Depicts a DNA molecule that is methylated on both strands on the centre cytosine.
CC BY-SA 3.0
Image by Christoph Bock/Max Planck Institute for Informatics via Wikimedia Commons. Depicts a DNA molecule that is methylated on both strands on the centre cytosine.
News
7 December 2018 • 3 minutes read

Epigenetics may give 'universal' cancer test

by Dr Charlott Repschläger

Australian researchers have developed a cancer test, which could potentially detect cancerous DNA in blood and tissue samples in under 10 minutes...

Leave a Reply Cancel reply

You must be logged in to post a comment.

« COVID-19 vaccines do not damage the placenta or cause infertility

Data-Label The UK's Leading Supplier Of Medical Labels & Asset Labels

RetiringDentist.co.uk The UK's Leading M&A Company.

Find out how you can advertise here
easyfundraising
amazon

This month in BioNews

  • Popular
  • Recent
8 August 2022 • 2 minutes read

Placenta and organ formation observed in mouse embryo models

8 August 2022 • 2 minutes read

Lower hormone doses may improve IVF egg quality

8 August 2022 • 2 minutes read

Boosting muscle cell production of gene therapy proteins

1 August 2022 • 2 minutes read

First UK medical guidelines issued for trans fertility preservation

1 August 2022 • 2 minutes read

Male age has more impact on IVF birth rate than previously thought

15 August 2022 • 2 minutes read

Call to end ban on HIV-positive partner gamete 'donation'

15 August 2022 • 2 minutes read

Melanoma invades new tissues using nerve cell gene

15 August 2022 • 2 minutes read

Exceeding alcohol limits could damage DNA and accelerate ageing

15 August 2022 • 2 minutes read

Blood cell gene mutations affect mitochondria, increasing cardiovascular disease risk

15 August 2022 • 2 minutes read

Jumping gene helps immune system fight viruses

Subscribe to BioNews and other PET updates for free.

Subscribe
  • Twitter
  • Facebook
  • Instagram
  • LinkedIn
  • YouTube
  • RSS
Wellcome
Website redevelopment supported by Wellcome.

Website by Impact Media Impact Media

  • Privacy Statement
  • Advertising Policy
  • Thanks and Acknowledgements

© 1992 - 2022 Progress Educational Trust. All rights reserved.

Limited company registered in England and Wales no 07405980 • Registered charity no 1139856

Subscribe to BioNews and other PET updates for free.

Subscribe
PET PET

PET is an independent charity that improves choices for people affected by infertility and genetic conditions.

  • Twitter
  • Facebook
  • Instagram
  • LinkedIn
  • YouTube
  • RSS
Wellcome
Website redevelopment supported by Wellcome.

Navigation

  • About Us
  • Get Involved
  • Donate
  • BioNews
  • Events
  • Engagement
  • Jobs & Opportunities
  • Contact Us

BioNews

  • News
  • Comment
  • Reviews
  • Elsewhere
  • Topics
  • Glossary
  • Newsletters

Other

  • My Account
  • Subscribe

Website by Impact Media Impact Media

  • Privacy Statement
  • Advertising Policy
  • Thanks and Acknowledgements

© 1992 - 2022 Progress Educational Trust. All rights reserved.

Limited company registered in England and Wales no 07405980 • Registered charity no 1139856