JAN 20, 2020 8:49 AM PST

Open-Source Software Judges The Accuracy of Cancer Predicting Computer Programs

WRITTEN BY: Nouran Amin

Cancers are generally composed of diverse cells that vary in genetics—these variations often make a particular cancer more susceptible or resistant to a certain treatment. Pointing out these variations can help health care providers determine a suitable treatment that will likely succeed. However, conventional testing methods for these variations are prone to mishaps and so recent computer programs have made processes less challenging.

Watch this video below to learn more about understanding genetic testing and cancer:

Now, a study published in Nature Biotechnology aims to improve these cancer predictions by judging the accuracy of these computer methods.

"Our new framework provides a foundation which, over time as it is run against more tumours, will hopefully become a much-needed, unbiased, gold-standard benchmarking tool for assessing models that aim to characterize a tumor’s genetic diversity," says joint-lead author Maxime Tarabichi, postdoc in the Cancer Genomics Laboratory at the Crick.

The study specifically describes the development of an open-source software program that uses an algorithm to predict various measure of gentic diversity including proportion of cancerous cells in a tumor sample, number of genetically different groups of cancer cells within a sample, proportion of cells within each of these groups, genetic mutations in each group and the genetic relationship between groups.

Scientists analyzed 580 predictions and added new features to the tumour-simulation software program that can create more realistic tumours.

"Computer simulations in cancer genomics are helping us develop more accurate tools, as we understand where these tools perform well, and where they need improvement," says author Peter Van Loo, group leader in the Cancer Genomics Laboratory at the Crick. "Further developing these tools, so they more closely match real-life tumours, should ultimately help clinicians better match patients with personalised medicines."

Source: Science Daily

About the Author
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
DEC 01, 2019
Neuroscience
DEC 01, 2019
Are teens addicted to their phones?
Journalists quickly jumped to the conclusion that 23% of teenagers are addicted to their smartphones thanks to findings from a new study from King’s ...
DEC 22, 2019
Cell & Molecular Biology
DEC 22, 2019
Learning More About Cell Dynamics with Holo-Tomographic Microscopy
A new microscopy technique called holo-tomographic microscopy can generate 3D images and does not require labeling....
DEC 22, 2019
Clinical & Molecular DX
DEC 22, 2019
Can Google Health's AI interpret X-rays as well as radiologists?
Patients presenting with severe coughs, chest pain or suspected infections are more than likely to be sent for a chest X-ray -- the most commonly taken med...
JAN 15, 2020
Technology
JAN 15, 2020
Can A Computer Identify You By How You Dance?
We have heard of face and voice recognition software programs that work to ensure the identity of someone. But, now researchers are indicating that the way...
FEB 02, 2020
Space & Astronomy
FEB 02, 2020
Everything You Need to Know About Solar Orbiter
The Sun is something you see every day when you look up at the daytime sky, but despite residing right in plain sight, there’s still so much about th...
FEB 15, 2020
Clinical & Molecular DX
FEB 15, 2020
FDA nod for AI-powered technology to detect strokes
The US Food and Drug Administration (FDA) has provided clearance for a novel technology that uses artificial intelligence (AI) to detect strokes. The platf...
Loading Comments...