Applying machine learning to biomedical science

August 17, 2020

With potential application diagnosing cancer or predicting how viruses, such as HIV, attack human cells, machine learning is opening promising new areas of application for bioinformatics - the data science of molecular biology. Dr Pengyi Yang from the Charles Perkins Centre and School of Mathematics and Statistics with colleagues has summarised the latest developments in this emerging field in a review article in Nature Machine Intelligence.

Latest techniques are bringing together two previously disparate approaches to machine learning: ensemble methods and deep learning.

Just like 'many heads are better than one', ensemble deep learning combines multiple 'computer brains' to achieve high levels of performance. Dr Yang summarises the latest developments in ensemble deep learning and its application in a range of biological and biomedical fields; highlights achievements unattainable by traditional methods; and maps out its potential to revolutionise molecular biological and biomedical sciences.
'Ensemble deep learning in bioinformatics', Nature Machine Intelligence
DOI: 10.1038/s42256-020-0217-y
Authors: Yue Cao, Thomas Andrew Geddes, Jean Yee Hwa Yang, Pengyi Yang

Corresponding author:

DECLARATION: The authors receive funding from the Australian Research Council, National Health and Medical Research Council and the University of Sydney.

University of Sydney

Related Viruses Articles from Brightsurf:

Sorting out viruses with machine learning
Researchers at Osaka University created a machine-learning system to identify single viral particles that cause respiratory diseases, including coronavirus, using silicon nanopores.

The rafts used by viruses
The study may suggest new strategies to limit virus attacks and prevent or combat diseases like Sars and Covid-19 based on biomedical and engineering principles.

Animals keep viruses in the sea in balance
A variety of sea animals can take up virus particles while filtering seawater for oxygen and food.

Hundreds of novel viruses discovered in insects
New viruses which cause diseases often come from animals. Well-known examples of this are the Zika virus transmitted by mosquitoes, bird flu viruses, as well as the MERS virus which is associated with camels.

First video of viruses assembling
For the first time, researchers have captured images of the formation of individual viruses, offering a real-time view into the kinetics of viral assembly.

Plant viruses may be reshaping our world
A new review article appearing in the journal Nature Reviews Microbiology highlights the evolution and ecology of plant viruses.

Checkmate for hepatitis B viruses in the liver
Researchers at Helmholtz Zentrum M√ľnchen and the Technical University of Munich, working in collaboration with researchers at the University Medical Center Hamburg-Eppendorf and the University Hospital Heidelberg, have for the first time succeeded in conquering a chronic infection with the hepatitis B virus in a mouse model.

How viruses outsmart their host cells
Viruses depend on host cells for replication, but how does a virus induce its host to transcribe its own genetic information alongside that of the virus, thus producing daughter viruses?

Mobile, instant diagnosis of viruses
In a first for plant virology, a team from CIRAD recently used nanopore technology to sequence the entire genomes of two yam RNA viruses.

How ancient viruses got cannabis high
THC and CBD, bioactive substances produced by cannabis and sought by medical patients and recreational users, sprung to life thanks to ancient colonization of the plant's genome by viruses, U of T researchers have found.

Read More: Viruses News and Viruses Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to