Researchers use machine learning to rank cancer drugs in order of efficacy
Researchers from Queen Mary University of London have developed a machine learning algorithm that ranks drugs based on their efficacy in reducing cancer cell growth
2021-03-25
(Press-News.org) Researchers from Queen Mary University of London have developed a machine learning algorithm that ranks drugs based on their efficacy in reducing cancer cell growth. The approach may have the potential to advance personalised therapies in the future by allowing oncologists to select the best drugs to treat individual cancer patients.
The method, named Drug Ranking Using Machine Learning (DRUML), was published today in Nature Communications and is based on machine learning analysis of data derived from the study of proteins expressed in cancer cells. Having been trained on the responses of these cells to over 400 drugs, DRUML predicts the best drug to treat a given cancer model.
Speaking of the new method, Professor Pedro Cutillas from Queen Mary University of London, who led the study, said: "DRUML predicted drug efficacy in several cancer models and from data obtained from different laboratories and in a clinical dataset. These are exciting results because previous machine learning methods have failed to accurately predict drug responses in verification datasets, and they demonstrate the robustness and wide applicability of our method."
The research was funded by The Alan Turing Institute, Medical Research Council, Barts Charity and Cancer Research UK.
How does DRUML work?
The team used datasets derived from proteomics (the study of proteins within cells) and phosphoproteomics (the study of how these proteins are modified) analyses of 48 leukaemia, oesophagus and liver cancer cell lines as the input for DRUML to build models that may be applied to leukaemia and solid tumours.
By training the models using the responses of these cells to 412 cancer drugs listed in drug response repositories, DRUML was able to produce ordered lists based on the effectiveness of the drugs to reduce cancer cell growth. The team then verified the predictive accuracy of the models using data obtained from 12 other laboratories and a clinical dataset of 36 primary acute myeloid leukaemia samples.
Importantly, as new drugs are developed moving forwards, DRUML could be retrained to capture all clinically relevant cancer drugs.
Machine learning and personalised medicine
Cancers of the same type exhibit great variation in their genetic makeup and characteristics from patient to patient. In the clinic, this variation translates to patients having different responses to therapy. To address this issue, the field of personalised medicine aims to combine genetic insights with other clinical and diagnostic information to identify patterns that can allow clinicians to predict patient responses to therapies and select the most effective interventions.
The application of artificial intelligence and machine learning to biomedicine promises to aid personalised medicine and transform how cancers are diagnosed and treated in the future. This study represents a significant advancement in artificial intelligence in biomedical research, and demonstrates that machine learning using proteomics and phosphoproteomics data may be an effective way of selecting the best drug to treat different cancer models.
INFORMATION:
Research paper: 'Drug ranking using machine learning systematically predicts the efficacy of anti-cancer drugs'. Nature Communications. DOI 10.1038/s41467-021-22170-8
Available here after embargo lifts: http://www.doi.org/10.1038/s41467-021-22170-8
ELSE PRESS RELEASES FROM THIS DATE:
2021-03-25
The interiors of nonflowering trees such as pine and ginkgo contain sapwood lined with straw-like conduits known as xylem, which draw water up through a tree's trunk and branches. Xylem conduits are interconnected via thin membranes that act as natural sieves, filtering out bubbles from water and sap.
MIT engineers have been investigating sapwood's natural filtering ability, and have previously fabricated simple filters from peeled cross-sections of sapwood branches, demonstrating that the low-tech design effectively filters bacteria.
Now, the same team has advanced the technology and shown that it works in real-world situations. They have fabricated new xylem filters that can filter out pathogens ...
2021-03-25
An international team of scientists has found evidence that SARS-CoV-2, the virus that causes COVID-19, infects cells in the mouth. While it's well known that the upper airways and lungs are primary sites of SARS-CoV-2 infection, there are clues the virus can infect cells in other parts of the body, such as the digestive system, blood vessels, kidneys and, as this new study shows, the mouth. The potential of the virus to infect multiple areas of the body might help explain the wide-ranging symptoms experienced by COVID-19 patients, including oral symptoms such as taste loss, ...
2021-03-25
Philadelphia, March 25, 2021 - Dining out is a popular activity worldwide, but there has been little research into its association with health outcomes. Investigators looked at the association between eating out and risk of death and concluded that eating out very frequently is significantly associated with an increased risk of all-cause death, which warrants further investigation. Their results appear in the Journal of the Academy of Nutrition and Dietetics, published by Elsevier.
Eating out is a popular activity. The US Department of Agriculture recently estimated that Americans' daily energy intake from food away from home increased from 17 percent in 1977-1978 to 34 percent in 2011-2012. At the same time, the number of restaurants has ...
2021-03-25
WASHINGTON - A food preservative used to prolong the shelf life of Pop-Tarts, Rice Krispies Treats, Cheez-Its and almost 1,250 other popular processed foods may harm the immune system, according to a new peer-reviewed study by Environmental Working Group.
For the study, published this week in the International Journal of Environmental Research and Public Health, EWG researchers used data from the Environmental Protection Agency's Toxicity Forecaster, or ToxCast, to assess the health hazards of the most common chemicals added to food, as well as the "forever chemicals" known as PFAS, which can migrate to food from packaging.
EWG's analysis of ToxCast data showed that the preservative tert-butylhydroquinone, ...
2021-03-25
New Edith Cowan University (ECU) research has found that despite having the best intentions, most people give up on their New Year resolutions within the first month.
The study also revealed that approximately half the people surveyed had the same, or nearly the same, resolution as in the previous year, and more than half of the resolutions listed focused on either diet or exercise.
The research, led by ECU Associate Professor Joanne Dickson, investigated personal goal factors that predicted greater wellbeing and sticking with one's most important New Year resolution over time. Around 180 Australian and UK participants took part in an online survey over a two-month period. ...
2021-03-25
The thermodynamic state of the tropical atmosphere plays an important role in the development of tropical cyclone (TC) intensity. A TC imports thermodynamic energy from ocean-air heat and moisture fluxes and exports heat aloft at the much colder upper troposphere, through a radially and vertically directed overturning circulation in a TC. The work done through this cycle drives the TC's winds.
A negative response of cloud water in the lower troposphere to dust aerosol optical depth (AOD) has recently been reported in Atmospheric and Oceanic Science Letters (https://doi.org/10.1016/j.aosl.2020.100028) by Dr. Zhenxi Zhang from the Inner Mongolia University of Technology, Hohhot, China, by analyzing MERRA-2 reanalysis data and GCM simulations from CMIP6.
"The ...
2021-03-25
Philadelphia, March 25, 2021 - Anabolic androgenic steroids (AAS), a synthetic version of the male sex hormone testosterone, are sometimes used as a medical treatment for hormone imbalance. But the vast majority of AAS is used to enhance athletic performance or build muscle because when paired with strength training. AAS use increases muscle mass and strength, and its use is known to have many side effects, ranging from acne to heart problems to increased aggression. A new study now suggests that AAS can also have deleterious effects on the brain, causing it to age prematurely.
The report appears in Biological Psychiatry: Cognitive Neuroscience and ...
2021-03-25
WEST LAFAYETTE, Ind. - A Purdue University innovator has developed a new approach to creating popular thin films used for devices across a broad range of fields, including optics, acoustics and electronics.
Epitaxial lithium niobate (LNO) thin films are an attractive material for electronics and other devices. These films offer flexibility and other properties that are important to manufacturers.
The challenge is that these devices demand high-quality thin films that can be difficult to grow and produce. Haiyan Wang, a Purdue materials engineer, developed a new approach to creating these films. The work is published in Advanced Photonics Research.
"We created an approach ...
2021-03-25
PLYMOUTH MEETING, PA [March 25, 2021] -- New recommendations to advance racial equity, ways to mitigate the impacts of the COVID-19 pandemic on cancer care, and ongoing strategies for preventing and controlling HPV-associated cancers led the conversation at the National Comprehensive Cancer Network® (NCCN®) 2021 Virtual Annual Conference March 18-20. More than 1,300 attendees from across the United States and more than 40 countries met online to learn about updates to the NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines®) and new research in the field. Sessions explored supportive care and ways to help survivors return to work, updates on best ...
2021-03-25
For the first time, scientists have succeeded in continuous monitoring of a subglacial discharge plume, providing a deeper understanding of the glacier-fjord environment.
As marine-terminating glaciers melt, the fresh water from the glacier interacts with the seawater to form subglacial discharge plumes, or convective water flows. These turbulent plumes are known to accelerate the melting and breakup (calving) of glaciers, drive fjord-scale circulation and mixing, and create foraging hotspots for birds. Currently, the scientific understanding of the dynamics of subglacial plumes based on direct measurements is limited to isolated instances.
A team of scientists consisting of Hokkaido University's Assistant Professor Evgeny A. Podolskiy and Professor Shin Sugiyama, and the ...
LAST 30 PRESS RELEASES:
[Press-News.org] Researchers use machine learning to rank cancer drugs in order of efficacy
Researchers from Queen Mary University of London have developed a machine learning algorithm that ranks drugs based on their efficacy in reducing cancer cell growth
