Breaking News
November 22, 2018 - Response to daily stressors plays important role in cognitive health of older adults
November 22, 2018 - Efficient method for producing induced pluripotent stem cells
November 22, 2018 - Report outlines inequalities in access to healthcare
November 22, 2018 - New research center will pave way to better diagnosis and treatment of skin diseases
November 22, 2018 - Mylan Initiates Voluntary Nationwide Recall of 15 Lots of Valsartan Tablets, USP, Amlodipine and Valsartan Tablets, USP, and Valsartan and Hydrochlorothiazide Tablets, USP, Due to the Detection of Trace Amounts of NDEA (N-Nitrosodiethylamine) Impurity Found in the Active Pharmaceutical Ingredient
November 22, 2018 - Lung Cancer Tumor Markers: MedlinePlus Lab Test Information
November 22, 2018 - Patchy distribution of joint inflammation resolved
November 22, 2018 - Researchers find crucial inhibitory role for signal peptide in GluK1 trafficking
November 22, 2018 - nutritional supplement, could slow some cancers
November 22, 2018 - Researchers awarded $7 million funding in Pancreatic Cancer Collective’s ‘New Therapies Challenge’
November 22, 2018 - UMN researchers focus on improving dermatologic care for sexual and gender minority patients
November 22, 2018 - Researchers harness visible light to develop safer building block for drug discovery
November 22, 2018 - Scientists identify key protein involved in Hantavirus Pulmonary Syndrome
November 22, 2018 - ACAAI: Oral Immunotherapy Is Protective in Peanut Allergy
November 22, 2018 - Arthritis and depression often occur together in older adults
November 22, 2018 - Scientists uncover unexpected ‘foreign’ genes in tiny itch-inducing chigger mite
November 22, 2018 - Negative social cues on tobacco packaging could help reduce smoking intentions
November 22, 2018 - Study finds no differences in quit rates for ‘dual users’ of both traditional and electronic cigarettes
November 22, 2018 - Immunity connects gut microbiota and age-related pathologies
November 22, 2018 - New diagnostics based on nanopore analytics and AI can identify single influenza virions
November 22, 2018 - Blocking activity of plasma protein can be possible way to protect against radiation-induced injury
November 22, 2018 - Secondhand Pot Smoke Found in Kids’ Lungs
November 22, 2018 - Air pollution may be linked to heightened dementia risk
November 22, 2018 - Brain implant lets people with limb paralysis compose and send emails, select videos and even play music, just by thinking
November 22, 2018 - Should health-care workers press charges against violent patients?
November 22, 2018 - Obesity linked to COPD in never-smokers
November 22, 2018 - Improving dementia treatment and staff training in care homes saves thousands of pounds per year
November 22, 2018 - Researchers identify genetic changes that could increase risk for death by suicide
November 22, 2018 - John Snow Labs launches new Data Market to help healthcare and life science innovators
November 22, 2018 - New inhibitor could hold key to treating Acute Respiratory Distress Syndrome
November 22, 2018 - Misconceptions about opioid use undermine pain control among Asian cancer patients
November 22, 2018 - Owlstone Medical named Medtech Company of the Year
November 22, 2018 - Anabolic steroids may increase risk of early death in men
November 22, 2018 - Researchers develop model that predicts transmissibility of viral zoonoses
November 22, 2018 - Evidence mounts that an eye scan may detect early Alzheimer’s disease
November 22, 2018 - Sensors could provide dexterity to robots, with potential surgical applications
November 22, 2018 - Why Are We Still So Fat?
November 22, 2018 - MRI scans may help predict dementia risk
November 22, 2018 - Groundbreaking research projects show how AI can be used to predict under diagnosed chronic diseases
November 21, 2018 - Stand Up to Cancer supports potential approach to more efficiently target pancreatic cancer
November 21, 2018 - Using smartphone confocal microscopes to stop cancer
November 21, 2018 - Self-care program for COPD patients reduces emergency room visits and burdensome symptoms
November 21, 2018 - Blueprint Medicines Announces Updated NAVIGATOR Trial Results in Patients with Advanced Gastrointestinal Stromal Tumors Supporting Development of Avapritinib Across All Lines of Therapy
November 21, 2018 - Cocaine adulterant may cause brain damage
November 21, 2018 - Amid the devastation, a Stanford doctor stitches up George, a search dog
November 21, 2018 - America’s Health-Care System Is Making the Opioid Crisis Worse
November 21, 2018 - Colorectal cancer screening reduces need for intense treatments among male patients
November 21, 2018 - Scientists find evidence of prions in the eyes of CJD patients
November 21, 2018 - Study explores individual and organizational risk factors for one-year mortality in ICU survivors
November 21, 2018 - Pulmonologists want more information on inhalation devices for COPD
November 21, 2018 - Cessation fatigue predicts relapse rate after attempts to quit smoking
November 21, 2018 - Special care should be taken with drugs that inhibit epigenetic factors, study suggests
November 21, 2018 - More than one in ten heavy cannabis users experience withdrawal after quitting cannabis
November 21, 2018 - Reflections on the California fires
November 21, 2018 - Donna Lynne Appointed to Key Leadership Role at CUIMC
November 21, 2018 - Smoke-free laws associated with reduced systolic blood pressure
November 21, 2018 - Achieving new guideline blood pressure goals may prevent 3 million cardiovascular events
November 21, 2018 - LDR brachytherapy for treating early-stage prostate cancer lacks conclusive data
November 21, 2018 - Older adults with CVD more likely to experience rapid functional decline
November 21, 2018 - Purified omega-3 and aspirin reduce pre-cancerous bowel polyps, shows study
November 21, 2018 - Study warns that potential epigenetic therapy may boost lung cancer stem cells
November 21, 2018 - Noise pollution in hospital impact quality and safety of healthcare
November 21, 2018 - Interventions to improve sleep may reduce risk of falls
November 21, 2018 - Outdoor air pollution linked to intellectual disabilities in children
November 21, 2018 - Study highlights need for better screening tools to detect maternal sepsis
November 21, 2018 - Higher Risk for Amputation, DKA With SGLT2 Inhibitors for T2DM
November 21, 2018 - Researchers stop ‘sneaky’ cancer cells in their tracks
November 21, 2018 - People who are afraid to draw their blood over-estimate the risk of fainting
November 21, 2018 - Personalized physical exercise reverses functional, cognitive deterioration in the elderly
November 21, 2018 - COPD linked to obesity in older women who have never smoked
November 21, 2018 - AHA: Cold-Weather Drinks Are Here, But Watch Out for the Calories
November 21, 2018 - Crowds line up at 1st East Coast pot shops
November 21, 2018 - Merck declares 2018 Life Science Award winners
November 21, 2018 - Many people underestimate the impact of sprains, say foot scientists
November 21, 2018 - Lower levels of protein make squamous carcinoma cells more invasive
November 21, 2018 - Study highlights a new predictor of type 2 diabetes
November 21, 2018 - NTU and TTSH join forces to improve doctor-patient communication
November 21, 2018 - New low-cost injectable hydrogel could help wounds heal faster
November 21, 2018 - Merck Announces Winners of 2018 Life Science Awards
November 21, 2018 - Check your medical records for dangerous errors
Big data strikes again — subdividing tumor types to predict patient outcome, personalized treatment

Big data strikes again — subdividing tumor types to predict patient outcome, personalized treatment

image_pdfDownload PDFimage_print

One of the first things I learned as a graduate student in cancer biology is that the idea of “cancer” as a single entity is a vast oversimplification of the disease.

It’s kind of like referring to all four-wheeled motorized vehicles as cars, when in reality there are a nearly infinite number of shapes, sizes, colors, makes and models of that type of transport, from garbage trucks to golf carts. Some go fast, some pull large loads and some can lug massive amounts of sports equipment and small children to soccer field after soccer field. Each has a specific purpose.

When I was in school there were just a few ways to tell different types of cancers apart from one another or to distinguish the defining characteristics of individual tumors. What organ did it affect? How did it look under the microscope? What types of mutations does it harbor?

Although it doesn’t feel like that long ago, it was practically the Dark Ages when one considers the volume of data and information that can now be gleaned about each patient’s disease. But integrating that data into useful treatment plans can still be challenging.

Now, pathologists and postdoctoral scholars Avantika Lal, PhD, Daniele Ramazzotti, PhD, and Arend Sidow, PhD, professor of pathology and of genetics, have devised a computer algorithm to bring together several types of genetic data about specific cancers such as lung or breast and divide those cancers into many smaller groups that share common biological traits. This practice can yield important information about tumor behavior and patient survival, they found. (To extend the car analogy, I probably have more in common with other drivers of 2004 dark green Honda Pilots than I do with people who drive newer red Ferraris).

Lal and Ramazzotti named their algorithm “Cancer Integration via Multikernel Learning,” or CIMLR. They published their results last week in Nature Communications.

As Lal explained in an email to me:

CIMLR allows us to classify individual cancers based on the underlying genetic changes in the tumor. Using CIMLR, we identified genomic subtypes for 36 types of cancer.

Tumors belonging to the different subtypes have very different underlying biology and so behave differently. By classifying patients into these subtypes, we can predict their chance of survival and their likelihood of relapse after treatment.

CIMLR works by integrating many different types of data about a tumor, including changes in gene expression, genetic mutations, variations in gene copy number (a change that often occurs in cancers when stretches of DNA are repeated or deleted during cell division) and promoter methylation (a physical tag that can trigger the expression or repression of downstream genes).  Until now it’s been difficult to combine these data and consider their effect on cancer growth as a whole.

The researchers applied CIMLR to 36 types of cancer, including liver, lung, kidney, melanoma and breast from more than 6,000 people. In 27 of the 36 cancer types, they found significant differences in patient survival among the various subcategories discovered by CIMLR.

Identifying patterns associated with poor patient outcomes could improve a clinician’s ability to better tailor treatments to individual patients, the researchers said.

As Ramazzotti explained:

By studying the biological characteristics that are defining different subtypes, we could potentially develop personalized treatments to improve the care of patients.

Lal and Ramazzotti found that CIMLR outperforms other currently available tools in its speed, accuracy, and ability to predict patient survival. They also point out that this type of “multi-omic” approach could be useful in other situations.

As Lal said:

We are applying CIMLR to other cancer datasets, and making it easier to classify new patients into the subtypes we discover.

But we also want to make CIMLR accessible for scientists working on other diseases. The approach that we applied to cancer can be used to identify subtypes of other complex diseases. For example, a European group has already used CIMLR to identify subtypes of Alzheimer’s disease with different brain features and there is interest in using it to find subtypes of human gut microbiomes. We are excited to see our method advance other medical fields.

Photo by AOMSIN

Tagged with:

About author

Related Articles